# Why Are We Still Paying for Power BI? I Tested Claude Dashboards on a Real Excel Report Source: https://qvantx.com/insights/claude-just-dropped-dashboards-excel-to-live-dashboard-in-15-minutes/ Author: Ani Björkström — QvantX Sweden AB, Stockholm Published: 2026-10-18 Updated: 2026-11-08 Video: https://www.youtube.com/watch?v=bC_tvr0UweY (14 min) Topic: AI in Finance License: free to quote and cite with attribution to https://qvantx.com --- _AI IN FINANCE_ ## Can Claude Dashboards Replace Power BI for Finance Reporting? #### Key takeaways - For most everyday finance reporting, Ani Björkström's verdict is that you no longer need Power BI: Claude built a full management dashboard from a raw Excel P&L in under 15 minutes. - Claude Dashboards, released by Anthropic on October 8, 2026, turns a single-sentence prompt into live, filterable charts instead of static artifacts — and works on every paid plan, including Pro. - The one exception is the big regulated company: audited numbers, access controls (e.g. a manager in Sweden who cannot see salaries in Denmark), and automated reports to 200 people still require Power BI's control layer. Ani Björkström, who builds data and AI systems for banks and investment companies from Stockholm, tested Anthropic's new Claude Dashboards feature on a real-world monthly finance report. In the video, she takes a realistic monthly P&L report for a fictive company, Nordica Partners (FY2026) — three revenue centers, nine months of actuals, a full-year budget, and revenue broken down by region — and turns it into a live, interactive dashboard without writing code or involving a BI team. The exercise is built for finance professionals who currently depend on a data team or Power BI specialist just to see how the business is performing. ### What is Claude Dashboards and when was it released? Claude Dashboards is a feature from Anthropic, the company behind Claude, that lets users describe a dashboard in plain language and have Claude build the charts, filters, and numbers automatically. It was released on October 8, 2026, and is currently in beta, meaning it is new and still being improved. Unlike Claude's earlier "artifacts," which showed frozen, static data, dashboards can stay live: when connected to a data warehouse, the same link updates automatically as new numbers arrive. The feature is available on every paid Claude plan, including the standard Pro plan; enterprise customers need their account admin to switch it on first. ### How do you turn an Excel finance report into a Claude dashboard? Björkström's process took three steps: create a Claude project, upload the Excel file, and send one descriptive prompt. She first created a project called "Monthly report" in Claude Code (the web browser version works too) so she could return to update it each month or quarter, then uploaded a workbook with three tabs — P&L actuals (January–September), Budget (January–December), and Revenue by Region (Sweden, Norway, Denmark, Finland) — containing only raw revenue, COGS, personnel, marketing, IT and other operating cost figures, with no formulas or metrics — every calculation is left to Claude. Before building anything, she asked Claude to read and describe the data back to her, to confirm it understood the three tabs correctly. She then sent this exact Claude dashboard prompt: Now build a management dashboard from this data. I want to see:1. Revenue against budget, per month, for each revenue center2. Profit per revenue center — revenue minus all costs — month by month3. Which cost lines are higher than the budget4. Revenue by region.Make it possible to filter by revenue center and by month. As she points out, the only words Claude strictly needs are "build a dashboard"; the numbered list simply tells it which views management wants. Claude organized the build steps in a progress panel and produced the full interactive dashboard in under 15 minutes. ### Can you trust the numbers and share a Claude dashboard with colleagues? Yes — every chart can be traced back to its source formula, and the dashboard can be shared via a private link or direct email invite. Double-clicking any chart reveals an "Ask Claude" button and a "Source" button; the Source button shows exactly which formula and underlying data produced that number, so a finance reviewer can verify reliability before presenting the figures. The "Ask Claude" option opens a chat where users can ask questions about the numbers or request changes, such as switching a bar chart to a pie chart or changing the color scheme, with no technical team involved. Sharing works through a "Share" button that offers a copy-private-link option, which opens the live dashboard in any browser. ### Is Power BI dead now that Claude Dashboards exists? Björkström's direct answer is that for most reports in most companies, Power BI is no longer necessary — but one exception remains. She argues that Power BI's real costs — a specialist to build every report, training to use it, per-user licenses, and days or weeks of waiting — are now harder to justify when Claude can connect directly to the same data warehouses, including Snowflake, BigQuery, Redshift, and Databricks, and build a live dashboard from one sentence. The exception is the large regulated company: official numbers signed off by auditors, access rules such as a Swedish manager being blocked from seeing Danish salary data, and reports