AI for Finance
FP&A, controllers, finance business partners and anyone who builds models, writes variance commentary or assembles a board pack
Prerequisites: Module 101 (AI at Work 101) or your platform's 101 module (01 Claude 101, 201 Gemini 101, 301 ChatGPT 101, 401 Copilot 101), and Module 02 (How to Prompt)
Last verified 2026-09-17
Learning objectives
- Run the assumptions gate before any model is built
- Inspect formulas rather than outputs, and find hard-coded values
- Write variance commentary where every sentence traces to a figure
- Draft board-pack sections from the numbers and a structure, not from a blank page
- Run reconciliation checks on assistant output as a habit, not an exception
- Name the spreadsheet assistant on each platform and the split between building and editing
What's in this module
7 lessons · 5 exercises · ~8 min reading
Starts withWhy finance needs a different discipline~1 minExecutive summary
You will learn a verification discipline for finance work with an assistant: assumptions before formulas, formulas before numbers, a reconciliation check before anything leaves your desk, and commentary that points at the cells it came from. End state is one model built assumptions-first, one variance commentary with an audit trail, one board-pack section drafted from your own numbers, and one reconciliation you ran on the assistant's output and found something. After this module you can do this on Claude, Gemini, ChatGPT or Copilot, and say which spreadsheet assistant your platform gives you and what it is for.
Sources
- Anthropic, "Use Claude for Excel", plan availability, cell-level citations, supported Excel builds and the caution about audit-critical work: https://claude.com/docs/office-agents/excel
- Google Docs Editors Help, "Collaborate with Gemini in Google Sheets", what the in-sheet assistant does and what it needs: https://support.google.com/docs/answer/14356410
- OpenAI Help Center, "Data analysis with ChatGPT", accepted files, the Python environment and the advice to review generated code: https://help.openai.com/en/articles/8437071-data-analysis-with-chatgpt
- Microsoft Support, "Copilot in Excel", what Copilot does inside a workbook and the file-location requirement: https://support.microsoft.com/en-us/copilot-excel
Prefer the live room?
This module also runs inside our in-person bootcamps and workshops in Copenhagen.
More in Track H
AI for Sales and Revenue Teams
The five sales workflows where an assistant pays for itself: pipeline triage, account and meeting prep, proposal and follow-up drafting from a brief, objection practice, and forecast commentary.
AI for HR and People
How to turn a role brief into a job ad and an interview kit, draft and plain-language a policy, build onboarding material, and run a bias check on all of it, without ever pasting a candidate or employee record into the wrong place.
AI for Project Managers
To turn raw updates into a status report people read, keep a decision log that survives staff turnover, write stakeholder communications for the audience rather than the project, maintain a risk register that changes, and schedule the recurring briefings where your platform supports them.