Home/Insights/AI in Finance

3 Claude Agents Every Finance Analyst Should Steal (Full Prompts Included)

By Ani BjörkströmPublished 13 August 2026Reviewed 17 November 202617 min video + articleAI in Finance

3 Claude Agents Every Finance Analyst Should Steal (Full Prompts Included)
▶ Watch the full 17-minute video · with chapters & transcript

AI IN FINANCE

How can AI agents automate real finance workflows in an enterprise setting?

In short: Three AI agents built for actual finance clients — a due diligence analyst, a scheduled news brief, and an Excel bug-finder — run in real enterprise environments.

Key takeaways

  • Three AI agents built for actual finance clients — a due diligence analyst, a scheduled news brief, and an Excel bug-finder — run in real enterprise environments.
  • A scheduled agent compiles the top five sustainability news items every weekday at 7:00 as a Gmail draft, replacing a client's 5 a.m. office routine before her 9:00 briefing.
  • Claude inside Excel traced a NAV discrepancy to a formula summing B11:B13 instead of B11:B15, fixed it on approval, and cut the difference to 0.00001 — within the 0.01 tolerance.

Most AI-agent tutorials on YouTube are built on private computers and would never survive a real enterprise environment. Here, Ani Björkström, a tech consultant based in Stockholm, shares three finance agents actually delivered to clients, including the prompts behind them.

What does an AI due diligence agent actually do?

A due diligence agent reads fund documents the way a senior analyst would and answers investor questions using only those documents. The first demo builds one for a Sweden-registered equity fund classified as Article 9 under SFDR, with a prompt structured in four parts: who you are, what I need, how to do it, and rules and constraints.

The agent lives in a Claude project rather than a chat. A project has a larger context window and persists, so users can return the next day without losing anything; once the answers satisfy the team, the knowledge is saved as a skill and reused on other funds.

How do you put a morning market brief on autopilot?

Create a project with a four-part prompt, connect the Gmail connector, and schedule the run for every weekday at 7:00. The client had to present 24 hours of sustainability news at a 9:00 daily brief, which forced her into the office at 5 or 6 in the morning; the agent now finds, summarizes, and drafts the news for her commute.

Precision comes from iteration with the actual user, not from the first prompt. The brief was scoped to the Nordic market at the client's request, and instructions were updated after each review round until the agent answered exactly the way she wanted.

Can AI find a real bug in an Excel model?

Yes — Claude in Excel located the source of a NAV discrepancy between the front-office model and the fund administrator's figure. NAV is calculated daily by both front office and back office, and because it is published to investors, any per-share discrepancy must be resolved fast.

Claude reads every formula in every tab, so one prompt asking it to trace the model found that total liabilities summed only rows B11 to B13 while rows 14 and 15 had been added without updating the formula. After a manual approval, it corrected the sum to B11:B15, leaving a difference of 0.00001 against a tolerance of 0.01.

AgentSetupOutput
Due diligence analystClaude project referencing a local folder of fund documentsAnswers on objectives, risk category, and annual costs from the documents only
Morning briefProject with web search, Gmail connector, weekday 7:00 scheduleTop five Nordic sustainability news items as a Gmail draft with sources
Excel bug-finderClaude opened inside the Excel workbookRoot cause of a NAV discrepancy plus the corrected formula

FAQ

Which model should a document-extraction agent use?

A cheaper model is often enough — extracting data from given documents is not the most advanced thinking task, so a lower-tier model performs well at lower cost.

Should agents approve their own actions?

Start with manual approval, where Claude pauses before each action, and shift to automatic approval once you are comfortable with how the agent behaves.

Does Claude in Excel require the desktop app?

No. The demo runs on Microsoft 365 in the browser, and the same setup works on Excel running locally on your computer.

Want this working inside your finance team?

Ani Björkström

Ani Björkström — founder of QvantX Sweden AB, a Stockholm consultancy building AI solutions for banks, asset managers and finance teams. Anthropic partner. Every article starts from a real client build, minus the confidential parts. LinkedIn →