automatically distributed to 200 people every Monday. Because Claude Dashboards is only about one week old and still in beta, it does not yet replace that control layer. Her recommendation: small and mid-size companies have little reason to start a new Power BI project for normal reporting, while big regulated firms should keep Power BI for official audited reports and move everyday reporting — which she estimates is 80% of the work — to Claude. | Step | Action | Result | |---|---|---| | 1. Setup | Create a Claude project ("Monthly report") and upload the Excel file with P&L actuals, Budget, and Revenue by Region tabs | Claude reads and describes the three tabs back before building anything | | 2. Prompt | Send the four-part dashboard prompt covering revenue vs. budget, profit by revenue center, over-budget cost lines, and revenue by region, with filters | Full interactive dashboard built in under 15 minutes | | 3. Verify | Double-click any chart and select "Source" | Shows the exact formula and data origin behind each number | | 4. Share | Click "Share" and copy the private link, or invite colleagues by email | Live dashboard opens in any browser and updates when data changes | | 5. Scale | Connect Claude to a data warehouse (Snowflake, BigQuery, Redshift, or Databricks) instead of Excel | Dashboard refreshes automatically as new data lands | #### FAQ **Which Claude plans include Dashboards?** Claude Dashboards is in beta and works on every paid Claude plan, including the standard Pro plan. On an Enterprise plan, the account admin has to switch the feature on first. **Claude Dashboards vs Power BI: do I still need Power BI?** For most everyday reporting in most companies, Ani Björkström says no. She recommends keeping Power BI only for the control layer of large regulated companies: official audited numbers, row-level access rules and scheduled distribution to large audiences. **Which data sources can a Claude dashboard connect to?** Besides uploaded Excel files, Claude can connect straight to data warehouses such as Snowflake, BigQuery, Redshift and Databricks — the same tables Power BI reads — so the dashboard updates itself when new data arrives. **How is a Claude dashboard different from a Claude artifact?** Artifacts are frozen and show static data at the moment they were created. Dashboards can stay live — when connected to a data warehouse such as Snowflake, the same dashboard link automatically refreshes with new numbers. **Is it safe to upload real company financial data to Claude?** Ani Björkström used only fictitious data in her demonstration and explicitly warns that real company numbers are confidential — she advises checking your company's rules before uploading real data to any AI tool. ## Full video transcript Chapters: 0:00 Claude Dashboards: Excel to live dashboard · 0:22 Why getting a dashboard is so slow today · 0:35 What Anthropic released on October 8 · 1:08 Who I am (data & AI for banks) · 1:40 Is Claude Dashboards free? Plans and Enterprise setup · 2:00 Step 1: Understand the Excel data · 3:32 Budget and revenue-by-region tabs · 4:55 The old way: waiting weeks for the BI team · 5:29 Claude Dashboards documentation explained · 6:27 Step 2: Create a project in Claude · 7:37 Step 3: The Claude dashboard prompt · 9:14 Step 4: Your live dashboard + share link · 10:31 Step 5: Where do the numbers come from? · 11:14 Step 6: Change charts in plain English · 11:52 Is Power BI dead? · 12:32 Claude + Snowflake, BigQuery, Databricks · 13:01 When you still need Power BI · 13:31 My verdict: small vs big companies · 14:03 Before you use real company data [0:00] Claude just released a new feature called dashboards. And I think it changes who can make business reports. Let me show you what I mean. A dashboard is one page with charts. It shows how your business is doing. Sales going up or down? Costs getting too big? Which country brings the money? One page, you see everything. Today, in most companies, getting a dashboard is slow. You send your data to the data team or the BI team. BI means business intelligence. You wait days, sometimes weeks. A week ago, on October 8th, Anthropic, the company behind Claude, released Claude dashboards. Now you can give Claude data, describe the dashboard you want in normal words, and Claude builds it for you. [0:46] The charts, the numbers, the filters, everything. No Power BI, no waiting for the data team, no code writing, and it is not a picture. The dashboard is alive. When your numbers change next month, you ask Claude to update it, and the same page, the same link, shows the new numbers. I'm Ani. I build data and AI systems for banks and investment companies in Stockholm. So I will not show you a toy. I will take a monthly report, the kind of Excel file every finance team sends around, and turn it into a live dashboard, step-by-step together with you. You can download my exact Excel file in my free community, for free, and do every step with me. And at the end, I will answer the big question, if this works, do we still need Power BI? [1:35] My honest answer may surprise you. One detail, Claude dashboards is in beta right now. Beta means it is new and still being improved. It works on every paid Claude plan, including the normal pro plan. If your company uses the enterprise version, your admin has to switch it on first. Okay. Let's open the Excel file and build your first dashboard. Before