CPD · Foundation courses
AI basics for finance: Claude, ChatGPT, Copilot and Gemini
Use a general AI assistant well on finance work, and check what it gives you.
- 4 modules
- 4 marked written tasks of 450 to 800 words
- Pass at 80
- Facts checked 1 November 2026
- Yours to keep, no end date
- Certificate when every module passes
Who it's for
Anyone in finance starting with AI tools.
The modules
Module 1
What a general assistant is good and bad at, and why it makes things up
How a general AI assistant produces its answers, the finance jobs it helps with, the ones it gets wrong, and why it states wrong things with confidence.
- Objective:
- To be able to explain how a general AI assistant produces answers, judge which finance tasks it can safely help with, and spot the typical errors it makes on technical accounting questions.
- Marked task:
- Identify the three errors in the AI answer and explain why each is wrong, referring to the FRS 102 amendments.
- What the marker looks for:
- Finds and explains the three errors (30), Gets the numbers right, with working (25), Explains why the tool made these errors (20), Sets practical rules for next time (25)
Module 2
Prompting for finance work: context, role, format and checks
Write prompts that give an assistant the facts, the audience, the format and the checks it needs, so the first draft is closer to usable and easier to verify.
- Objective:
- To be able to write clear prompts for finance tasks that set context, role, format and checks, and to explain how each part reduces the risk of a wrong or misleading draft.
- Marked task:
- List the weaknesses in Luke's prompt and the risk each one creates.
- What the marker looks for:
- Diagnoses the weak prompt (20), Writes a strong replacement prompt (35), Justifies each change (25), Sets the checks before the pack goes out (20)
Module 3
Checking output: figures, sources, standards and tone
A practical routine for checking AI drafts before they leave your hands: every figure, every source, every rule and the tone for the reader.
- Objective:
- To be able to check AI-drafted finance documents for errors in figures, sources, standards and tone, correct them, and record what was changed and why.
- Marked task:
- Check the supplier email. List each error or risk and give your corrected email.
- What the marker looks for:
- Corrects the figures (30), Deals with claims, commitments and tone (25), Produces usable corrected versions (20), Keeps a change log and improves the prompt (25)
Module 4
Choosing the tool: chat, built into Office, built into the ERP
Where general assistants sit (a chat app, inside Office or Google Workspace, inside the finance system), what each can see, and the controls each one needs.
- Objective:
- To be able to compare chat assistants, office-suite assistants and ERP-embedded AI for finance work, recommend a suitable tool set for a team, and set the controls each tool needs.
- Marked task:
- Recommend a tool set for the team: which kind of tool for which jobs, and what should not go into any tool. Give reasons.
- What the marker looks for:
- Recommends a sensible tool set (30), Sets controls for each tool (30), Asks the right questions of providers (20), Plans the review (20)
In every module
- A short written lesson, with its sources
- A quiz to check the ideas
- A written task, marked against a grid, with feedback. Pass at 80
- A reflection, and Copy for CPD record
A certificate for the course once every module is at 80 or more. Built for your CPD record.
Labs with this course
No lab comes with this course yet: labs are added as they open.
How it's marked
Your answer is marked by an AI model against the grid for the task, whose parts and marks are listed above for each module. Each part is judged Not shown, Partly, Mostly or Fully, and the mark is worked out from the grid's weights. A CIMA-qualified (CGMA) moderator checks a sample of marks and can add a note. Under 80, read the feedback and try again; your best mark counts.
See a marked task in full: the grid, an answer and its feedback
Price
£39
Or every course, track and lab for 365 days with the CPD year, £199. Or CPD monthly, £19.99 a month, cancel any time. Every lesson, plus 8 marked tasks a month, across every course, role track and lab.
More in AI, data and Excel foundations
On the path for using ai in finance.
Buying for a team
Seats by invoice or purchase order, with a manager report. See CPD for employers.