Member Articles

Recent Documents

Sort By:

Member Articles

Connecting Microsoft 365 Copilot to Qlik's MCP Server with the Agents Toolkit

This article will walk you through how to create a declarative agent for Copilot that uses an MCP plugin to connect MSFT 365 Copilot with Qlik’s MCP S... Show More
This article will walk you through how to create a declarative agent for Copilot that uses an MCP plugin to connect MSFT 365 Copilot with Qlik’s MCP Server. Please note, there are several prerequisites that you must meet to successfully execute the steps in this guide.

Note: at the time of writing, using plugins to connect to an MCP Server is in public preview.

Prerequisites
- Requirements for Copilot extensibility options
- Visual Studio Code
- Microsoft 365 Agents Toolkit version 6.3.x or later
- Qlik Tenant Admin Access
Create the Agent
1. Open Visual Studio Code and select the Microsoft 365 Agents Toolkit icon in the left-hand Activity Bar.
1. Select Create a New Agent/App in the Agents Toolkit task pane.
2. Select Declarative Agent.
3. Select Add an Action, then select Start with an MCP Server.
4. Enter your tenant’s MCP server URL: https://<your tenant URL>/api/ai/mcp
5. Choose a location for the agent project.
6. Enter a name for the agent.
Once you complete these steps, Agents Toolkit generates the required files for the agent and opens a new Visual Studio Code window with the agent project loaded.

Register an OAuth App with Your Tenant
1. In your browser, navigate to your tenant.
2. Navigate to the Administrative Activity Center > OAuth.
1. Create a new client with the following configuration.
  - Client Type: Web
  - Name: whatever name you would like
  - Scopes: user_default and mcp:execute
  - Redirect URLs:
  - http://127.0.0.1:33418
  - http://127.0.0.1:33418/
  - https://vscode.dev/redirect
  - https://teams.microsoft.com/api/platform/v1.0/oAuthRedirect
http://127.0.0.1:33418, http://127.0.0.1:33418/, and https://vscode.dev/redirect are redirect URLs for VS Code used for development and testing.https://teams.microsoft.com/api/platform/v1.0/oAuthRedirect will be the redirect URL when the plugin is provisioned and deployed.
1. Create the client configuration and make sure to save the Client ID and Client Secret in a secure location, as we will need to use that information throughout setup.
Add Tools from the MCP Server
1. Within VS Code, open the .vscode/mcp.json file. Select the Start button in the file editor.
1. You will receive a message saying Dynamic Client Registration not supported. Click Copy URIs & Proceed.
2. Add your Client ID and Client Secret that you copied from the Qlik OAuth step.
3. You will be prompted to authenticate, click Allow.
4. You will be prompted to open an external website, click Open.
5. You should be redirected to Qlik’s OAuth approval page, click Approve to authorize your agent to access your Qlik MCP Server.
6. Within VS Code and in the mcp.json file, select the ATK: Fetch action from MCP button in the file editor, then select ai-plugin.json.
1. Select which tools you would like the agent, and ultimately a user, to have access to. If desired, you can choose all tools.
2. Select OAuth (with static registration) as the authentication type.
Provision the Agent and Test in Copilot
1. In Visual Studio Code, select the Microsoft 365 Agents Toolkit icon in the left-hand Activity Bar.
2. In the Accounts pane, select Sign in to Microsoft 365. (If you’re already signed in, continue to the next step.)
3. Confirm that both Custom App Upload Enabled and Copilot Access Enabled display under your Microsoft 365 account. If they don’t, check with your organization admin.
4. In the Lifecycle pane, select Provision.
5. When asked to Enter client id for OAuth registration…, enter your client ID.
6. When asked to Enter client secret for OAuth registration…, enter your client secret.
7. When asked for scopes enter user_default,mcp:execute and press Enter to continue.
8. Read the message in the dialog and select Confirm to continue.
9. Wait for the toolkit to report that provisioning finished. NOTE: provisioning might fail initially but often works after retrying.
10. Your Agent should now be available to test within Copilot. Please note that the agent will only be available to you as the owner. To share the agent with others, please see the next section.
Deploying and Publishing

Please follow Microsoft’s guidance on Publishing agents for Microsoft 365 Copilot.

Considerations
- Declarative agents are limited to 4,096 tokens of shared context, so keep each agent focused on a single purpose. For example, create one agent scoped to read-only analytical queries and another scoped to development tasks like building scripts, sheets, and charts.
- Follow Microsoft’s guidance on writing effective agent instructions, but keep in mind the instructions count against the response token limit.
- For cases where greater control over orchestration, underlying models, and token utilization is needed, please see Microsoft’s guidance on custom engine agents.
- Since you configure which MCP tools are made available within your agent, you will need to update and re-publish your agent anytime you want to add a new tool to the agent.
References
- Microsoft 365 Copilot Extensibility Overview
- Build plugins from an MCP server for Microsoft 365 Copilot
Show Less
By banderson735 2026-04-08 / 11:36 AM

0 2 189
Member Articles

Beyond the Chart: The Impact of Design on User Experience and Dashboard Quality

Why Does UX Matter in Dashboards?Have you ever opened a dashboard and felt lost, unsure of where to look first? Or needed a quick piece of information... Show More
Why Does UX Matter in Dashboards?
Have you ever opened a dashboard and felt lost, unsure of where to look first? Or needed a quick piece of information, only to find it buried among too many charts and filters that did not work well together?
That is exactly what UX, or User Experience, is about. When we talk about dashboards, UX is not just about making them look more attractive. It is about efficiency, clarity, and supporting better decision-making. UX means ensuring that the people using a dashboard can find what they need in the simplest way possible1. Dashboards are not just collections of charts. They are decision-making tools, and poor user experience can lead to errors, wasted time, and even misguided decisions.
In a world where data is everywhere, having access to it is not enough. We need to turn data into clear and fast insights. That is where thoughtful design becomes essential. Using colors strategically to highlight important information, organizing data in a logical and hierarchical way, and choosing the right chart types for each kind of information are some of the practices that can significantly improve the user experience. In addition, incorporating user feedback can help refine and optimize a dashboard so it better meets their needs.

How Much Data Do We Create Every Day?
When we look at today’s landscape, it is impossible to ignore the enormous amount of data we generate every single day. This chart illustrates clearly: The exponential growth in the volume of data created globally, year after year.

If we look back at 2010, the amount of data being generated still seemed somewhat “manageable.” But notice how, starting around 2015, the curve begins to rise much more sharply.
By 2025, approximately 175 zettabytes of data had been generated, and the trend is expected to continue growing. In fact, that is more than the total amount of data generated from 2010 to 2020 combined2.
What does this mean in practice?
It means that as the volume and complexity of data increase, analyzing information stops being a natural advantage and often starts becoming an obstacle.
In other words, having all this data available is not enough if it is disorganized, confusing, or difficult to interpret. That is exactly where design, user experience, and well-built dashboards become essential.
There is also a very common belief that the more options we have, the better. After all, more choices are often associated with greater freedom, more control, and, as a result, greater satisfaction.
What does this mean in practice?
As the volume and complexity of data continue to grow, analyzing information stops being a natural advantage and often becomes an obstacle.
In other words, it is not enough to have all this data available if it is disorganized, confusing, or difficult to interpret. This is exactly where the importance of design, user experience, and well-built dashboards comes in.
There is also a very common belief that the more options we have, the better. After all, more choices seem to imply more freedom, more control, and, consequently, greater satisfaction.
The Paradox of Choice
There is a very common belief that the more options we have, the better. After all, more choices seem to mean more freedom, more control, and, therefore, greater satisfaction.
Sheena Iyengar of Columbia University and Mark Lepper of Stanford challenged that assumption in their well-known 2000 study, When Choice Is Demotivating: Can One Desire Too Much of a Good Thing? 3
Through a series of experiments conducted across three studies, both in laboratory settings and in real-world environments, they reached an important conclusion: having more options can lead to less action, less satisfaction, and even greater frustration.
To better understand whether more options help or hinder decision-making, the researchers designed a very practical experiment in a supermarket.
They set up a gourmet jam tasting booth that operated for two Saturdays, five hours each day.
In total, approximately 754 shoppers were observed. However, the analysis focused on the people who stopped at the booth to try the jam.
So, how was the experiment conducted?
There were two different scenarios, alternating throughout the day:
Scenario 1 – Limited choice: shoppers were presented with only 6 jam flavors to sample.
Scenario 2 – Extensive choice: in this case, the booth displayed a much wider variety, offering 24 jam flavors.
The goal was to observe how people behaved in these two different contexts: Would more options generate more interest? More purchases? Or simply more confusion?
Some might say the results were counterintuitive.
When 24 jam flavors were available, 60% of shoppers were drawn to the booth. They stopped, looked, and sampled the products.
When only 6 flavors were available, the level of attraction was lower: 40% of shoppers stopped.
In other words, more options really do attract more attention. They seem more interesting and more inviting.
But when we look at what truly matters action, decision-making, and purchase behavior the results change completely:
Only 3% of the people who encountered the 24-flavor display bought a jar of jam.
On the other hand, when there were only 6 options, the purchase rate rose to 30%.
So, people who were given fewer options were far more likely to make a decision and complete a purchase.
The conclusion of this study is clear: having many options may seem more appealing at first, but it can become demotivating when it is time to decide.
Yes! This is the paradox of choice.
That is why we need to reinforce the good old idea that less is more, and that good design is not just about aesthetics, it is about strategy.
Some Data on Dashboard Abandonment
If up to this point, we have been discussing how an excess of information and options can create paralysis, these numbers show the real impact of that problem in the world of dashboards.
The first figure comes from the Luzmo BI Adoption Report, published in March 2025. It reveals an alarming reality: only 20% of dashboards are used frequently, whether daily or weekly. This means that around 80% are abandoned or used very rarely4.
What does this tell us? It shows that there are a huge number of dashboards that simply do not create value, do not support the people who are supposed to use them, and end up being forgotten.
The second figure comes from a study by Yellowfin in partnership with Dresner Advisory, which found that 41.7% of users spend less than one hour per week looking at dashboards5.
In other words, a large share of users interacts with dashboards only superficially. This may point to two problems: either the dashboards are not relevant, or they are so difficult to understand that users prefer not to engage with them.
These numbers make one thing very clear: creating dashboards is not just about putting data on the screen. It is about designing an experience that truly helps people navigate information, interpret data easily, and make fast, confident decisions.
UX and Design Best Practices for Dashboards
That is why UX for Analytics is essential to creating value. Without good user experience, data does not turn into decisions. And that is exactly the problem we will continue exploring from this point forward.
Here, I have gathered some best practices for creating dashboards with the user experience in mind. These include staying focused on the objective, ensuring a clear information hierarchy, using colors correctly, minimizing visual noise, paying attention to alignment and spacing, choosing the right chart type, and making sure the dashboard delivers actionable insights.

It may seem obvious, but it is very common to see dashboards turn into large walls of charts without a defined purpose. And that creates more confusion than clarity.
Focus On The Objective
When we talk about focusing on the objective, we mean answering questions such as: Who is going to use this dashboard? What decision do they need to make? What is the main question that needs to be answered quickly?
For example, a dashboard for the finance team needs to answer different questions than a dashboard for the sales team. It does not make sense to mix everything in the same place.
A good exercise is this: if you had to explain the purpose of your dashboard in one sentence, what would it be? If you cannot answer that clearly, it is a sign that the objective is still not well defined.
Having that focus from the beginning guides every other design decision: what should go at the top, what should be treated as detail, and what can be left out.
Without a clear objective, there is no hierarchy, there is no simplicity, and the user experience will be confusing.
Information Hierarchy
With a clear and well-defined objective, it becomes much easier to organize what matters most.
Think of it as a pyramid: the top represents the most important information, such as KPIs, key metrics, and critical statuses. These are the elements that should appear at the top of the dashboard or receive the greatest visual emphasis.
In the middle, you place the supporting data, the information that helps explain the context behind the main indicator.
At the base, you include complementary details or more granular data for those who want to explore further.
Without hierarchy, everything appears to carry the same weight. And when everything is important, nothing is important. The result is that the user gets lost and cannot tell what should be prioritized.
That is why you should always ask: What does the user need to see first? What is essential for decision-making? What can remain in the background?
Hierarchy is not only about position on the screen. Color, font size, icons, and spacing also help guide the eye toward what matters most.
Correct Use of Colors
It is important to understand that color is information, not decoration7.
You should work with two distinct palettes. One should contain the client’s base brand colors, and the other should be an alert palette ranging from green to red.
🟢 Green: signals something positive, normal, or within expectations, usually meaning OK.
🟡 Yellow: indicates attention, something being monitored, or an early warning level.
🟠 Orange: points to higher risk, an ongoing issue, or a situation where immediate action may be needed.
🔴Red: represents a critical alert, failure, or a situation that is out of control and requires action.
Another important tip is to maintain consistency. If you use red to indicate a problem, do not use red somewhere else to represent something positive. This kind of consistency helps users quickly interpret what they are seeing.
It is also essential to consider contrast. Light text on a light background becomes difficult to read, just as charts with very similar shades create confusion instead of clarity.
Minimize Visual Noise
Visual noise happens when there are too many elements on the screen that do not help users understand the information, such as heavy gridlines, unnecessary borders, colored backgrounds, shadows, or decorative icons with no real function.
These details compete with the actual data. In the end, the user spends more time trying to figure out what is relevant and what is not.
Every element on the screen should have a clear purpose: guiding the eye, highlighting information, or structuring the reading flow8.
Let’s look at this example here 6: On the left side, each block seems to have the same level of importance, and there is no clear hierarchy. There are also several decorative or repeated elements that do not add value. This creates confusion and makes the user spend more time trying to understand what really matters.
Similar metrics appear in different areas without a clear need. At the bottom, we have a “Revenue and Orders over Time” chart, and right above it, other isolated charts showing the same segmented data, but without a clear connection. This duplicates information without adding analytical value. Customer Satisfaction is placed in the middle of the KPIs, with no clear connection to the performance metrics it influences, such as revenue by category or repeat purchases.
Notice that pieces of information that are part of the same story, such as revenue trend, revenue target, and customer satisfaction, are spread across distant sections. This forces the user to jump from one side to the other, creating unnecessary cognitive effort.
Everything is also crowded together, with little visual breathing room, which makes it harder to distinguish each section clearly.
Now let’s look at the panel on the right, labeled “Better.” This is where we can clearly see how applying UX best practices makes a real difference.
At first glance, we can already notice a clear hierarchy. The most important information is highlighted at the top, such as the main revenue KPI. Supporting metrics appear just below it, organized within the proper context.
The design is cleaner, with fewer unnecessary borders and gridlines, and it uses white space to separate sections. This creates visual breathing room and helps the user understand where each group of information begins and ends.
In addition, related data is grouped logically. For example, revenue trend and revenue target appear side by side, making comparison much easier. The filter panel is also well positioned, allowing users to adjust the analysis without creating confusion.
Colors are used consistently, highlighting only what is relevant and avoiding visual clutter. The layout is simple, but highly functional, because it provides context and guides the user’s attention to what matters most.
Remember: the cleaner the design, the faster the user can understand the data.
Alignment and Spacing
A dashboard with misaligned charts, inconsistent block sizes, or uneven spacing between elements creates a sense of disorder, even when the data itself is correct.
When elements are properly aligned, such as columns, charts, and KPIs, the eye moves through the content naturally and without effort. The brain can understand the logical structure without having to figure out where each section begins or ends.
In addition, since we read from left to right and from top to bottom, it is important to maintain that same logic in the dashboard layout as well.

