# Claude Dashboards + Snowflake: A CFO Dashboard in 1 Prompt, No Power BI, No Code Source: https://qvantx.com/insights/claude-dashboards-snowflake-a-cfo-dashboard-in-1-prompt-no-power-bi-no/ Author: Ani Björkström — QvantX Sweden AB, Stockholm Published: 2026-10-25 Updated: 2026-11-08 Video: https://www.youtube.com/watch?v=nLEd-jyxq4s (7 min) Topic: Data Engineering License: free to quote and cite with attribution to https://qvantx.com --- _DATA ENGINEERING_ ## How do you build a CFO dashboard in Claude without Power BI or code? #### Key takeaways - Claude Dashboards, connected to Snowflake via an OAuth connector and MCP server, turns one plain-English prompt into a finished CFO revenue dashboard in roughly 10 minutes, with no Power BI, no BI ticket and no code. - In the demo data, net revenue in Europe fell 20% between 1996 and 1997, while America was the only region to grow — the kind of regional breakdown Claude generated automatically from a single Snowflake table. - Every KPI on the dashboard is clickable: Claude shows the exact SQL query behind each number, which can be copy-pasted into Snowflake to confirm it returns the same result. Ani Björkström, the Stockholm-based consultant behind the YouTube channel "Ani Björkström | AI for Finance," demonstrates Claude Dashboards — in beta since 8 October 2026 — connected to a live Snowflake data warehouse. Rather than filing a ticket with a BI team and waiting weeks for a Power BI report, a business user types one prompt describing the dashboard they want, and Claude builds it directly against the company's own data. ### What do you need to connect Claude to a Snowflake data warehouse? Connecting Claude to Snowflake requires a Snowflake-managed MCP server and the Claude Snowflake connector, authenticated through OAuth. A technical user sets this up once, and it is not a complicated process. The setup involves creating the MCP server with the queries needed to run it, establishing an OAuth user, then in Claude going to Customize → Connectors → Add connector. Once that connector exists, Claude can read directly from the company's Snowflake tables — in this case a table called "monthly revenue" containing net revenue in USD and order counts broken out by month, region, country, nation and customer segment, spanning January 1992 to July 1998. ### What does the one prompt for a CFO revenue dashboard actually say? The prompt describes the data source and the business requirement in plain language: it names the Snowflake table, explains that it holds net revenue and orders by month, region, country, nation and customer segment, and asks Claude to "build an interactive Claude dashboard for CFO called Snowflake revenue dashboard," specifying exactly which figures should appear. Ani Björkström notes that this is where a business user has an advantage over a technical one: the business user knows the report specification and which figures matter, without needing to translate that into a developer ticket. After hitting enter, the dashboard took about 10 to 11 minutes to generate. ### What did the finished Snowflake revenue dashboard show? The finished dashboard displayed net revenue, orders for the same period, average order value and the last month in the dataset, followed by a chart of net revenue by month showing every dip and peak across the time span. Below that, it broke down year-over-year change by region and by customer segment. Between 1996 and 1997, Europe recorded the steepest decline at minus 20%, with the Middle East, Asia and Africa also down while America was the only region to grow. By customer segment, every category declined except automobile. A final table listed net revenue by country, region and order count, with a search function to filter to a single country. ### Can you trust an AI-built dashboard, and what's the Snowflake trial trap? Every number on the dashboard is clickable, revealing the exact SQL query and result used to calculate it, which can be copied into Snowflake directly to confirm the figure matches. Clicking refresh pulls updated numbers straight from the warehouse, since the dashboard queries live data rather than a static export. One setup detail catches people out: Claude cannot connect to a Snowflake trial account. The connection must be made to a real company Snowflake account, either set up directly or by asking a technical team to configure it once. Finished dashboards can be shared via a private link, opened by inviting colleagues, exported to tools like Hex, or turned into board-ready slides with a follow-up request to Claude. | Step | Tool / action | Result | |---|---|---| | Connect | Snowflake-managed MCP server + Claude Snowflake connector (OAuth) | Claude can query the company's live Snowflake tables | | Prompt | One plain-English prompt naming the table and required KPIs | Dashboard build starts, no code or ticket needed | | Build | Claude Dashboards generates the report | Finished CFO revenue dashboard in about 10-11 minutes | | Verify | Click any KPI to view the underlying SQL | Query can be run in Snowflake to confirm the same number | | Share | Private link, colleague invite, export, or convert to slides | Dashboard ready for a board meeting | #### FAQ **Does Claude Dashboards work with a free Snowflake trial account?** No. The video explicitly warns that Claude cannot connect to a Snowflake trial account — the setup must be done on a company's real Snowflake account, either directly or by asking a technical team to configure it once. **How long does it take Claude to build a CFO revenue dashboard from Snowflake data?** In the demo, the dashboard took about 10 to 11 minutes to generate after the single prompt was submitted, once Claude was already connected to Snowflake via the MCP server and OAuth connector. **How can a CFO check that the numbers on a Claude dashboard are correct?