we send this data into cloud, I want to make sure that we understand the data. We have the first tab that is called P&L actuals. Here we have three revenue centers. And by revenue center, I mean the areas that are creating revenue for the company. Company is a fictitious company that I created and all the numbers are also fictitious. [2:22] It is selling software to its clients and there are three revenue centers. The first one is advisory and it includes consultancy services. Next is software, which is the software that company is selling to its clients. And then we have managed services and you can see that we have data for January, February and the whole way until September. And for all of those, we have revenue, which is the money that we get paid from our clients for doing advisory services or for providing softwares or for running softwares. And after that, we have COGS, which stands for cost of goods sold. So, those are the costs that are associated with selling. [3:11] Next, we have personnel costs and it can involve, for example, salaries. Then we have marketing. Those are marketing costs that we do for getting more clients. And then after that, we have IT costs, which are connected to different type of softwares that we use and other operational costs. When we go to the budget tab, here you can see that we have the exact same information, but those are between January and December. And that is because this is an estimate. We estimated how much revenue, COGS, personnel, marketing, IT and other operation expenses will be coming from all of those three revenue centers during 2026. We did this estimate last year and this is something that we want to compare our actual numbers. [4:01] And our actual numbers are in the first tab that is called P&L actuals. Then last but not least, we have revenue by region. And here we have the same information that we had on the first tab. However, here we separated the revenue by region. So you can see that we have companies in Sweden, Norway, Denmark, and Finland. And the reason that we have those [clears throat] is because we want to see from which countries we get most revenue. And one thing that you can notice with this Excel sheet is that we just have raw numbers. We have no metrics and no calculations. [4:47] The reason for that is that we are going to use cloud for all the metrics and calculations. Now, let's think [laughter] how we will normally do when we have numbers in Excel sheets and we want to create a dashboard. The old way is that I have the data. I'm a business person. I do not create any dashboard, so I will send this to the data team or to Power BI team and I will ask them to create a dashboard based on this Excel sheet. Then this work has to be planned. So it can take just a month or two to plan. And then once the actual work starts, it can take a week or two to create the dashboard. That is the old way. On 8th of October, Antropi shared documentation that was about creating dashboard using cloud. [5:38] So this is the documentation that you can read. It is accessible on all plans and even on the pro plan. However, if you are on enterprise plan, then you need to ask your account owner to activate it. Other than that, the difference between cloud dashboard and artifact is that artifact were frozen. So they were showing frozen data. However, if you connect dashboard to a data warehouse, for example, Snowflake, then the dashboard will be automatically refreshed and you will save a lot of time to create your reports. Now, for this example, I will show how to take an actual Excel sheet and create dashboards under 15 minutes using cloud. [6:27] For this example, I'm using cloud code. However, you can use even cloud on web browser. We will create new project and of course you can create chart. However, project is a good way to organize all of your charts and files. And because this is project that I will come back to next month or next quarter when I have to update the dashboard. So, it is more smart to create project. So, this project will be called monthly report. And then we can click on create button. Once that is done, we can upload the Excel sheet that we're looking into and ask cloud to read information in this Excel sheet and to describe it to me. Reason for this is because I want the AI tool to understand the data before it will create the report. [7:17] And now this can take couple of seconds before it answers. We have an answer. We can see that it understood that we have three different tabs and it is explaining which data is in each tab. Once we see this information, then we are good to go. The next step will be asking to create the dashboard. I have a pre-made prompt for this. It says, "Now build a management dashboard for this data." So, note that the only thing you need to say in order to create dashboard is build a dashboard. After that, I'm saying I want to see revenue against budget per month per each revenue center. Next, I'm saying profit per revenue center, revenue minus all costs month by month. [8:07] Next, which cost lines are higher than budget? Next, revenue by region. And last, make it possible to filter by revenue center and by month. And then we send this prompt and it will take under 15 minutes for Cloud to create this dashboard. And dashboard is going to be very interactive and you can share it with your colleagues. For example, if you want to share it with