A good practical tip is to use grids and guides to keep blocks aligned, and to apply consistent margins and padding. Small details like these communicate care and professionalism.
Choosing the Right Chart Type
Each chart type serves a specific purpose. It highlights a particular relationship within the data and helps users understand the main message with minimal effort.
The figure below works as a practical visual guide to help choose the most appropriate chart type based on the objective of the analysis.

In the left column, we see different key ideas that may guide the way we analyze data. For example: Do you want to show a single number? Compare values across groups? Present proportional composition? Visualize changes over time? Or understand the relationship between metrics?
Each of these questions points to a set of recommended chart types. For example, if the goal is to show changes over time, line charts or area charts are usually the best options. To compare values across categories, bar charts or column charts tend to work better. And to show the composition of a whole, pie charts, donut charts, or treemaps can make sense, as long as they are used correctly.
The most important thing to understand is that a chart is not just decoration. It is a bridge between the data and the insight we want to extract. A poorly chosen chart can confuse the user or even distort the interpretation of the data.
That is why this kind of matrix is so helpful. It helps prevent classic mistakes, such as using a pie chart to compare very different values or a line chart to display data with no time progression.
Use it as a checklist: What question am I trying to answer? From there, choose the chart type that makes the most sense for telling that story as clearly as possible.
So now we arrive at the final item in our list of best practices.
Actionable Insight
Think about how a GPS or Waze works: you need to know where you are right now, which is your current result, represented by Outcome Metrics. You also need to understand what is influencing your route, such as traffic, roadwork, or road conditions, which are your Driver Metrics. Most importantly, you need practical guidance on how to adjust your path, which is where Actionable Metrics come in.
Without that, the map is just a drawing. But when these three layers work together, the dashboard stops being a panel of static data and becomes a navigation system for decision-making.

The Outcome Metric shows the starting point and the destination. It represents the view of the final result.
The Driver Metrics are the factors you monitor to understand why you are ahead or behind, just as a GPS shows traffic, roadblocks, or alternative routes.
And the Actionable Metrics are like alerts and voice commands: “Turn left now,” “Take a faster route.” They tell you what to do in practice in order to get where you want to go.
Turning dashboards into data navigation systems is one of the solutions that could help prevent the dashboard abandonment problem mentioned earlier in this article.
Conclusion
A dashboard is much more than a collection of charts placed on a screen. It is a tool designed to help people make sense of information, identify what matters most, and take action with confidence.
In a world where the volume of data continues to grow at an overwhelming pace, the challenge is no longer just accessing information. The real challenge is presenting it in a way that is clear, relevant, and easy to use. Too much data, too many options, and poor organization can create confusion instead of clarity. And when that happens, even the most technically well-built dashboard can fail to deliver value.
That is why UX and design are not secondary concerns in analytics. They are essential. When we apply good practices such as focusing on the objective, creating a clear information hierarchy, using color intentionally, reducing visual noise, aligning elements properly, and choosing the right chart types, we make dashboards more than visually appealing. We make them useful.
A well-designed dashboard helps people understand faster, decide better, and act sooner. And that is ultimately the goal of analytics: not simply to display data, but to turn data into insight, and insight into action.
References:
How to Design Better Dashboards [Video]. YouTube.
https://www.youtube.com/watch?v=s-Il4S0OvzQ
Statista. Global data creation growth statistics.
https://www.statista.com/?srsltid=AfmBOopieefYKjcXZiGL93eDj-b8cYuLMs3Q0zCwj80-m1w11zd50hos
Iyengar, S. S., & Lepper, M. R. (2000). When Choice Is Demotivating: Can One Desire Too Much of a Good Thing?
Luzmo. Is Data Visualization Dead?
https://www.luzmo.com/blog/is-data-visualization-dead
Yellowfin BI. Need More Than Dashboards to Run a Data-Driven Business.
https://www.yellowfinbi.com/blog/need-more-than-dashboards-to-run-data-driven-business#:~:text=in%20...
Metabase. Top 5 Dashboard Fails.
https://www.metabase.com/blog/top-5-dashboard-fails
Pedrosa, T., & Toutain, L. [PDF document].
https://cinform-anteriores.ufba.br/vi_anais/docs/TaisPedrosaLidiaToutain.pdf
Lucas. Menos é Mais: Pare de “Suar” seu Dashboard no Power BI. Medium, February 4, 2026.
Interaction Design Foundation. What Is Visual Hierarchy?
https://ixdf.org/literature/topics/visual-hierarchy
Show Less
By priscilarubim 2026-03-26 / 01:11 PM

5 10 335
Member Articles

Qlik and Snowflake Cortex

If you are a Snowflake customer you have probably seen the left side of this image frequently. Snowflake Intelligence is legit cool and you've drea... Show More
If you are a Snowflake customer you have probably seen the left side of this image frequently. Snowflake Intelligence is legit cool and you've dreamed of ways for it to impact your business.

If you are a Qlik and Snowflake customer you have probably seen the left side of this image frequently, and thought "Wow I sure wish I could take advantage of Snowflake Intelligence within my Qlik environment to impact my business. Feel free to do your celebration dance because this post is designed to walk you through how Qlik can work with Snowflake Cortex AISQL as well as Snowflake Cortex Agents (API).

Both series are designed in 3 part Show Me format. The first video for each will frame the value you can attain. The second video will help you drool as you begin imagining your business implementing the solution. Finally I conclude each series for those that get tapped on their shoulder to actually make the solutions work.

Qlik + Snowflake Cortex AISQL

In this comprehensive three-part series exploring the integration of Qlik and Snowflake Cortex AI-SQL, I guide viewers from executive vision to hands-on implementation. While demonstrating how organizations can democratize AI capabilities across their entire analytics ecosystem—without requiring data science expertise.

Series Flow:
- Video 1: Show Me What's Possible - This opening video presents the strategic value of combining Qlik's governed analytics with Snowflake Cortex AI-SQL. Executives will see real-world scenarios demonstrating how AI-powered analytics transforms decision-making without requiring technical expertise. Showing how organizations ask complex questions in natural language and get instant insights.
- Video 2: Show Me How It Works - Explores technical architecture without code-level complexity, targeting solution architects and technical managers who need to understand system mechanics. We'll demonstrate data flow from Snowflake's semantic layer through Cortex functions into Qlik's visualization engine, showing how LLM capabilities integrate with BI workflows. .
- Video 3: Show Me How to Build It - This technical deep-dive is designed for developers, data engineers, and hands-on architects who need to actually implement the Qlik-Snowflake Cortex integration in their environments. We'll start from scratch with environment setup, authentication configuration, and establishing secure connections between platforms.
Qlik + Snowflake Cortex Agents

This series demonstrates how to combine Qlik's associative analytics engine with Snowflake's AI-powered semantic intelligence to transform natural language questions into interactive, fully contextualized insights.

Series Flow:
- Video 4: Show Me What's Possible - Introduces the game-changing capabilities of this integration—from automatic filter context application and chain-of-thought transparency to the ability to query billions of rows through on-demand generation. See how semantic views built with Snowflake's Open Semantic Interchange (OSI) standard enable large language models to understand your data relationships and business logic, then watch how Qlik supercharges this by making every result fully interactive within the associative engine.
- Video 5: Show Me How It Works - Provides the technical deep-dive using real synthetic healthcare data with 887 million claims records, demonstrating live REST API calls, metadata integration from semantic views into Qlik's data model, and dynamic filter passing that modifies SQL queries on-the-fly.
- Video 6: Show Me How to Build It - Delivers the hands-on implementation guide with complete code walkthroughs, REST connector configuration, partial reload strategies, and the critical JSON parsing techniques you'll need to handle the dynamic chain-of-thought responses. Dalton provides detailed documentation links and resources so you can spend about a day implementing this powerful integration in your own environment. Whether you're the executive exploring possibilities, the architect understanding the technical flow, or the developer ready to build it yourself, this series gives you everything you need to leverage Qlik as a launch partner for Snowflake's Cortex agent functionality.
Agentic approach? OSI Semantic Views?

Heck yeah we've got both covered.

Healthcare Synthetic Data Set -> Semantic View -> Build Qlik Sense Application through Claude and Qlik MCP - This demo begins by pulling the information out of a Semantic View for the shared Healthcare Synthetic data set. Huge tables. Constructs the code to load the tables into Qlik Sense including concatenating the Patient and Encounters fact tables and creating concatenated keys for the dimensional tables. What about all of that wonderful metadata about the fields? Yeah we pull that in as well because governance is important. Then we build Master Dimensions for all of the fields with that as well, including the sample values. Now data modelers/designers can see the data and end users can see it all so they know they can trust the answers and act on them. Chef Qlik Dork and Chef Claude were really cooking in the kitchen for this one.

PS - This was the beginning of the application. See Video 5 - Show me How It Works above to see the final application and how it interacts with Snowflake Cortex Agent API for the full end user experience of awesomeness. I'm talking about the results of questions being displayed as charts, tables and users can see the SQL that was generated. The data returned is ingested into the Qlik Data Model so users can then filter to the records returned and see all of the details to answer their next 10 questions. What if they asked about big data tables that aren't loaded into Qlik Sense? No problem we go pull that data live.

Snowflake Cortex Code (CoCo)

As you know by now MCP servers are essentially invisible. They provide super human, highly performant tasks, but they a visual host. While the Synthetic Healthcare video demonstration above used Claude as the user interface, now that Snowflake has officially released Coco. I mean Cortex Code. I figured I better ensure our joint partners could do their happy dance and take advantage of both of these leading edge power tools.

Previously I created a post called Creating your Secret Sauce. In which I described the process of creating and using #skills. Guess what? The same skill files that I created and shared for Claude can be imported and used directly by CoCo. You gotta be loving that.

The videos in these courses subtly demonstrate the power of using skills to enhance the prompts. My skill for Master Items ensures that their naming convention is user friendly. When I ask to create a sheet ... the skill transforms it into "let's create a story that is prepared with love" instead of microwaving random mystery charts onto a sheet just for speed.

🎥 Course 405 - Cortex Code generating Master Dimensions and Master Measures in Qlik Sense via Qlik MCP

🎥 Course 410 - Cortex Code generating a sheet inside of Qlik Sense via Qlik MCP

Resources

The Show Me How to Build It videos for both series will refer to other resources. I thought about making you crawl on your desktop and squint in order to see the URLS and then make you hand type 50 characters from memory. Then I thought it's not going to be much fun for either of us since I wouldn't actually see you doing it. Fortunately for you I've included the needed resources below.

Calling Snowflake Cortex Agent API within Qlik Sense

Creating a REST API Connection for Snowflake Cortex Agent

How to do a partial reload

Show Less
By Dalton_Ruer 2026-01-26 / 12:58 PM

1 0 989
Member Articles

Q Division Field Training: Module 1 - Agent Information Intelligence

Creating Your First Qlik Answers Knowledge Base 🎯 Mission Briefing Operatives, this is Dork, 007 Dork reporting from Q Division headquarters. Unlike... Show More
Creating Your First Qlik Answers Knowledge Base

🎯 Mission Briefing

Operatives, this is Dork, 007 Dork reporting from Q Division headquarters. Unlike my data, I prefer my Mountain Dew shaken, not stirred.

THE SITUATION: The dreaded Dashboard Disruption Monkey Gang is on the loose again, and we need to find which agent has experience dealing with them. Fast.

YOUR MISSION: Create your first Qlik Answers knowledge base to track Q Division agent dossiers, then build an assistant that can query this intelligence on demand.

DELIVERABLE: A fully functional knowledge base containing agent information with an assistant capable of answering questions about your operatives.

📦 Field Equipment

What You'll Need:
- Access to Qlik Answers in your environment
- Agent dossier files (7 PDF documents included in download)
- Approximately 15 minutes mission time
Download Mission Pack: 📥 You will find the QlikAnswers_SwarmAgents_Dossiers.zip attached

Video Intelligence Briefing: 🎥 Watch the Full Mission Walkthrough

🚀 Mission Steps

Step 1: Establish Your Field Academy Space

First, let's set up your training environment. Navigate to your Qlik hub and create a space called "Q Division Field Academy" (or use an existing space - this is your headquarters for all future training missions).

Once in your space, navigate to the Answers section in the hub where you'll see options for assistants, knowledge bases, data connections, and file uploads.

Step 2: Create Your Agent Information Knowledge Base

Click to create a new knowledge base and name it: "Agent Information"

Pro tip: Normally you'd add a detailed description here. For field training, we're moving fast, but in production you'd want to document what this knowledge base contains and its intended use.

You'll see three options for data sources:
- Data connections (we'll cover in a future module)
- Catalog sources (another mission for another day)
- Upload files ← This is our target for today
Step 3: Deploy Your Agent Dossiers

Unzip the mission pack you downloaded and you'll find 7 agent dossier PDFs.

Simply drag and drop all 7 files into the upload area. You should see all seven appear in your upload queue.

Click "Upload" and watch as Q Division's finest get cataloged into your system.

Step 4: Index Your Intelligence (CRITICAL)

⚠️ FIELD NOTE: Here's where rookies often get tripped up!

After upload, check the Index Status. It will say "Never been indexed" - this means the RAG (Retrieval-Augmented Generation) system hasn't parsed your documents yet. You cannot query unindexed data.

Click "Index All" and switch to the flat view to watch the progress. With only a handful of pages per dossier, this should complete in seconds.

Refresh your screen. When you see "Index Status: Completed" with a timestamp, your intelligence is ready for deployment.