** Every KPI is clickable and shows the exact SQL query and result that produced it. That query can be copied and run directly in Snowflake, which returns the same number, and the dashboard can also be refreshed to pull current data from the warehouse. ## Full video transcript Chapters: 0:00 A finance dashboard without Power BI, a BI team or code · 1:00 The data: a monthly revenue table in Snowflake · 2:11 Connecting Claude to Snowflake (MCP server + OAuth connector) · 2:43 The one prompt a business user writes for Claude Dashboards · 3:51 The CFO revenue dashboard: KPIs and revenue by month · 4:25 Change by region and by customer segment · 5:00 Net revenue by country with search · 5:22 Can you trust it? Click any number and see the SQL · 6:00 Share, export or present from a private link · 6:17 The trap: Claude cannot connect to a Snowflake trial account · 6:45 What should I connect to Claude next? [0:00] What if you could build a finance dashboard like this without Power BI, without a BI team, and without writing a single line of code? In most companies, the real numbers sit in a data warehouse. That is a big, secure database where the company keeps all its data. Snowflake is one of the most popular ones, but turning those numbers into a nice dashboard usually means a ticket, a developer, and weeks of waiting. In this video, I will show you how to connect Cloud to Snowflake and turn your company data into an interactive dashboard. Revenue, orders, regions, and countries ready for your next board meeting. I am Ani. I build data platforms and AI for banks, pension funds, and investment firms in Stockholm. [0:46] So, I will show you how this works in a real setup. And watch the setup part carefully. There is one trap with Snowflake trial accounts that nobody tells you about, and it can cost you hours. Let's get started. Let's start with understanding our data in Snowflake data warehouse. I'm using a table called monthly revenue, and this table shows how much revenue did we get per segment, per country, and we can even see in which region the country belongs to. So, this type of information normally is used by CFOs to create charts and to present in quarterly reports. However, in order to present this data nicely, we need to use some type of tool like Power BI. And that is the old way. [1:32] CFO will ask a technical person to create report. However, after Cloud created Cloud dashboard, we as a business people have a lot of independence, and we can create this report without coding and without any technical help. We can just open Cloud and in natural language ask which type of report to create. And before we do that, it is also important to know that our Snowflake account needs to be connected to cloud. And again, this is something that the technical user will do. It is not very complicated. I can show quickly how I set up. I created the MCP server. Here I have all the queries needed to run the MCP server. Once those parts are done, we have an OAuth user. [2:20] We will log in into cloud. We will go to customize, connectors, and then we will add connector. Right now, I have already created that connector. This is the connector. So, the reason that we need to do this is because you want cloud to access your Snowflake data because you will literally ask cloud to use data in Snowflake to create your dashboard. Now, once this is done, we will create a new project or a new chart. The difference between project and chart is that you can come back to project. Project is like a folder that is keeping your files together. So, here we can just type dashboard and then create project. Once this is done, we will use this prompt that says, "Here is an export from our Snowflake table and this is the name of the table. [3:07] It has net revenue in USD and orders by month, region, country, nation, and customer segment from January 1992 to July 1998. Build an interactive cloud dashboard for CFO called Snowflake revenue dashboard." Then we are specifying how exactly the report should be. And this is the part that you as a business user can do a lot better than the technical user than because it's you who has the business specification and you know better how the report should look like and which figures you want to have in the dashboard. So, here we click on enter button and this normally takes 10-11 minutes until the report is created. I will directly show what the first version of Snowflake revenue dashboard looks like. [3:56] So, this is it. We can see revenue dashboard. Here we have the numbers, net revenue. We have orders, same period, and then average order value and last month, which is the last month in our data sets. Underneath that, we have the graph that we asked for. It's net revenue by month, so we can see during our time span how much revenue changed during each month, and it can clearly show us all the dips and all the tops. If we scroll down, as we asked, we can even see change by a region between 1997 and 1996. Here we can see that we had the strongest cut down in Europe, which was minus 20% in revenue between 1996 and 1997. And we can see that all the other regions, Middle East, Asia, and Africa also went down while America was plus. [4:49] We can see also change by the segments, which segments part of revenue went up or down. Here we can see that everything went down except the automobile. And then underneath that, we have net revenue by country. Here we can even try, for example, to search and see just one country, so we can see name of a country, region that country belongs to, and the net revenue, and the number of orders that made that revenue. And of course, you can go back and change everything that you did not like in this dashboard. And once this is created, the next step is that you want to know if you can trust on this dashboard or not. And in order to do that, we will click on the buttons. You can see from exactly where those numbers come from. You remember that this was the table that we used. [5:36] You can see the query that was used to get this number. And underneath that, you can see the result as well. So, you can of course get the query, go into Snowflake, run it on your own, and see that it will pull exactly the same numbers. And you can even do a refresh, and it will automatically refresh the numbers, because this dashboard is pulling the numbers directly from our data warehouse. Once you are happy with this dashboard, then you can share it. Either you can invite your colleagues, or you can export it. For example, hex, if you use it, there are different options. Or you can do like me, you will copy the private link, and you will present it in your browser. So, that is it. Once Claude is connected to Snowflake, a business person can describe a dashboard in plain words, and get it in minutes. [6:25] You can click any number to see exactly where it comes from. You can share it with your team, or even ask Claude to turn it into slides for your board meeting. Remember the one trap. Claude cannot connect to a Snowflake trial account. So, do the setup in your company's real Snowflake account, or ask your tech team to do it once for you. All the queries from this video are free in my community, Enterprise AI Practitioners. The link is in the description. Tell me in the comments, what should I connect to Claude next? Databricks, Salesforce, or Excel files in SharePoint? And if you want to build a dashboard from a simple Excel file, watch this video next. See you there.