someone, you can even share it to different software. So, here on the right side you can see a little progress menu. And in there, Cloud already organized all the steps to do in order to build the dashboard. Now, while Cloud is preparing the dashboard, we can see that there is a black button that says share. [8:52] And in here you can see that it's just shared with me. But if I want to share this with my coworkers, then I can just invite people by email. Then, if we click on share, you can see that there is copy private link section where you can just copy the URL for this dashboard and open it in any browser. Now, we have the dashboard created and in order to make it easier for us to go through the numbers, I will click on share button and I will copy private link. Then I will open any browser and in that browser I will just pass this link and the dashboard will be opened in here. And you can see that in the beginning we have some information about the company and underneath that we have all revenue centers. [9:43] We have advisory, software, managed services. If you remember, those were the revenue centers that we discussed. Then we have year-to-date and then we can click on reset filters. And again, we can see in here all the information for all revenue centers. And here we have revenue versus budget. So, what is the actual numbers compared to what was planned. And underneath that we have profit by revenue center those graphs. And then we have even cost lines we see budgets. And underneath that, we have revenue by region with very nice numbers. We can see very easily that the most of the revenue in this particular company is coming from Sweden. Then we have next Norway, next Denmark, and Finland. [10:29] And of course, before presenting those numbers, you might want to understand where our numbers coming to be sure that all is reliable. And in order to do that, you will just click, for example, in the graph or anywhere in the actual dashboard. If you double click on that, you can see ask cloud button and the source button. See where this comes from. And if you click on that button, you can see that this is cost lines we see budget. It's basically information about this chart. And then you can see the formula, how are all of those numbers calculated. And if there is something that you still do not understand, and you want to talk to cloud in order to understand, then you can just click on ask cloud, and cloud will be opened in the browser. [11:17] And you can directly ask cloud about these numbers or formula. And you can even ask to change the visualization. Maybe you don't like bar chart, you want to have pie chart. You can just ask cloud to use your favorite type of visualization. You can even ask to change colors. Everything is changeable, and this is very quick to develop. And most importantly, you are not dependent on technical people. And you can see where data is coming, how is it visualized. And if you have questions, you know that cloud will be there to answer to your questions. Time to answer the question from the start. Do we still need Power BI? My direct answer, for most reports in most companies, no, not anymore. Think about what Power BI actually costs you. [12:05] You need a specialist to build every report. You need training just to use the thing. You need licenses for every person who wants to look at it, and you need time, days or weeks of waiting for something Claude just did in minutes from one sentence. I built these systems inside banks, and I will say it straight. If the goal is to answer a business question, the Power BI way of building reports is now the slow and expensive way. And here is the part that makes it serious. Today, I used Excel, but Claude connects straight to the data warehouse, Snowflake, BigQuery, Redshift, Databricks, the same tables your Power BI reads today. Once that connection is live, the dashboard updates itself when new data arrives. So, the question is very real. [12:51] If the data is the same, the charts are the same, and one of them builds itself, why would you pay for the other one? There is one honest exception, only one, the big regulated company. Official numbers that auditors sign, rules about who can see what, the manager in Sweden cannot see the salaries in Denmark, reports that go automatically to 200 people every Monday. That control layer is what Power BI still sells. Claude Dashboards is 1-week-old and in beta, it does not replace that layer yet. Yet. So, here is how I would say it to a client. Small or mid-size company? I cannot give you one good reason today to start a new Power BI project for normal business reporting. [13:40] Big regulated company? Keep Power BI for the official audited reports and move everything else, all the everyday questions, to this. Because the everyday questions are 80% of the work, and the waiting for them just ended. One warning before you try this at work. My file was made up data. Real company numbers are confidential. Check your company's rules before you upload real data to any AI tool. Now, tell me in the comments, am I wrong? Is there a reason to keep Power BI that I missed, or do you agree its days are counted? And should I make this video again connected live to Snowflake or another data warehouse? Write which one. All the prompts from this video are free in my community. The link is in the description. [14:25] See you in the next one.