Step 5: Create Your Field Training Assistant

Now let's build an assistant that can query this knowledge base.

Click to create a new assistant and name it: "Field Training Assistant"

Add your Agent Information Knowledge Base.

We'll cover conversation starters in a future module - these are pre-written prompts that help users know what questions to ask.

Step 6: Test Your Intelligence Network

Time to validate your setup. Ask your assistant:

"Which agent has interacted with the dreaded Dashboard Disruption Monkeys?"

Watch the reasoning panel (this is where the magic happens):
1. Answer Agent activates first - it's always first on the job, collecting data sources and formulating a plan
2. Knowledge Base Agent takes over - searches through your indexed dossiers
3. Answer Agent reports back - "The Assembler Agent interacted with the dreaded Dashboard Disruption Monkeys during Operation Layout Logic"
Click on the citation link and it will jump directly to the source document, highlighting exactly where that information was found in the dossier.

✅ Mission Debrief

What You've Accomplished:
- ✓ Created your first Qlik Answers knowledge base
- ✓ Uploaded and indexed unstructured PDF documents
- ✓ Built an assistant that queries your knowledge base
- ✓ Successfully tracked down intel using natural language queries
- ✓ Understood the agent reasoning flow (Answer → Knowledge Base → Answer)
Validation Check: Can you ask your assistant "Which agent dealt with the Dashboard Disruption Monkeys?" and get back "Assembler Agent" with a citation? If yes, mission accomplished! 🎯

Challenge Exercise (Optional): Try asking other questions about your agents. What skills do they have? What operations have they completed? Test the limits of what your knowledge base knows!

📚 Field Notes: Technical Deep-Dive

What's happening with RAG and indexing?

When you upload PDFs to a knowledge base, Qlik Answers uses RAG (Retrieval-Augmented Generation) to:
1. Parse the document content
2. Break it into searchable chunks
3. Create vector embeddings for semantic search
4. Store these in an index
Until indexing completes, the content is just raw files - the AI can't "see" it yet. Think of indexing as translating your documents into a language the AI agents understand.

Understanding the Agent Reasoning Flow

Qlik Answers uses multiple specialized agents:
- Answer Agent: The orchestrator. Receives your question, determines what data sources are needed, coordinates other agents, and formats the final response.
- Knowledge Base Agent: Specialized in searching unstructured documents. Uses semantic search to find relevant passages and return citations.
This multi-agent approach allows each specialist to do what it does best, similar to how Q Division has different operatives with different skills!

Why Citations Matter

Every answer includes citations showing exactly where the information came from. This is critical for:
- Trust: Users can verify the answer
- Governance: Track what data sources are being used
- Debugging: Understand why an answer was given
- Compliance: Prove where recommendations originated
In enterprise analytics, "because the AI said so" doesn't cut it. Citations provide the audit trail.

🎬 That's a Wrap, Operatives

You've successfully completed your first Q Division field training mission. You're now equipped to turn unstructured documents into queryable intelligence using Qlik Answers.

Remember: In analytics, as in espionage, the right question is more valuable than a thousand answers.

Dork, 007 Dork, signing off. Keep your data shaken and your queries stirred.

Questions? Feedback? Spotted a Dashboard Disruption Monkey? 👎 Use the feedback button or reach out to your Q Division training coordinator
Show Less
By Dalton_Ruer 2026-02-01 / 04:38 PM

1 2 186
Member Articles

How to Manually Migrate an NPrinting Excel Template to Qlik Cloud Tabular Report

When migrating from NPrinting to Qlik Cloud, existing Excel report templates can be reused with the Tabular Report feature through the Qlik Add-in for... Show More
When migrating from NPrinting to Qlik Cloud, existing Excel report templates can be reused with the Tabular Report feature through the Qlik Add-in for Microsoft Excel. This article walks through the correct steps to adapt and connect an NPrinting Excel template to a Qlik Cloud app when you don’t have access to the “Export Qlik Cloud Reports” option in Nprinting.
Prerequisites
- The Qlik Add-in for Microsoft Excel installed via Microsoft AppSource or your organization’s Office Add-ins manifest. If you need assistance on how to install the Add-in, check this page: https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/Reporting/Install/reporting-install-add-ins.htm.
- Access to a Qlik Cloud tenant with at least one published app containing the data you want to report on.
- Export template permission in Nprinting.
Step 1 — Download the Report Template from NPrinting
The template can be downloaded directly from the Reports section in NPrinting. Use the Export > Download option. You may optionally set a password for the exported file if required by your organization.

Once downloaded, unzip the file and save the template to a location that is easy to find and access later.
Step 2 — Ensure the Qlik Add-in is Installed and Connect to Your App
Make sure the Qlik Add-in is already installed in the version of Microsoft Excel you intend to use.

When you open the template, you will see the field names as they were defined in the NPrinting Designer Console.

Using the Add-in panel, connect to the appropriate Space and App that correspond to this report.

Step 3 — Locate the Chart Sources in Your Qlik Cloud App
Open your Qlik Cloud app and identify the chart objects that contain the fields used in the report template. For each relevant object, note:
- The Sheet where the chart is located.
- The Object ID of the chart.
To find it, you can right click in the table/Chart > Share > Embed:

In the next window, you will see info about this chart, including the Object ID:
You will need the Object ID in the next step to match the correct table in the Add-in console.

Step 4 — Add the Table to the Add-in Console (Without Inserting Fields)
In the Qlik Add-in console, locate the table or chart that matches the Object ID identified in Step 3.
Add this table or chart to the console.

Important: Do not insert any fields from the console into the template. Since the field names are already present in the template (from the original NPrinting layout), the table only needs to be added to the console to establish the field mapping. The Add-in will use the existing field references in the template cells automatically, as long as the corresponding table is active in the console.
Step 5 — Preview and Validate the Report
Run a preview from the Qlik Add-in panel to check that all fields are returning data correctly. Verify that each mapped cell is populated as expected and refine the formatting if necessary before distributing or scheduling the report.
Additional Notes
- Formatting, styling, and layout from the original NPrinting template (colors, fonts, borders) are preserved and do not need to be recreated.
- If a field shows no data during preview, double-check that the field name in the template cell exactly matches the field name in the Qlik Cloud app — including capitalization and spacing. Even a minor mismatch will result in blank output.
- If your Qlik Cloud app uses master measures or calculated dimensions, make sure those are exposed as fields or that the chart object added to the console includes them. The Add-in can only resolve references to fields that are part of the loaded object.
- If the NPrinting template used variables or expressions directly in cells (rather than field references), those will need to be reviewed manually — the Add-in does not support NPrinting-style expression syntax and may require adjustments in the template or in the app’s load script.
Show Less
By Camilla84 2026-03-24 / 10:43 AM

7 12 450
Member Articles

Building a Snapshot History Table in Qlik Cloud: Capturing Point-in-Time Data fo...

Introduction One of the most common requests in any analytics project is deceptively simple: "Can we see how this looked last week?" Or last month. Or... Show More
Introduction

One of the most common requests in any analytics project is deceptively simple: "Can we see how this looked last week?" Or last month. Or as of the end of Q2.
The problem is that most source systems don't keep that history — they just reflect the current state of the world. When a work order gets closed, it's closed. When a headcount changes, the old number is gone. By the time someone asks the question, the data that would have answered it no longer exists.
This is where snapshot history tables come in. A snapshot is a copy of your data taken at a specific point in time and preserved so you can compare it against past and future states. Done right, it unlocks trending, period-over-period comparisons, "as of" reporting, and a whole class of analysis that live data simply can't support.
In this article, we'll walk through how to design, build, and maintain a snapshot history table in Qlik Cloud — from the first QVD write to a fully connected data model ready for analysis.
Part 1: Understanding the Pattern What Is a Snapshot?
A snapshot is a full or partial copy of a dataset, tagged with the date (or datetime) it was captured. Instead of overwriting your data on each reload, you accumulate records over time, each stamped with when they were taken.
For example, imagine a table of open production orders. Today it has 120 rows. Tomorrow, some will close and new ones will open — maybe 115 rows. A snapshot approach saves both versions, so you can always ask: "How many open orders did we have on any given day?"
Incremental vs. Full Snapshots
There are two main approaches:
- Full snapshots capture the entire dataset each time. Simple to implement, but storage grows quickly.
- Incremental snapshots only capture what changed. More efficient, but more complex to build and query.
For most use cases in Qlik, full daily snapshots stored as QVDs strike the best balance of simplicity and utility. Storage is cheap, and the load logic stays manageable.
Choosing Your Snapshot Frequency
Your snapshot frequency should match your reporting needs:
- Daily — good for operational metrics like open orders, headcount, or inventory
- Weekly / Monthly — good for slower-moving KPIs or when daily granularity isn't meaningful
- On-demand — useful for financial close snapshots or project milestones
For this walkthrough, we'll use a daily snapshot pattern.
Part 2: Setting Up the Snapshot Table Designing the Table Structure
The key to a useful snapshot table is adding a SnapshotDate field to whatever you're capturing. This becomes the anchor for all your time-based analysis.
Here's a simple example — capturing open work orders:
qlik
// Load current data from sourceWorkOrders_Current:LOAD WorkOrderID, Description, Status, AssignedTo, DueDate, Date(Today(), 'YYYY-MM-DD') AS SnapshotDateFROM [lib://DataSource/WorkOrders.qvd] (qvd)WHERE Status = 'Open';
The SnapshotDate field is what distinguishes today's records from yesterday's once they're all loaded together.
Using Store to Write Snapshot QVDs
After loading the current data, write it out to a dated QVD file:
qlik
STORE WorkOrders_Current INTO [lib://Snapshots/WorkOrders_$(vToday).qvd] (qvd);DROP TABLE WorkOrders_Current;
Where vToday is a variable set earlier in the script:
qlik
LET vToday = Date(Today(), 'YYYY-MM-DD');
This produces a series of files like:
WorkOrders_2025-01-01.qvdWorkOrders_2025-01-02.qvdWorkOrders_2025-01-03.qvd...
The Load-Append-Store Loop
The full pattern each reload looks like this:
1. Load today's source data
2. Tag it with today's date
3. Store it as a new dated QVD
4. Load all historical QVDs together for analysis
Part 3: Loading and Managing History Loading Historical QVDs with a Wildcard
Once you have a folder of dated QVDs, loading them all is straightforward using a wildcard path:
qlik
WorkOrders_History:LOAD WorkOrderID, Description, Status, AssignedTo, DueDate, SnapshotDateFROM [lib://Snapshots/WorkOrders_*.qvd] (qvd);
Qlik will automatically find and load every matching file in that folder.
Preventing Duplicates
If your reload runs more than once in a day, you could end up with duplicate snapshot records for the same date. The safest guard is to check whether today's QVD already exists before writing it:
qlik
IF NOT FileSize('lib://Snapshots/WorkOrders_$(vToday).qvd') > 0 THEN // Load and store logic hereEND IF;
Alternatively, handle this at the analysis layer by filtering to distinct SnapshotDate values.
Managing Retention
Snapshots accumulate fast. If you're taking daily snapshots of a large table, you'll want a retention policy. Common approaches:
- Keep only the last N days of daily snapshots
- Roll up older snapshots to weekly or monthly granularity
- Archive to cold storage after a certain age
For most mid-size Qlik projects, keeping 90–365 days of daily snapshots in QVD form is very manageable.
Handling Schema Changes
If the source table adds or removes columns over time, older QVDs may not match newer ones. A few strategies:
- Use LOAD * ... with care — missing fields will simply be null in older files
- Document your schema and version your QVD folder if major changes occur
- Use a NullAsValue or explicit field list to normalize across versions
Part 4: Modeling for Analysis Linking the Snapshot Table to Your Data Model
The snapshot table is usually a fact table in your model. Link it to dimension tables (e.g., a date dimension, an employee dimension, a location dimension) via their respective keys.
Your date dimension is especially important here — it lets users filter and group by week, month, quarter, or year without doing date math in expressions.
qlik
// Link SnapshotDate to your master calendar[Master Calendar]:LOAD Date, Week(Date) AS WeekNum, Month(Date) AS MonthName, Year(Date) AS YearRESIDENT TempCalendar;
Make sure SnapshotDate in your fact table and Date in your calendar are the same format.
Avoiding Fan Traps and Synthetic Keys
Snapshot tables can grow wide and create association issues if you're not careful. A few tips:
- Give your snapshot table a clear, unique grain (one row per entity per snapshot date)
- Avoid associating it to multiple fact tables without a bridge or intermediate key
- If you see synthetic keys, use QUALIFY or rename fields to resolve them
Building a "Latest Snapshot" Flag
For dashboards where users want to see the current state by default, add a flag field:
qlik
LEFT JOIN (WorkOrders_History)LOAD WorkOrderID, SnapshotDate, 1 AS IsLatestSnapshotRESIDENT WorkOrders_HistoryWHERE SnapshotDate = Date(Today(), 'YYYY-MM-DD');
Users can then filter to IsLatestSnapshot = 1 to see today's view, or remove the filter to analyze trends over time.
Part 5: Real-World Example — Tracking Open Production Orders Over Time
Let's put it all together with a practical example. Imagine you're supporting a food manufacturer who wants to track how their open production order count trends week over week.
The Full Script
qlik
// -----------------------------------------------// Set variables// -----------------------------------------------LET vToday = Date(Today(), 'YYYY-MM-DD'); // -----------------------------------------------// Load today's open production orders from source// -----------------------------------------------ProdOrders_Today:LOAD OrderID, ProductCode, TargetQty, ActualQty, Status, PlannedDate, Date('$(vToday)', 'YYYY-MM-DD') AS SnapshotDateFROM [lib://Source/ProductionOrders.qvd] (qvd)WHERE Status = 'Open'; // -----------------------------------------------// Store today's snapshot (if not already stored)// -----------------------------------------------IF NOT FileSize('lib://Snapshots/ProdOrders_$(vToday).qvd') > 0 THEN STORE ProdOrders_Today INTO [lib://Snapshots/ProdOrders_$(vToday).qvd] (qvd);END IF; DROP TABLE ProdOrders_Today; // -----------------------------------------------// Load full snapshot history// -----------------------------------------------ProdOrders_History:LOAD OrderID, ProductCode, TargetQty, ActualQty, Status, PlannedDate, SnapshotDateFROM [lib://Snapshots/ProdOrders_*.qvd] (qvd); // -----------------------------------------------// Flag the latest snapshot// -----------------------------------------------LEFT JOIN (ProdOrders_History)LOAD DISTINCT OrderID, SnapshotDate, 1 AS IsLatestSnapshotRESIDENT ProdOrders_HistoryWHERE SnapshotDate = Date(Today(), 'YYYY-MM-DD');
With this in place, a simple line chart with SnapshotDate on the x-axis and Count(OrderID) on the y-axis gives you a daily trend of open orders — something that would be impossible with live data alone.
Wrap-Up Common Pitfalls to Avoid
- Not tagging records with a snapshot date — without this, all your history is meaningless
- Letting QVDs accumulate without a retention policy — this sneaks up on you
- Associating the snapshot table incorrectly — always validate your data model after adding it
- Running the snapshot write multiple times per day — add a guard to prevent duplicates
When Snapshots Aren't the Right Tool
Snapshots work best when your source system doesn't retain history. If your source already has effective-dating, change data capture (CDC), or an audit log, it may be better to leverage that directly rather than building your own snapshot layer.
Also, if you only ever need to compare two specific points in time (e.g., current vs. prior year-end), a simpler approach — loading two static datasets and joining them — might be more maintainable.
What's Next
Once you have a solid snapshot history table in place, there are several natural extensions:
- Adding manual overrides or adjustments using Qlik's writeback capabilities
- Rolling up snapshots into weekly or monthly aggregates for longer-range trending
- Combining snapshots with targets to show actual-vs-plan over time
Snapshot history is a foundational pattern — once you build it once, you'll find yourself reaching for it on almost every operational analytics project.
Show Less
By WeLoveQlik 2026-03-21 / 08:35 AM

0 0 121
Member Articles

How to recover Qlik NPrinting Administrator account privileges

This article assumes you understand:How to use pgAdminHave postgres credentials for Qlik NPrintingHow to connect to the Qlik NPrinting database * Modi... Show More
This article assumes you understand:
- How to use pgAdmin
- Have postgres credentials for Qlik NPrinting
- How to connect to the Qlik NPrinting database
* Modifying the Qlik NPrinting Repository will void the Support Agreement! Changes to the database should be performed by the Qlik NPrinting services only or through the use of supported API calls.

Overview
If, for some reason, you lost the Administrator role for your Qlik NPrinting Admin account and you are unable to change settings in the Web Console, you can follow this article to restore administrative access to the target account.

Symptoms
You are unable to edit/change any Administrative settings.

Resolution
You can force insert/update the user in the database with the administrator role id.
The first step is to connect to the database using pgAdmin.
- Refer to How to Connect to the PostgreSQL Database used for... - Qlik Community - 1714888
The second step is to identify the administrator role id using pgAdmin.
- Open pgAdmin
- Connect to the Qlik NPrinting database
- Navigate to: Databases>nprinting>Schemas>public>Tables>role
- Right-click the table "role" and select "All Rows".
- Take note of the administrator "id" (green marked in the image above).
In my test environment, the administrator role equals "6b800774-db4f-4b5e-a975-24e5b86b5ece".

The third step is to identify the user role ID using pgAdmin.
- Open pgAdmin
- Connect to the Qlik NPrinting database
- Navigate to: Databases>nprinting>Schemas>public>Tables>usr
- Right-click the table "usr" and select "All Rows".
- Take note of the administrator "id" (green marked in the image above).
In my test environment, the administrator role equals "1628ad97-75af-4cb3-897f-da1cb07777e5".
The fourth step is to update the "role_recipient" table.
- Open pgAdmin
- Connect to the Qlik NPrinting database
- Open the Query tool by navigating to the top menu "Tools>Query Tool".
Use the following command line, replacing the information you previously retrieved.
Insert into public.role_recipient VALUES ('user role id','administrator role id');
In my scenario, it will be:
Insert into public.role_recipient VALUES ('1628ad97-75af-4cb3-897f-da1cb07777e5','6b800774-db4f-4b5e-a975-24e5b86b5ece');
Click "Execute script" or press F5.
Go back to Web Console and refresh the page. The target user should have Admin privileges.

Environment
- Qlik NPrinting May 2023 IR to February 2025 SR4
- pgAdmin 9.13
Show Less
By Eduardo_Monteiro 2026-03-10 / 09:38 PM

0 4 68
Member Articles

Qlik Cloud IP Allow List Does Not Support IPv6 - WebSocket Error 1006

If users on your Qlik Cloud tenant are experiencing frequent WebSocket disconnections (Error 1006) and your organization has an IP Allow List configur... Show More

If users on your Qlik Cloud tenant are experiencing frequent WebSocket disconnections (Error 1006) and your organization has an IP Allow List configured, IPv6 may be the root cause. Qlik Cloud's IP Allow List feature currently only supports IPv4 addresses. When users connect via IPv6, their traffic does not match any entry in the allow list, causing the connection to be dropped.
Symptoms
Users experience random disconnections while working in Qlik Cloud apps. The error code reported is Error 1006 (WebSocket disconnection). The issue affects multiple users simultaneously and is not tied to a specific app or sheet. The problem is more prevalent after network changes or in environments where IPv6 is enabled by default.
Resolution
Qlik has confirmed they are adding native IPv6 support to the IP Allow List feature. The estimated delivery is between Q4 2026 and early 2027. You can follow the progress and vote on the ideation item here:
https://ideation.qlik.com/app/#/case/527417?currentProductId=9da99bc1-0dfb-4471-8e12-d23685578c43&cpid=6f31e7a4-d798-4ac8-8e65-7756267b3354

Workaround
Work with your IT or network team to disable or restrict IPv6 on the network infrastructure used to access Qlik Cloud. This forces client connections to use IPv4, which is properly handled by the IP Allow List. Once IPv6 traffic is restricted, users should no longer experience WebSocket disconnections caused by this issue.

Cause
Qlik Cloud's IP Allow List feature only evaluates IPv4 addresses. When a user's device connects over IPv6, the source address does not match any entry in the allow list, and the connection is rejected or dropped at the WebSocket layer, resulting in Error 1006. This is a known platform limitation. Qlik has confirmed they are adding IPv6 support to the IP Allow List feature, with an estimated delivery between Q4 2026 and early 2027.

Related Content
Qlik Help: IP Allow List configuration: https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/Admin/mc-configure-ip-allowlist.htm
Show Less

By AnaSilva 2026-03-10 / 12:28 PM

2 7 444
Member Articles

Qlik Cloud with Qlik IDP: Users Are Not Automatically Removed When Email Is Deac...

When using Qlik Cloud with Qlik's built-in Identity Provider (Qlik IDP), deactivating or deleting a user's corporate email address does not automatica... Show More
When using Qlik Cloud with Qlik's built-in Identity Provider (Qlik IDP), deactivating or deleting a user's corporate email address does not automatically remove or disable their access to Qlik Cloud. This is a common misconception that can create a security gap during employee offboarding.
Symptoms
A user's corporate email has been deactivated or their account deleted from the corporate directory. However, the user still appears as active in Qlik Cloud Management Console and their license seat remains occupied. The user may still be able to log in to Qlik Cloud if they have an active session or a previously set password.
Resolution
Administrators must manually remove or disable the user directly in Qlik Cloud. To do this, go to Management Console, navigate to Users, find the user and either remove them or change their role to No Access. This should be added as a required step in your organization's employee offboarding checklist.
If your organization requires automatic user deprovisioning, the permanent solution is to replace Qlik IDP with an external Identity Provider such as Microsoft Entra ID (Azure AD) or Okta, configured with SCIM provisioning. With SCIM enabled, when a user is disabled or removed in your corporate directory, Qlik Cloud is automatically notified and the user's access is revoked without any manual intervention.

Cause
Qlik IDP is a standalone identity store built into Qlik Cloud. It manages user accounts independently from any external corporate directory. Because there is no synchronization between Qlik IDP and external systems, changes made outside of Qlik Cloud such as deactivating an email or removing an Active Directory account have no effect on the user's Qlik Cloud account.

Environment
- Qlik Cloud Analytics (SaaS)
- Qlik IDP (built-in Identity Provider)
Show Less
By AnaSilva 2026-03-10 / 12:28 PM

2 8 161
Member Articles

Qlik Excel Add-in OAuth Errors After Tenant Rename (OAUTH-1 and OAUTH-14)

If your Qlik Cloud tenant hostname was recently renamed (for example, from company-old.us.qlikcloud.com to company-new.us.qlikcloud.com) and users are... Show More
If your Qlik Cloud tenant hostname was recently renamed (for example, from company-old.us.qlikcloud.com to company-new.us.qlikcloud.com) and users are now receiving OAuth errors when connecting the Qlik Excel Add-in, this article explains what is happening and how to resolve it.
Symptoms
Users open Excel, launch the Qlik Add-in, and receive one of the following errors during authentication:
OAUTH-1: redirect_uri is not registered (Status 400)
OAUTH-14: OAuth client is not authorized
These errors appear even though the add-in was working before the tenant rename.
Resolution
1. Log in to the Qlik Cloud Management Console on the new tenant hostname.
2. Go to OAuth and delete the existing OAuth client used for the Excel Add-in.
3. Create a new OAuth client with the following settings: Client type: Public. Grant types: Authorization Code. User default scope: Enabled. Allowed origins: your current tenant URL (e.g., https://company.us.qlikcloud.com).
4. Go to Settings > Sharing and reports > Qlik add-ins for Microsoft Office. Select the new OAuth client from the dropdown and download the updated manifest.xml file.
5. Distribute the new manifest.xml to your users. Users must remove the old add-in from Excel before installing the new one.
Important: If users access the tenant through both the original URL and an alias, add both to the allowed origins field. Missing either one will cause authentication to fail.

Cause
The Excel Add-in manifest.xml and its OAuth client are created as a pair and are tied to a specific tenant hostname. When the tenant is renamed, the existing OAuth client retains the old hostname in its redirect URIs and allowed origins, triggering OAUTH-1. If the manifest is recreated but the OAuth client configuration still has incorrect settings, OAUTH-14 follows. The manifest file cannot be edited to point to a new hostname. It must be regenerated from a newly created OAuth client on the correct tenant.

Related Content
- Tabular Reporting OAUTH Error Status 400 resolution: https://community.qlik.com/t5/Official-Support-Articles/Tabular-Reporting-OAUTH-Error-Status-400-resolution/ta-p/1716773
- Qlik Help: Administer the Qlik add-in for Microsoft Office: https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/Sense_Hub/Admin/mc-administer-add-in.htm
Show Less
By AnaSilva 2026-03-10 / 12:31 PM

2 8 207
Member Articles

Q Division - Qlik Answers - Agent Dossiers

Purpose If you were looking for a super deep technical explanation of each of the Qlik Answers Agentic Agents ... you've come to the wrong place. As p... Show More

Purpose

If you were looking for a super deep technical explanation of each of the Qlik Answers Agentic Agents ... you've come to the wrong place.

As part of my Q Division training series I wanted humanize each of these #AI titans for you just a little bit. After all just seeing their names on the screen while they are working hard on your behalf is really impersonal.

Dossiers

This is from an official presentation about the Agentic Agents that are part of Qlik Answers.

But as the Dork, 007 Dork, I assumed you would want a little more understanding. So, each of their, totally fictitious, and hilarious, dossiers is attached.

Simply download the zip file and spend as many hours laughing as you read each and every page about each of the agents. No self-destructing. The files will remain as long as you want. Page after page of fun, mixed in with occasional insight.

But ensure their protection! They are highly classified and for your eyes as a Q Division operative in training only.

Meet the Agents

QD-001 | The Maestro | Answers Agent

QD-002 | Cipher | Semantic Agent

QD-003 | Curator | Knowledge Agent

QD-004 | Architect | Data Analyst Agent

QD-005 | Illustrator | Chart Agent

QD-006 | Assembler | Dashboard Agent

QD-007 | Navigator | Help Agent

Show Less

By Dalton_Ruer 2026-01-31 / 02:19 PM

2 3 393
Member Articles

Loops in Qlik Sense Script: FOR, FOR EACH, WHILE, and DO WHILE

When working with large datasets, loading everything in a single query is rarely an option. When the source can't return all the data at once, you nee... Show More
When working with large datasets, loading everything in a single query is rarely an option. When the source can't return all the data at once, you need to break the load into steps: by date, by region, by file. That's exactly what loops are for in Qlik Sense script. They reduce code volume, make the load process manageable, and allow you to build incremental ETL pipelines that refresh only the required data slice without overloading the source.

Qlik Sense has four types of loops, and each has its own use case.

FOR..NEXT: when the number of iterations is known in advance. The period is defined through a variable storing the difference between dates. Since the counter starts at 0, we use -1 to avoid an extra iteration:
```
LET vDaysCount = Date#(vEndDate,'YYYY-MM-DD')
               - Date#(vStartDate,'YYYY-MM-DD');

FOR i = 0 TO $(vDaysCount) - 1
    LET vDate = Date(Date#(vStartDate,'YYYY-MM-DD') + i, 'YYYY-MM-DD');
    // query body
NEXT i
```
FOR EACH..NEXT: iterates over a list of values: regions, file names, product codes. The list can be defined explicitly or generated using functions like FileList(), DirList(), or FieldValueList():
```
FOR EACH vRegion IN 'UZB', 'KAZ', 'RUS'
    LOAD * FROM [lib:///_$(vRegion).qvd](qvd);
NEXT vRegion
```
WHILE: used inside a LOAD statement together with AutoGenerate and the IterNo() function. The classic example is generating a Master Calendar:
```
TempCalendar:
LOAD Date($(vMinDate) + IterNo() - 1, 'YYYY-MM-DD') as tDate
AutoGenerate 1
While $(vMinDate) + IterNo() - 1 <= $(vMaxDate);
```
The condition is evaluated on each row via IterNo(): this is row generation inside a single LOAD statement.

DO WHILE: a loop with an updatable variable. The condition is re-evaluated before each iteration. Used for incremental loading from an external source with a date-by-date breakdown:
```
LET vEndDate       = Date(Today(), 'YYYY-MM-DD');
LET vStartDate     = Date(Today() - 7, 'YYYY-MM-DD');
LET vIterationDate = vStartDate;

DO WHILE vIterationDate <= vEndDate

    // query body
    WHERE date_field = toDate('$(vIterationDate)')

    STORE TempOneDay INTO [lib://…/data_$(vQVDName).qvd](qvd);
    DROP TABLE TempOneDay;

    LET vIterationDate = Date(Date#(vIterationDate,'YYYY-MM-DD') + 1, 'YYYY-MM-DD');
LOOP
```
Show Less
By Assel_Dochshanova_Pazylbekova 2026-02-28 / 01:16 AM

0 2 278
Member Articles

KPI Cards on a Dashboard: What Types Exist?

At first glance, a KPI is just a number on a dashboard. But depending on the task, cards can vary significantly in structure. I'd highlight several gr... Show More
At first glance, a KPI is just a number on a dashboard. But depending on the task, cards can vary significantly in structure. I'd highlight several groups:
1. Single one number
2. Monitoring number + delta + trend
3. Multi-metric one main metric with several related ones in a single card
4. Threshold a value alongside its target
5. Progress visual % of completion
6. Comparative plan vs fact, segment A vs segment B
7. Status where the color matters more than the number itself 🟢🟡🔴
Today I want to focus on monitoring KPIs where you can immediately see not just the current value, but also the dynamic: delta to the previous period and a trend line.

In Qlik Sense, I build these cards using an HTML Box. It's not a separate widget it's a string expression where HTML is assembled via & concatenation, and Qlik calculations are embedded directly inside the string:
='<div style="font-family:Arial; padding:12px;">' & '<div style="font-size:11px; color:#888;">OPERATIONS COUNT</div>' & '<b style="font-size:28px;">' & Num(sum(cnt)/1e6, '#.##0,00') & ' M</b>' & '<span style="color:' & If(wow > 0, '#2E8B57', '#B22222') & ';">' & Num(wow, '+##0,0%;-##0,0%') & ' WoW' & '</span>' & '</div>'
The delta color is calculated dynamically with If()construction directly inside the style attribute. Writing this HTML manually isn't necessary: ChatGPT handles it well, just describe the layout you want.

Pro tip for reuse: use variables and master measures. To create a second KPI with the same design, simply copy the block and replace the master measure and variables using Find & Replace.

The card with a trend line at the bottom is built from three objects inside a Layout Container:
1. HTML Box main value and delta
2. Line Chart trend line with no axes or labels
3. Layout Container combines them into a single block
The result looks like a fully polished product design using only the built-in tools of Qlik Sense.

Dashboard example built in Qlik Sense showing 6 KPI card types: Monitoring (value + delta + trend line), Multi-metric (primary metric with additional metrics), Status (with background color), Comparative (two dimensions side by side), Progress (value + % of target), and Single (standalone number).
Show Less
By Assel_Dochshanova_Pazylbekova 2026-02-28 / 12:44 AM

0 1 273

Q Division Field Academy

Mission Briefing Welcome to Q Division Headquarters, Operative. Behind these doors lies the future of AI-powered analytics. Qlik Answers isn't just a... Show More

Mission Briefing

Welcome to Q Division Headquarters, Operative.

Behind these doors lies the future of AI-powered analytics. Qlik Answers isn't just another tool—it's your answer intelligence platform that lets anyone ask natural language questions of their unstructured data, their structured data, or both working together in perfect coordination.

Your mission, should you choose to accept it: Master the Q Division agent swarm architecture, earn your Field Operative certification, and deploy answer intelligence across your organization.

Inside, you'll meet our specialist agents, complete hands-on training exercises, watch live mission playbacks, and prove your tactical intelligence through the Agent Recognition Protocol.

By the time you exit these doors, you won't just understand Qlik Answers—you'll be ready to implement your (or guide others through) first deployments with confidence.

The briefing room awaits. Enter when ready, Operative.

Agent Roster

Q Division operates on what the intelligence community calls a "swarm architecture" – the industry gold standard for AI agent collaboration. Instead of relying on a single agent to handle every mission, we've assembled a specialized team where each agent excels at their specific domain. When you ask a question, our system intelligently identifies which agents have the expertise needed and orchestrates a precision handoff sequence to deliver the most accurate answer.

Think of it like a real intelligence agency: you wouldn't send the same operative to handle cryptography, field reconnaissance, AND financial analysis – you'd send specialists who work together, each completing their part of the mission before passing critical intelligence to the next agent. That's exactly what Qlik Answers does, ensuring you get enterprise-grade accuracy through expert collaboration. Meet the agents who'll be working your missions:

Operation: Swarm Intelligence - Agent Dossiers ►

Field Training Exercises

Welcome to active duty, Operative. In this section, you'll receive the same intelligence assets that Q Division uses in live operations: a fully configured Qlik Answers application, pre-loaded knowledge bases, and the Answer Assistant framework that orchestrates our agent swarm. This isn't a simulation – these are production-grade materials that you'll download, deploy, and interrogate with real questions. You'll see firsthand how questions flow through the agent network, learn to craft queries that leverage each agent's expertise, and build the muscle memory needed to guide others through their first Qlik Answers deployment. By the end of these exercises, you won't just understand the theory – you'll have hands-on experience running actual missions.

Unstructured Data

🎯 Q Division Field Training: Module 1 - Agent Information Intelligence - Buidling your first Knowledge Base and Assistant

🎯 Q Division Field Training: Module 2 - Application Documentation - Building another Knowledge Base and enhancing your Assistant wit the additional knowledge.

🎯 Q Division Field Training: Module 3 - Expense Statements - Building an enterprise grade Knowledge Base with Advanced Chunking and enhancing your Assistant with the additional knowledge

Structured Data

🎯 Q Division Field Training: Module 100 - Uploading Q Division Operations Application - Asking Answers

Unstructured + Structured

🎯 Q Division Field Training: Module 200 - Dashboard Inconsistency - Asking Questions of Unstructured and Structured Data in your Assistant

Mission Playback

Field Operative, it's time to see the agents in action. In this section, you'll watch live mission recordings where real questions trigger the full agent swarm workflow. On one side of your screen, you'll see the complete Qlik Answers solution being constructed in real-time. On the other, you'll see which Answer Agent is currently on mission – giving you a visual understanding of who does what, when they're called into action, and how they hand off intelligence to the next specialist in the sequence. Here's where it gets powerful: since you already have the same materials from Field Training, you can run these exact same questions in your own Qlik Answers environment and watch your agents work the mission alongside mine. These aren't just recordings to watch passively – they're your playbook for getting comfortable with the agent workflow before you guide others through it.

Mission Playback - Review 1 - Counter Terrorism	In this Q Division mission playback, an auditor spots a suspicious English-Russian dictionary expense on case 1006—a Swedish healthcare analytics mission that had nothing to do with Russian operations. Using Qlik Answers, the auditor conducts a comprehensive counter-terrorism review that reveals Agent 099 (Alec Trevelyan) purchased suspicious items including the dictionary from an oddly-named bookstore, multiple alcoholic beverages at "Cafe Pushkin" (named after a famous Russian poet), and celebrated with expensive champagne before the case was even closed. It's a masterclass in how conversational analytics can connect the dots between structured databases and unstructured documents to surface anomalies that traditional reporting would miss.

Agent Recognition Protocol

Final assessment, Field Operative. Before you earn your Clearance Level certification, you need to prove you can recognize which agents handle which intelligence requests. We'll present you with real-world questions – the kind partners and customers will actually ask – and you'll identify which Answer Agent(s) will be deployed on the mission. This isn't about memorizing definitions; it's about developing the tactical instinct to know instantly: "That's a Data Agent question," or "This one needs both Knowledge and Visualization working together." Pass the Agent Recognition Protocol, and you'll have earned more than a certification – you'll have the operational confidence to guide anyone through their first Qlik Answers deployment

Take the Agent Recognition Protocol Test

Show Less

705

Member Articles

Q Division Field Training: Module 200 - Dashboard Inconsistency

Solving the Mystery of Dashboard Numbers That Don't Add Up 🎯 Mission Briefing Operatives, this is Dork 007 Dork reporting from Q Division headquart... Show More
Solving the Mystery of Dashboard Numbers That Don't Add Up

🎯 Mission Briefing

Operatives, this is Dork 007 Dork reporting from Q Division headquarters. We have a situation that keeps every intelligence analyst up at night: Numbers that don't add up.

THE SITUATION: The original programmer for our Q Division application has left the company. A talented new designer built a beautiful dashboard, but there's a critical problem: Active Cases (16) + Closed Cases (15) = 31... but Total Cases shows 50. In an intelligence agency where no mission can be left behind, this kind of inconsistency is unacceptable.

YOUR MISSION: Use Qlik Answers to investigate the application and notes from the original programmer. In other words Structured Data -AND- Unstructured Data

DELIVERABLE: A dashboard that accurately reflects all case statuses with proper reconciliation, plus an understanding of how to use AI to diagnose and fix data model inconsistencies.

📦 Field Equipment

What You'll Need:
- Access to Qlik Answers with an existing assistant
- The Q Division application (uploaded in Mission 100 - attached here if needed)
- Approximately 15 minutes mission time
Video Intelligence Briefing: 🎥 Watch the Full Mission Walkthrough

🚀 Mission Steps

Step 1: Connect Your Application to Your Assistant

Navigate to your Q Division Field Academy catalog and locate your Field Training Assistant. This time, instead of adding another knowledge base, we're going to add structured data from your application itself.

Click to add content to your assistant, but instead of selecting a knowledge base, choose your Q Division application. Make sure you're in your Q Division Field Academy space and select the application you uploaded in Mission 100.

Pro tip: Once configured, your assistant can now query both unstructured data (knowledge bases with PDFs) AND structured data (your application's data model). This hybrid capability is what makes Qlik Answers so powerful for investigative work.

Step 2: Ask the Diagnostic Question

Now comes the moment of truth. Ask your assistant:

"Please tell me the total number of cases we have, the total closed cases we have, and the total open cases we have. Can you help me understand why there seems to be an inconsistency with the totals? Because what I see in my application seems wrong. The programmer's no longer with our company."

Watch the multi-agent collaboration unfold in the reasoning panel:

Step 3: Observe the Agent Reasoning Flow

⚠️ FIELD NOTE: Pay close attention to this workflow - it's the heart of how Qlik Answers investigates data issues.
1. Answer Agent Activates: First on the scene, determining what data sources might contain relevant information about case statuses.
1. Semantic Agent Searches: Scans your application's data model to find the most relevant fields. It identifies perfect matches: Total Cases, Closed Cases, Open Cases, and the Status field.
1. Data Analyst Agent Plans: Creates a step-by-step analysis strategy to break down the case counts by status.
1. Chart Agent Visualizes: Builds a visualization showing the breakdown: Resolved, Closed, Escalated, In-Progress, and Open cases.
1. Answer Agent Synthesizes: Combines all findings and delivers the verdict.
Step 4: Analyze the Discovery

The Answer Agent reveals the mystery: there's a hidden "Resolved" status in your data model containing 19 cases!

The complete breakdown:
- Resolved: 19 cases (the missing number!)
- Closed: 15 cases
- Active (Open + In-Progress + Escalated): 16 cases
- Total: 50 cases ✓
The Explanation: "Resolved" represents cases where agents completed their work, but haven't yet received client confirmation to officially close them. It's essentially a holding status between active work and final closure.

The assistant even suggests intelligent follow-up questions like "What is the breakdown of the 19 resolved cases by priority level?" or "How many days on average do cases spend in resolved status before closing?"

Step 5: Request the Dashboard Fix

Now that you understand the problem, ask your assistant to fix it:

"Can you add a KPI to my dashboard to show me the number of resolved cases so that our totals will look correct?"

Watch another beautiful agent collaboration:
1. Answer Agent recognizes the request to add a KPI visualization
2. Semantic Agent finds the appropriate field: Number of Resolved Cases
3. Dashboard Authoring Agent checks for existing relevant visualizations
4. Chart Agent creates the KPI specification
5. Data Analyst Agent designs the analysis package (single metric, no dimensions)
6. Dashboard Authoring Agent adds the KPI showing "19 Resolved Cases" to your dashboard
Step 6: Verify and Finalize

Return to your Q Division application. The AI has created a new sheet called "Case Status Dashboard" with the Resolved Cases KPI displaying the value 19.

Important: Since your original dashboard is a public sheet, the AI created a new private sheet rather than modifying the public one. To complete the mission, you'll need to manually:
1. Make the public dashboard private (or create a working copy)
2. Copy the Resolved Cases KPI from the AI-generated sheet
3. Add it to your main dashboard
4. Style it to match your existing KPIs
Now your dashboard shows: Closed (15) + Resolved (19) + Active (16) = Total (50) ✓

✅ Mission Debrief

What You've Accomplished:

✓ Connected an application to your Qlik Answers assistant

✓ Used Qlik Answers to diagnose a dashboard inconsistency using programmer documentation

✓ Discovered a hidden status field causing reconciliation issues

✓ Generated a new KPI visualization through natural language

✓ Understood multi-agent workflows combining semantic search, data analysis, and dashboard authoring

Validation Check: Can your dashboard now reconcile to 50 total cases with all statuses visible? If yes, mission accomplished!

Challenge Exercise (Optional): Ask your assistant to build a text object for your dashboard that explains the case status values.

📚 Field Notes: Technical Deep-Dive

For this mission, the Qlik Answers Assistant needed access to both the structured application and it's data as well as the unstructured programmer notes.

Understanding the Multi-Agent Specialist System

This mission showcased all of the agentic agents that Qlik Answers uses:

Answers Agent: Orchestrates the entire process: Decomposes the questions users ask into sub-tasks, and presents final findings back to users.

Knowledge Agent: Searches through vector database to get relevant unstructured data

Semantic Agent: Expert at understanding your data model's structure, field names, and relationships. It's like a data dictionary that speaks human language.

Data Analyst Agent: Designs analysis packages that specify what data to use, how to analyze it and what output best answers the question(s).

Chart Agent: Specializes in visualization design after receiving the analysis package from the data analyst agent.

Dashboard Authoring Agent: Consumes outputs from the answer agent, data analyst agent or chart agent, investigates if existing required charts already exist.

Each agent is optimized for its specific task. When they collaborate, you get both depth and accuracy.

Why This Mission Matters for Real Organizations

The scenario in this mission - programmer leaves, new designer inherits an application, numbers don't reconcile - happens constantly in enterprises. Traditional approaches require:
- Digging through data model documentation (if it exists)
- Manually exploring every table and field
- Writing SQL queries to test hypotheses
- Rebuilding institutional knowledge from scratch
With Qlik Answers, you simply ask what's wrong and let the AI investigate the data model itself. The time savings are enormous, but more importantly, you don't lose critical business logic when people change roles.

The "Resolved" Status Pattern

This specific scenario - a holding status between "active" and "closed" - appears in many business processes:
- Support tickets: "Pending Customer Response"
- Sales opportunities: "Verbal Commitment" (before contract signature)
- Project tasks: "Delivered for Review" (before final approval)
- Purchase orders: "Goods Received" (before payment processing)
These intermediate states are often invisible in executive dashboards, leading to the exact reconciliation problems we solved in this mission. The pattern repeats across industries because workflows are rarely binary (open/closed) - they have nuanced intermediate states that matter for operations but get overlooked in reporting.

🎬 That's a Wrap, Operatives

You've successfully completed Field Training Mission 200 and learned how to use Qlik Answers as your data detective. As I mentioned in the video, I honestly never suspected a day when AI could auto-transcribe programmer notes, let alone use those notes alongside the application itself to solve data mysteries. But here we are, operatives. The future of analytics isn't just faster dashboards - it's intelligent systems that understand your data as well as the people who built it.

Questions? Feedback? Have you ever encountered a situation like this in the past where you had to take over maintenance of an application and something didn't add up?
Show Less
By Dalton_Ruer 2026-02-08 / 10:21 AM

0 0 162
Member Articles

MCP - Creating your Secret Sauce

Your Secret Sauce "Let's make it simple" - one recipe at a time Just like real chefs each of you has your own secret ingredients that make your Qlik ... Show More
Your Secret Sauce

"Let's make it simple" - one recipe at a time

Just like real chefs each of you has your own secret ingredients that make your Qlik work delicious and that people can recognize. Your secret sauce goes beyond just throwing random objects on the screen. It goes beyond just slapping a Select * of tables into your load script and data model. It goes beyond making up new expressions in charts.

But your secret sauce takes time to prepare.

I know mine sure does.

Because it's manual. If I want things to be a certain way, or look a certain way I have to spend the time. This post and the video are to encourage you that when you enter the Claude chat sessions, you don't have to go alone.

You can predefine your secret sauce so that's always at the ready. Taking the great meal you have in your head, that Chef Claude helps you prepare, and have your secret sauce added to it.

Your secret sauce prevents Claude from doing what you just asked because you were in a hurry.

Your secret sauce provides the boundaries in which Claude will work, and ensure that what you generate will follow your approved standard.

While you don't want Claude to follow a "just sling it on the screen" methodology, you also don't want to have to do this each and every time:

Like any new person that might join your team ... you want to have Claude follow your 99 explicit - gold standard guidelines, without having to type them in. That means taking them to teach him the skills needed to ensure your standard is followed. Just as you would teach Fred, Sally, Suzie or Bob.

Each of the following skills represents a critical ingredient in the art of making complex analytics deliciously simple. No matter how much of a rush is on you.

Master Items

Building reusable, governed analytics components
This skill governs how master dimensions and master measures are created, documented, and maintained in Qlik applications. It establishes a governance framework that treats master items as reusable, governed analytics building blocks that must be thoroughly documented with descriptions, tags, business context, and calculation logic. The skill defines when to create master items versus ad-hoc fields, emphasizes rich metadata that helps users understand what they're using, and establishes naming conventions that make items discoverable. It covers expression patterns for measures including proper aggregation contexts, handles dimension creation with drill-down hierarchies, and ensures that master items follow the same field naming standards as the load script. The skill transforms master items from simple field lists into a governed analytics vocabulary that enforces consistency across all sheets and visualizations while making it easier for users to self-serve.

🎯 Chef's Philosophy: Master items are your mise en place - prepare once, use everywhere. Good governance starts with well-documented, consistently named building blocks that anyone can understand and reuse. 📊

Sheet Creation

Audience-driven dashboard design methodology

This skill implements Qlik Dork's audience-driven workflow methodology for building Qlik sheets and dashboards. It starts by identifying the audience type (Financial, Clinical, Operations, or other domain-specific roles) and transforms metrics to match that audience's motivation and mental model. The skill follows a structured workflow: audience identification → metric transformation → context parameter collection → template selection → sheet building using a Story→Data→Visuals approach. It emphasizes that different audiences need the same data presented differently based on their decision-making context and priorities. The skill includes template selectors for common use cases, design patterns for effective visualizations, and ensures that dashboards tell a clear story rather than just dumping data on the screen. It transforms sheet creation from "what charts should I add?" into a strategic design process that starts with understanding who needs to make what decisions and works backward from there.

🎯 Chef's Philosophy: Great dashboards aren't about showing data - they're about telling stories that drive action. Know your audience, speak their language, and design with purpose. ⚙️

Load Script

Standardized data loading patterns

This skill establishes the foundational rules for generating Qlik load scripts that connect to Snowflake and transform data correctly. It mandates a critical "stop and ask first" workflow - you must gather information about the audience, data grain, required fields, and business context before writing any code. The skill defines specific syntax patterns including the Snowflake connection format using LIB CONNECT, the preceding LOAD pattern for transformations, and strict field naming conventions using table prefixes (like fct_adm_admission_id). It covers date handling standards using Floor() for clean date fields, calendar key creation as integers, and proper table aliasing with square brackets. The skill also includes YAML-based code generation patterns, validation workflows using qlik_create_data_object to verify field existence, and emphasizes the "one wrong decimal = lost trust" philosophy where accuracy always trumps speed.

🎯 Chef's Philosophy: Clean, well-structured scripts are like organized recipes - easy to follow, easy to modify, and they produce consistent results every time. ✅

Validation

Quality control before deployment

This skill provides a secondary validation process to verify calculations are correct before declaring work complete. It acts as a quality control checkpoint that prevents common mistakes like Sum() versus Count() errors from reaching end users. The skill defines specific validation workflows to check measure calculations, dimension values, filter logic, and data model relationships. It establishes a systematic review process that catches errors before they erode trust, reinforcing the "one wrong decimal = lost trust" philosophy. The skill triggers after creating any calculated measures, KPIs, or complex expressions, serving as the final quality gate before presenting work to users. It's essentially a "trust but verify" framework that ensures analytical accuracy through structured verification steps rather than hoping you got it right the first time.

🎯 Chef's Philosophy: Taste before serving! Validation is your quality control checkpoint - catching mistakes before they reach users saves time, credibility, and trust. ❓

Questions About Data

Critical thinking framework as Chief Question Officer

This skill establishes rules for how to answer data analysis questions in a way that promotes critical thinking and data literacy. It requires transparency about assumptions, defaults, and data interpretation choices rather than just providing answers. The skill mandates explaining the "why" behind analytical decisions - why certain filters were applied, why specific aggregations were chosen, why particular time periods were used. It transforms simple question-answering into an educational process where users learn to think more critically about their own data queries. The skill prevents the "black box" problem where users get answers without understanding the logic behind them, and instead builds their analytical capabilities by making the reasoning transparent. It's designed to teach users to ask better questions rather than just accepting whatever answer comes back.

🎯 Chef's Philosophy: As Chief Question Officer, curiosity is your superpower. The best analytics start with the right questions - about data sources, quality, relationships, and business context. 🎨
Presentation

Professional branding and delivery standards

A simple, straightforward skill that ensures Claude uses official Qlik brand colors when creating PowerPoint presentations. This skill provides the exact RGB and hex values for all six Qlik brand colors (Green, Blue, Aqua, Blended Green, Fuscia, and Deep Purple) along with ready-to-use Python code snippets for python-pptx implementation.

Perfect for anyone who needs to create Qlik-branded presentations and wants consistent, accurate color usage every time. Just upload this skill to Claude, and it will automatically reference these colors when building your decks.

What's included:

All 6 official Qlik brand colors with RGB and hex values

Python code snippets for easy implementation

Quick reference table for manual use

No fluff, no complicated guidelines - just the colors you need to stay on-brand.

🎯 Chef's Philosophy: Presentation matters! Professional, consistent branding elevates your work from good to great. Make it beautiful, make it branded, make it memorable.
Seeing is Understanding

In this video I demonstrate how these skills turn the bland, into the sublime each and every time. Not only does the agentic nature of Claude working with Qlik MCP save you time, as you will see it can ensure that your gold standard is followed every single time.

Even though we both know there are occasions you don't follow your rules yourself due to time.

Show Less
By Dalton_Ruer 2026-01-25 / 06:41 AM

2 4 848
Member Articles

Q Division Field Training: Module 100 - Q Division Application Upload

Pivoting from Unstructured to Structured Data 🎯 Mission Briefing THE SITUATION: You've proven yourself with unstructured data across Field Training... Show More
Pivoting from Unstructured to Structured Data

🎯 Mission Briefing

THE SITUATION: You've proven yourself with unstructured data across Field Training Modules 1-3. You've mastered knowledge bases, advanced chunking, and contextual intelligence. Now it's time to shift gears. The real power of Q Division emerges when you combine unstructured documentation WITH structured data that resides in live applications.

YOUR MISSION: Get access to the Q Division Application - the actual case tracking system that our operatives use in the field. Upload it to your environment, make it available to Qlik Answers, and ask questions about the structured data within. You'll meet two NEW agents: the Semantic Agent and the Data Analyst Agent.

THE MYSTERY: Figure out exactly what the "Active Case Percentage" KPI showing?

DELIVERABLE: A fully indexed Qlik application connected to Qlik Answers, with the ability to ask natural language questions about structured data and receive detailed explanations.

PREREQUISITES: ⚠️ Complete Modules 1-3 first to understand knowledge bases and unstructured data. This module introduces structured data as a contrast and foundation for Module 200 where we'll combine BOTH!

📦 Field Equipment

What You'll Need:
- Access to Qlik Answers in your environment
- Completed Modules 1-3 (understanding of knowledge bases)
- Q Division Application QVF file (included in download)
- Approximately 15 minutes mission time
- Your Field Training Assistant (we won't use it in this module, but you'll need it for Module 200!)
Download Mission Pack: 📥 Q Division Application attached

Video Intelligence Briefing: 🎥 Watch the Full Mission Walkthrough

🚀 Mission Steps

Step 1: Upload the Q Division Application

Navigate to your Q Division Field Academy space in your Qlik hub.

Click to upload a file and select the QDivision.qvf file that you downloaded from the community page.

The upload process should take just a few seconds. Once complete, you'll see the Q Division application appear in your space.

Click to open the application - let's take a quick tour before we make it available to Qlik Answers.

Step 2: Make the Application Available to Qlik Answers (CRITICAL STEP)

⚠️ FIELD NOTE: This is the KEY step that connects structured data to AI!

Here's something you need to know about ANY of your apps - whether it's this Q Division application we just uploaded, or one that you already have on your site:

You must explicitly enable Qlik Answers access in the application settings.

Why? Not all of your applications should be made available. When you're doing development on things, you don't want to confuse users with 18 versions of the same application. Governance matters!

Here's how to enable it:
1. Open the Q Division application
2. Navigate to Settings (typically in the app menu)
3. Click Capabilities
4. Find the option to "Make available to Qlik Answers"
5. Toggle that button ON
Watch what happens:

You'll notice a message appear saying "Indexing this application for you..."

This is similar to knowledge base indexing, but instead of parsing PDFs, it's analyzing:
- Master items (dimensions and measures)
- KPI definitions and calculations
- Field names and values
- Set analysis expressions
- Data model relationships
- Vocabulary and business terms
Once it's done, you'll see a message: "Indexing complete"

The toggle will flip all the way and turn green ✓

You're ready to go!

Step 3: Tour the Dashboard (Before We Ask Questions)

We can start jumping into Answers, but let's hold off on pressing that button just for a second. Let's go to the dashboard - because you know the dashboard is the place to be!

Take a look at this very well-thought-out application:

What you'll see:
- Number of Closed Cases: 15
- Active Cases: 16
- Add those together: 15 + 16 = ...30.50?
🤔 WAIT A MINUTE...

I don't know about you, but in 007 Dork's mind, that should be 31. What in the world? That doesn't add up!

I wish we had the original programmer to understand these values and what we might be missing...

🎯 SPOILER ALERT: Don't worry, operatives! In Field Mission 200, we're going to take a look at this because that is obviously a problem. And what we're gonna do in Mission 200 is look at questioning structured AND unstructured data together. If you'll recall from Module 2, I set this up for this very scenario when we talked about case status values! wink wink

For now, let's move on to the next question...

Step 4: Navigate to Field Mission 100 Analysis

Go to the screen labeled "Field Mission 100" in the application.

You'll see it tells us that our Active Case Percentage is 16%.

Now that'd be nice if users could just... ask a question and get that KPI defined for them, beyond just the brief description in the Master Item, right?

Well, guess what? THEY CAN!

Step 5: Ask Your First Structured Data Question

From within the application, click to open Qlik Answers

I'm going to paste this question right in here (because you've seen my typing, and we don't have all day):

"Can you describe for me in detail what the Active Case Percentage value is?"

Now watch the magic happen...

Step 6: Meet the NEW Agents - Semantic Agent & Data Analyst Agent

Not surprising, the Answer Agent is the first one to show up. Whether it's structured data or unstructured data, the Answer Agent is ALWAYS gonna be first, trying to figure out what you're looking to do.

But now watch as it goes through different processes behind the scenes...

The Flow:

1️⃣ Answer Agent (Orchestrator)
- Receives your question
- Identifies this as a request about structured data
- Checks: "Hey, I found a Q Division application that contains this kind of information"
- Notes: "There are no unstructured data sources available" (because we're asking from within Qlik Answers in an app that is structured only)
2️⃣ Semantic Agent ← NEW AGENT ALERT!
- This agent hasn't appeared in Modules 1-3!
- Its job: Search the data and semantic model and return the relevant fields
- Searches fields, master dimensions, master measures, vocabulary
3️⃣ Data Analyst Agent ← ANOTHER NEW AGENT!
- Takes the information from the Semantic Agent
- Builds an analysis package that specifies the data to use, how to analyze it and what output will best answer the users questions
4️⃣ Answer Agent (Response Synthesis)
- Collects all the intelligence
- Presents the comprehensive answer to you
Step 7: Analyze the Response

Look at what the AI returns:

"Active Case Percentage is a key performance indicator in our Q Division data. It shows you the percentage of cases that are currently Open or In Progress."

Notice what it did:
- ✓ Identified it as a KPI (not just a field)
- ✓ Converted the set analysis terms for us (Open + In Progress)
- ✓ Explained what it measures
- ✓ Provided the calculation details
Business Context: "This metric helps Q Division management understand workload distribution and resource allocation needs."

Interpretation Guidelines:
- Over 70-80% would indicate a workload buildup and insufficient resources
- Under 30% suggests efficient case resolution
- 40-60% suggests a healthy balance
Related Metrics You Might Want to See:
- Average case resolution time
- Cases by status breakdown
- Agent workload distribution
- Escalation rate
🤯 MIND. BLOWN.

The AI didn't just tell you what the KPI is - it gave you HOW to interpret it, WHAT benchmarks to consider, and WHAT other metrics complement it!

Step 8: Review the Reasoning (Always Show Your Work)

Click to expand "Show reasoning" or "Show details" to see the full agent workflow.

You'll see the complete conversation:
1. Answer Agent: "Let me gather data sources and figure this out..."
2. Semantic Agent: "Found matching KPI, here's the definition and calculation..."
3. Data Analyst Agent: "Based on the calculation, here's what it means and how to interpret it..."
4. Answer Agent: "Synthesizing all that intelligence into a comprehensive response..."
This transparency is CRITICAL for:
- Trust: Understanding how the AI reached its conclusion
- Debugging: Identifying if the AI misunderstood something
- Learning: Seeing how different agents specialize
- Governance: Auditing AI recommendations
✅ Mission Debrief

What You've Accomplished:
- ✓ Uploaded a Qlik application to your environment
- ✓ Made the application available to Qlik Answers (enabled indexing)
- ✓ Asked natural language questions about structured data
- ✓ Met the Semantic Agent (KPI and field vocabulary expert)
- ✓ Met the Data Analyst Agent (interpretation and context expert)
- ✓ Received comprehensive KPI explanations with calculations and benchmarks
- ✓ Understood the agent orchestration workflow for structured data
Validation Check: Can you ask your Q Division application questions about KPIs and get back detailed explanations including calculations, business context, and interpretation guidelines? If yes, you've mastered structured data querying! 🎯

The Mystery Remains: We still haven't solved why 15 + 16 = 50 instead of 31. And THAT, operatives, is where Module 200 comes in...

Challenge Exercise (Optional): Ask other questions about the Q Division application:
- "Can you describe each of our agents roles?"
- "Can you describe the risk scores that we use to classify villains?"
See how the Semantic Agent and Data Analyst Agent work together to provide comprehensive answers. Don't be surprised if a new Q Division assists!

🎬 Intelligence Secured. Licensed to Query.

You've successfully shifted gears from unstructured to structured data. You've met two new agents who specialize in understanding your applications' vocabulary and interpreting what your KPIs mean in business context.

Questions? Feedback? Are you becoming more comfortable with the Agentic experience of agents working together?

Show Less
By Dalton_Ruer 2026-02-05 / 11:57 AM

0 2 113
Member Articles

Q Division Field Training: Module 3 - Expense Statements

Advanced Chunking, Enterprise Connections & The Power of Context 🎯 Mission Briefing The name's Dork. 007 Dork. They say you're only as good as your ... Show More
Advanced Chunking, Enterprise Connections & The Power of Context

🎯 Mission Briefing

The name's Dork. 007 Dork. They say you're only as good as your questions. Well, lucky for you, I never miss.

THE SITUATION: Missions one and two involved rather static data. Today we're dealing with something much more near real-time: expense statements. After each Q Division mission closes, travel and expense statements get generated and logged. But something caught my eye while walking through accounting... a 4TB external hard drive and an encrypted USB drive on an agent's expense report. That seems a little "sus" to me, operatives. Double agent? Corporate espionage? Or legitimate operational expense?

YOUR MISSION: Build a knowledge base around agent expense statements using enterprise storage connections (like Amazon S3 buckets where files are constantly being inserted), enable advanced accuracy for complex multi-page tables, add this intelligence to your Field Training Assistant, and then test a theory about whether we've got a rogue agent on our hands.

DELIVERABLE: An enhanced assistant with three knowledge bases that can perform forensic accounting analysis across complex expense documents, understanding context that spans multiple pages and document sections.

PREREQUISITES: ⚠️ You must complete Modules 1 & 2 first! You'll need your existing Field Training Assistant with Agent Information and Application Design knowledge bases already configured.

📦 Field Equipment

What You'll Need:
- Access to Qlik Answers in your environment
- Completed Modules 1 & 2 (Field Training Assistant with 2 knowledge bases)
- Q Division Expense Statement documents (15 PDF files included in download)
- Approximately 20 minutes mission time
- Optional: AWS S3 bucket credentials (we'll show you the manual alternative)
Download Mission Pack: 📥 QDivision_Field_Expense_Reports.zip attached

Video Intelligence Briefing: 🎥 Watch the Full Mission Walkthrough

🚀 Mission Steps

Step 1: Create Your Agent Expense Statements Knowledge Base

Navigate to your Answers section from your hub (not your applications - we don't want to see all that other junk cluttering our intelligence operations).

Click to create a new knowledge base and name it: "Agent Expense Statements"

Normally you'd add a description here, but we're field operatives on a mission, so let's keep moving!

Step 2: Enable Enhanced Accuracy (CRITICAL FOR THIS MISSION)

⚠️ FIELD NOTE: This is NEW and IMPORTANT!

Before adding files, toggle on the "Enhanced Accuracy" flag.

Why? These expense statements contain:
- Multi-page tables that cross page boundaries
- Timeline information mixed with expense line items
- Mission notes at the top, expenses at the bottom, activities scattered throughout
- Relationships between purchases and mission context that span three pages
Enhanced accuracy uses advanced chunking to handle these complex document structures. It takes a bit longer to process, but when you see what's in these expense statements, you'll absolutely understand why we need it.

The Trade-off:
- Standard processing: Fast, good for simple documents
- Enhanced accuracy: Slower, essential for tables and cross-page relationships
For expense forensics, we need enhanced accuracy. Period.

Step 3: Choose Your Data Source Approach

Here's where it gets interesting. I'm going to show you TWO approaches:

APPROACH A: Enterprise Storage Connection (S3 Bucket) - The Professional Way

Click "Add from connection" and select your space.

Choose your connection - in my case, "Q Division Expense Statements" which points to an Amazon S3 bucket.

The Power of Connections: When looking at enterprise file storage connectors, you can set up filters:
- Only pull files after certain dates
- Exclude files under/over specific sizes
- File type filtering
- Automatic indexing schedules
The Magic: As new expense statements get dropped into your S3 bucket, they can be indexed without manual uploads.

You can either:
- Set up automatic filters (recommended for production)
- Do manual selection (I'll select specific expense statements from my bucket)
In this scenario, the files stay in S3 - they're not copied to your Qlik tenant. You're indexing references to enterprise storage.

I would now select each expense statement from my bucket and add them to my knowledge base.

APPROACH B: Manual File Upload (The Field Operative Workaround)

But wait... my poor field operatives out there don't have access to MY S3 bucket, and I'm not giving you my secret key! That's classified information!

So here's what we're ACTUALLY going to do:

Click "Add files" and choose "Browse" to upload files directly.

Navigate to your unzipped mission pack containing the Q Division expense statement PDFs.

Select ALL 15 expense statement files and upload them.

You'll see them loading into your knowledge base.

Step 4: Index with Advanced Processing

I'm not even going to suggest it because you're going to wag your finger at me...

These are NOT indexed yet. You are NOT ready to use these until you've indexed them!

Click "Index All"

Now, because we turned on Enhanced Accuracy, this is going to take longer than our previous modules. Don't panic!

What's happening behind the scenes:
- Advanced chunking is analyzing table structures
- Vector embeddings are being created with enhanced precision
Watch the progress. You'll start seeing files complete their indexing. Keep scrolling to monitor status.

Wait for completion: You should see 39 pages across 15 different documents indexed.

Refresh and verify: "Index Status: Completed" with a recent timestamp (if it says "5 weeks ago" when you come back in 5 weeks, we've got problems!).

Step 5: Add Third Knowledge Base to Your Assistant

We're NOT creating another assistant. We want to tie ALL this intelligence together!

Navigate back to the Answers catalog. With all those files and knowledge bases accumulating, use the filter to show "Assistants and Knowledge Bases only" so you can find what you need.

Open your "Field Training Assistant" (the one you created in Module 1 and enhanced in Module 2).

Click to add content, then select "Add a knowledge base".

Filter to your "Q Division Field Academy" space.

Select "Agent Expense Statements" - notice it's the only one NOT grayed out (the others are already connected).

Click to add it.

Boom. Your assistant is now ready. Everything is indexed. Your agent has three knowledge bases:
1. Agent Information (Module 1)
2. Application Design (Module 2)
3. Expense Statements (Module 3)
This is business, operatives!

Step 6: The Forensic Accounting Test

Expand your assistant chat interface. I'm going to paste this question because you've seen my typing in other modules - it can be pretty bad:

"I reviewed the expense statement in the knowledge base for Case 103, and it seems suspicious to me that the agent purchased hard drives and a USB. Does that raise any red flags with you? Are they understandable?"

Before we see the AI's response, let me show you what I saw...

Scroll through the expense statements for Case 103. You'll find on November 16th:
- External hard drives (4TB capacity)
- 10-port USB hub with encryption
I don't know why an agent who's out in the field getting wined and dined and meeting with clients is buying hard drives! That raises a red flag to me. If I were a human auditor reading this, that seems a little flaky!

Now watch what happens...

Step 7: The Answer Agent Goes to Work

You already guessed it - yes, the Answer Agent is on the job right away:
- Gets all data sources
- Understands the context is about Case 103
- Tries to find the right information
The Knowledge Base Agent gets involved next:
- Performs vector search for this information
- Searches for hard drives related to this case
- Returns a whole bunch of contextual information about what the case is about
Step 8: The Plot Twist (This Is Where It Gets Interesting)

I came in here assuming this agent was up to no good. I happened to read an expense statement. I think something's flaky. This is crazy!

But here's what the AI comes back with:

"The hard drive and USB are legitimate operational expenses. They don't raise any red flags. Let me give you the context: The case involved Operation False Precision, a data center investigation. These purchases are justified given that they were conducting forensic analysis of an ETL pipeline and code. All expenses comply with operational requirements."

WAIT, WHAT?!

When I jumped in to show you those suspicious expense line items, I didn't show you the mission notes at the top of the expense statement that documented the investigation activities and timeline!

Step 9: Understanding the Real Magic Here

Let me be crystal clear about what just happened, operatives:

This isn't just a search-and-find operation.

The other modules had super easy questions. I want you to understand the logic going on here - the collective wisdom of the world that's in that large language model that Qlik Answers is sitting on top of.

Here I am trying to do forensic accounting. I get the wisdom of the world saying:

"Whoa, whoa, whoa, 007 Dork! You've got binoculars on and you are FOCUSED on that expense line, and that is NOT what you need to see. You need to see the BIG PICTURE of what was going on!"

The AI was able to interpret from both contexts in a knowledge graph - these things are related:
- The expense line items on page 3
- The mission activities documented on page 1
- The case notes explaining the investigation
- The timeline showing when forensic analysis occurred
It connected the dots across multiple pages and document sections.

Operatives, you gotta be loving that! If you're not ready to dig in even deeper, I don't know what's gonna get you excited about Qlik Answers!

✅ Mission Debrief

What You've Accomplished:
- ✓ Created knowledge base with enhanced accuracy enabled
- ✓ Learned about enterprise storage connections (S3 buckets)
- ✓ Uploaded and indexed complex multi-page documents with advanced chunking
- ✓ Added third knowledge base to your Field Training Assistant
- ✓ Performed forensic accounting analysis with AI
- ✓ Witnessed contextual understanding that spans multiple document sections
- ✓ Experienced the difference between search and true intelligence
The Big Lesson: As a young Dork, I found that my focus could be very narrow. I would see one piece of information and jump to conclusions. If there's one thing I've learned here in Q Division, it's that the real story usually involves the ability to see a much larger context - one that's larger than even my Dork brain can handle.

Asking Qlik Answers is my way of ensuring that all the elements are being accounted for, and that in conjunction with the collective wisdom of the world in that large language model, the answers to my questions make me look a whole lot smarter.

Your Mission (Should You Choose to Accept It): Ask ONE better question today.

Next Mission: Module 4 will introduce data connections to live Qlik applications, combining structured data WITH all this unstructured intelligence. The Q Division Operation Data application will finally be revealed!

Challenge Exercise (Optional): See how far we can push this concept. Ask your assistant the following question: "The agent from Case 1006 returned from the mission acting a little sus, and an English-Russian dictionary slipped out of his attaché case. Please Conduct a comprehensive counter terrorism review of the expenses for case 1006 and please flag anything suspicious or out of scope for the mission, the target or the environment."

📚 Field Notes: Technical Deep-Dive

Why Use Storage Connections Instead of Direct Upload?
1. Auto-Update: New files automatically get indexed
2. Scale: Handle thousands of documents without manual uploads
3. Single Source of Truth: Files stay in your enterprise storage
4. Version Control: Updates to files are reflected automatically
5. Governance: Leverage existing access controls and permissions
6. Cost: Don't duplicate storage across systems
How Context Understanding Actually Works

When I asked about the suspicious hard drive purchase, here's what happened technically:

Step 1: Query Processing
- User question parsed for intent: "Are these expenses suspicious?"
- Key entities extracted: Case 103, hard drives, USB
Step 2: Vector Search
- Knowledge Base Agent searches for semantically similar content
- Finds expense line items matching "hard drives" and "USB"
- Also finds mission notes containing related operational context
Step 3: Knowledge Graph Assembly
- AI recognizes these chunks are from the same document
- Identifies temporal relationships (mission timeline)
- Maps expense items to mission activities
- Understands cause-effect: "forensic analysis" → "data storage equipment"
Step 4: Collective Wisdom Application
- LLM knowledge: "Forensic investigations typically require data storage"
- Domain reasoning: "Hard drives are standard tools for ETL analysis"
- Context synthesis: "Expenses align with documented mission objectives"
Step 5: Response Generation
- Reframes the question with full context
- Provides evidence from multiple document sections
- Offers conclusion based on holistic understanding
This is NOT:
- Simple keyword matching
- Basic search and retrieval
- Pattern recognition without understanding
This IS:
- Semantic relationship mapping
- Cross-document reasoning
- Contextual intelligence with world knowledge
- Evidence-based conclusions
The Difference Between Search and Intelligence

Traditional Search Would Return:
- "Found: 4TB hard drive on line 47"
- "Found: USB hub on line 52"
- End of story
Qlik Answers Returns:
- The expense items (with citations)
- The mission context explaining WHY they were purchased
- The operational justification from the case notes
- A reasoned conclusion about legitimacy
- Connections I didn't even know to look for
Real-World Application: This is the difference between:
- ❌ "Here are all documents containing 'budget overrun'" (search)
- ✅ "The budget variance is explained by Q3 supplier changes documented in procurement notes, which align with the strategic pivot mentioned in the board minutes" (intelligence)
Use Cases Where This Matters:
- Compliance auditing (connecting transactions to policies)
- Root cause analysis (linking symptoms to causes across documents)
- Due diligence (connecting financial data to operational context)
- Knowledge transfer (understanding the "why" behind the "what")
- Decision support (seeing the full picture before acting)
🎬 Mission Accomplished, Operatives!

You've graduated from simple document retrieval to contextual intelligence that understands relationships across complex multi-page documents. You've seen firsthand how AI can provide the larger context that even a focused analyst might miss.

Your Field Training Assistant now has three knowledge bases working in harmony. It can answer questions about agents, application design, AND financial operations - all with citations and contextual understanding.

Remember: The most dangerous weapon in your arsenal isn't a golden gun - it's a golden question! And sometimes, the best answer is the one that shows you what you DIDN'T know to ask about.

Dork 007 Dork, signing off. Keep your chunking advanced and your context windows wide.

Questions? Feedback? What did the challenge question yield for you in terms of results and which agent do we need to investigate if Qlik Answers confirmed anything suspicious? 👎 Use the feedback button or share your forensic accounting stories

#QlikAnswers #QlikSense #DataAnalytics #BusinessIntelligence #AIAssistant #RAG #QlikDork #QDivision #007Dork #AdvancedChunking #EnhancedAccuracy #ForensicAccounting #ContextualAI #SemanticSearch #DocumentIntelligence #AIReasoning #KnowledgeGraph #AskBetterQuestions
Show Less
By Dalton_Ruer 2026-02-03 / 06:55 AM

0 1 119
Member Articles

Q Division Field Training: Module 2 - Application Documentation

Mastering Catalog Integration & Multi-Knowledge Base Assistants 🎯 Mission Briefing The name's Dork. 007 Dork, and I have a license to question. THE ... Show More
Mastering Catalog Integration & Multi-Knowledge Base Assistants

🎯 Mission Briefing

The name's Dork. 007 Dork, and I have a license to question.

THE SITUATION: A customer has experienced turnover in their development department. There's yelling. Lots of yelling. "WHAT DO THESE VALUES MEAN?!" echoes through the halls. Dashboard fields are a mystery. Status codes are hieroglyphics. Chaos reigns.

YOUR MISSION: Add unstructured application design documentation to the Qlik catalog, create a new knowledge base from those existing files, and enhance your Field Training Assistant with this intelligence. Then query the original programming team's documentation to understand what those mysterious values actually mean.

DELIVERABLE: An enhanced assistant that can answer questions about both agent information AND application design documentation, demonstrating how knowledge bases can share files and grow in power over time.

PREREQUISITES: ⚠️ You must complete Module 1 first! You'll need your existing Field Training Assistant from that mission.

📦 Field Equipment

What You'll Need:
- Access to Qlik Answers in your environment
- Completed Module 1 (Field Training Assistant must exist)
- Q Division Application Design documents (2 PDF files included in download)
- Approximately 15 minutes mission time
Download Mission Pack: 📥 ZIP file attached

Video Intelligence Briefing: 🎥 Watch the Full Mission Walkthrough

🚀 Mission Steps

Step 1: Upload Documentation to Your Catalog

This time, we're taking a different approach. Instead of uploading files directly to a knowledge base, we're adding them to the Qlik catalog first. Why? Because catalog files can be shared across multiple knowledge bases and assistants - upload once, use everywhere!

Navigate to your Qlik hub and locate the file upload area.

⚠️ CRITICAL: At the bottom of the upload dialog, verify the space selector is set to "Q Division Field Academy" - do NOT let it default to your personal space!

Unzip your mission pack and drag and drop both PDFs into the upload area:
- Q Division Data Model documentation
- Q Division Case Status documentation
Watch as they load into your catalog. You now have 2 additional files in your Q Division Field Academy space.

Step 2: Create Your Application Design Knowledge Base

Click to create a new knowledge base and name it: "Q Division Application Design"

This knowledge base will contain information about how your Q Division application (which you'll build in a future module) was originally designed by the programming team.

Here's where it gets interesting. In Module 1, we walked through browsing and uploading files directly. But now those files already exist in your catalog!

Instead of the "Upload files" option, choose "Use from catalog".

Filter to show files from "Q Division Field Academy" space.

Select both documents:
- ✓ Q Division Data Model
- ✓ Q Division Case Status Documentation
Click to add them to your knowledge base.

Step 3: Index Your Application Intelligence

If you're wagging your finger at the screen right now saying "But 007 Dork, you forgot to index!" - EXCELLENT! You're learning!

Navigate to your new "Q Division Application Design" knowledge base and check the index status. It will show "Never been indexed."

Click "Index All" and wait for completion. Each document should index quickly.

Refresh and verify: "Index Status: Completed" ✓

Step 4: Enhance Your Existing Assistant (DO NOT Create a New One!)

Here's the power move. We're NOT creating a new assistant. We're making your existing assistant smarter by adding a second knowledge base to it.

Navigate to the Answers section and find your assistants.

Pro tip: If you're lost in a sea of documents, use the filter at the top to show "Assistants only" - you'll recognize them by their distinctive icons.

Open your "Field Training Assistant" that you created in Module 1.

You'll see it already has access to the "Agent Information" knowledge base (it's even grayed out to show it's already connected).

Now click to add another knowledge base. Filter to "Q Division Field Academy" space.

Select "Q Division Application Design" and add it.

Boom. Your assistant now has access to TWO knowledge bases. This is how assistants grow in power over time!

Step 5: Query Application Design Documentation

Time to test your enhanced intelligence network. Expand the assistant chat interface and ask:

"Can you help me understand how agent case status is tracked and what the values mean?"

Watch the reasoning panel (because we're operatives, not civilians):
1. Answers Agent activates first - collecting data sources and formulating a strategy
2. Knowledge Base Agent takes over - searching through your newly indexed documentation
3. The response flows back with the Answers Agent delivering the answer
You should receive information about the case status phases:
- Open - Initial case creation
- In Progress - Agent is actively working
- Escalated - Requires higher authority
- Resolved - Agent work is complete
- Closed - Client has verified resolution
Step 6: The Critical Detail (Remember This!)

Pay special attention to this distinction: "Resolved" means the agent's work is done, but the case is NOT physically closed yet because we're waiting on client verification.

🎯 FIELD NOTE FOR FUTURE MISSIONS: Remember this distinction between Resolved and Closed! In an advanced training module, we're going to revisit this question when building applications. If you're not aware of this difference, your case number counts won't add up correctly, and you'll be scratching your head wondering why. Hint, hint, wink, wink!

Click on the citations to see exactly where in the documentation this information came from. Jump directly to the source documents if you want to read more context.

✅ Mission Debrief

What You've Accomplished:
- ✓ Uploaded files to the Qlik catalog (not directly to a knowledge base)
- ✓ Created a knowledge base using catalog files
- ✓ Enhanced an existing assistant with multiple knowledge bases
- ✓ Queried unstructured documentation about data meaning (not the data itself)
- ✓ Understood the critical difference between Resolved and Closed status
- ✓ Learned how knowledge bases can share files across assistants
Validation Check: Can you ask your Field Training Assistant questions about BOTH agent information (Module 1) AND application design (Module 2)? If yes, your assistant is now multi-talented! 🎯

The Big Picture: You've just learned how to scale your Q Division intelligence network. As you find more sources of unstructured data - design docs, meeting transcripts, training videos, data dictionaries, programmer notes - you can add them as new knowledge bases. Your assistants grow smarter over time without starting from scratch.

Challenge Exercise (Optional): One of the documents now available to you in the assistant describes the application. Find out how much you can learn about the application data model and master items without reading the PDF. You will soon earn the privilege of accessing the Q Division operational data application.

📚 Field Notes: Technical Deep-Dive

Why Upload to Catalog vs. Direct to Knowledge Base?

Catalog Upload Benefits:
- Reusability: One file can be used in multiple knowledge bases
- Governance: Centralized file management and version control
- Efficiency: Upload once, reference many times
- Organization: Better file discovery across your environment
🎬 Mission Accomplished, Operatives!

You've successfully enhanced your Field Training Assistant with application design intelligence. Over time, your assistants can grow in power as you find more and more sources of unstructured data and create more and more knowledge bases.

Your assistant started with only the ability to answer questions about agents themselves. Now it also supports questions about application design from the original programming staff - an application that will be revealed to you soon, operatives. But let's face it: you have more training to do before you're entrusted with Q Division Operation Data.

Remember: The most dangerous weapon in your arsenal isn't a golden gun - it's a golden question! 🎯

Dork 007 Dork, signing off. Keep your documentation indexed and your queries semantic.

Questions? Feedback? In this AI powered world with meeting transcripts automatically generated, what do you think of this idea of a knowledge base that stores them? Have you had situations in the past where a developer had left and you really could have used access to their original documentation? 👎
Show Less
By Dalton_Ruer 2026-02-02 / 02:02 PM

0 1 132
Member Articles

Qlik MCP - Cordon Green - Culinary School of Agentic Awesomeness

Welcome to the Qlik MCP - Cordon Green - Culinary School of Agentic Awesomeness Forget microwaved analytics. In these courses, you'll learn to build A... Show More

Welcome to the Qlik MCP - Cordon Green - Culinary School of Agentic Awesomeness

Forget microwaved analytics. In these courses, you'll learn to build AI-assisted Qlik applications and dining experiences with the precision and care of a master chef. As Sous Chefs in Chef Qlik Dork's kitchen, you'll master all of the features of what Qlik MCP offers you:

⚙️ Data Products - Starting with trusted ingredients (metadata, quality, governance)

⚙️ Building Screens - Plating your creations for YOUR DINERS with story-driven design

⚙️ Building Code - Pushing down predictable, repeatable code to your Qlik ovens

⚙️ Asking Questions - Teaching your diners to become Chief Question Officers

⚙️ Paradigm Shift - Understanding the transformation from builder to orchestrator

As each culinary course is developed they will appear below, but this brief introductory video will help you understand what is coming when Qlik MCP Server functionality is released in your #SaaS environments on February 10, 2026.

Cordon Green Courses

The goal of the courses here at the Cordon Green is to help your organization go from an ordinary agentic experience, to one that is EXTRAordinary.

100s: Knife Skills & Kitchen Setup (mise en place for the agentic kitchen)

👨‍🍳 Course 100 - Learning to create your Secret Sauce

Sharing my Secret Sauce to get you started

👨‍🍳 Course 120 - Defining the Organizational Gold Standard
👨‍🍳 Course 125 - Helping an LLM understand your context with Smart Defaults
👨‍🍳 Course 130 - The role of a Chief Skills Officer

200s: Understanding Ingredients (asking the right questions = knowing your ingredients)

👨‍🍳 Course 200 - Moving from Questions to Conversations
👨‍🍳 Course 210 - Security and Filters
👨‍🍳 Course 220 - Context Wars - Google vs LLM vs Human
👨‍🍳 Course 230 - Metacognitive Analytics - Thinking about Thinking
👨‍🍳 Course 250 - Chief Question Officer

300s: Quick Tips from the Sous Chef (those little technique refinements)

👨‍🍳 Course 300 - Discombobulated Sessions in Claude

👨‍🍳 Course 310 - Chaos to Clarity - Using Qlik MCP for Data Model Documentation

400s: Fusion Cuisine (integrating different culinary traditions/MCP servers)

👨‍🍳 Course 401 - Create Qlik application from Snowflake OSI Semantic View

500s: The Tasting Menu (showcasing the complete dining experience)

👨‍🍳 Course 501 - Create Qlik application from Qlik Data Product

Show Less

By Dalton_Ruer 2026-01-27 / 12:03 PM

0 2 510

Member Articles

Member Articles

Recent Documents

Prerequisites

Create the Agent

Register an OAuth App with Your Tenant

Add Tools from the MCP Server

Provision the Agent and Test in Copilot

Deploying and Publishing

Considerations

References

Qlik + Snowflake Cortex AISQL

Series Flow:

Qlik + Snowflake Cortex Agents

Series Flow:

Agentic approach? OSI Semantic Views?

Snowflake Cortex Code (CoCo)

Resources

Creating Your First Qlik Answers Knowledge Base

🎯 Mission Briefing

📦 Field Equipment

🚀 Mission Steps

Step 1: Establish Your Field Academy Space

Step 2: Create Your Agent Information Knowledge Base

Step 3: Deploy Your Agent Dossiers

Step 4: Index Your Intelligence (CRITICAL)

Step 5: Create Your Field Training Assistant

Step 6: Test Your Intelligence Network

✅ Mission Debrief

📚 Field Notes: Technical Deep-Dive

Why Citations Matter

🎬 That's a Wrap, Operatives

Purpose

Dossiers

Meet the Agents

QD-001 | The Maestro | Answers Agent

QD-002 | Cipher | Semantic Agent

QD-003 | Curator | Knowledge Agent

QD-004 | Architect | Data Analyst Agent

QD-005 | Illustrator | Chart Agent

QD-006 | Assembler | Dashboard Agent

QD-007 | Navigator | Help Agent

Mission Briefing

Field Training Exercises

Mission Playback

Agent Recognition Protocol

Solving the Mystery of Dashboard Numbers That Don't Add Up

🎯 Mission Briefing

📦 Field Equipment

🚀 Mission Steps

Step 1: Connect Your Application to Your Assistant

Step 2: Ask the Diagnostic Question

Step 3: Observe the Agent Reasoning Flow

Step 4: Analyze the Discovery

Step 5: Request the Dashboard Fix

Step 6: Verify and Finalize

✅ Mission Debrief

📚 Field Notes: Technical Deep-Dive

Understanding the Multi-Agent Specialist System

Why This Mission Matters for Real Organizations

The "Resolved" Status Pattern

🎬 That's a Wrap, Operatives

Your Secret Sauce

Master Items

Sheet Creation

Load Script

Validation

Questions About Data

Presentation

Seeing is Understanding

Pivoting from Unstructured to Structured Data

🎯 Mission Briefing

📦 Field Equipment

🚀 Mission Steps

Step 1: Upload the Q Division Application

Step 2: Make the Application Available to Qlik Answers (CRITICAL STEP)

Step 3: Tour the Dashboard (Before We Ask Questions)

Step 4: Navigate to Field Mission 100 Analysis

Step 5: Ask Your First Structured Data Question

Step 6: Meet the NEW Agents - Semantic Agent & Data Analyst Agent