An accounting firm uses Gemini agents for onboarding, invoices and statements
In plain words
Working with Seisma, accounting firm P&C set up Gemini Enterprise agents for client onboarding, invoice and expense checks, and financial-statement analysis.
What happened: Practice work scaled up with AI handling the grunt work.
Source: seismagroup.com ↗
How to do it yourself
Our suggested steps. The company didn't publish theirs.
- 1
Pick one job: new-client onboarding checklist, expense coding or statement review.
- 2
Write the steps and the output you want.
- 3
Build a Gem with the prompt below.
- 4
Have a senior check the first 20 outputs.
- 5
Roll out to the team once it's reliable.
The instructions to give the AI
Paste this into ChatGPT (the free plan is fine), swap the [brackets] for your details, and test it on a few real examples.
Agent instructions (prompt)
Review these financial statements for [client]. List: big movements vs last year (with %), anything unusual, missing notes, and 5 questions to ask the client. Plain English, no jargon. [paste]
[Highlighted] = replace with your own details before you run it.
What you should get back: "Revenue up 22% (new contract). Wages up 35% — check. Missing: depreciation schedule."
Written by Quickly and Good, inspired by this case.
More detail: tools, prices and what you'll need
The company used: Google Gemini Enterprise
You could use: Google Gemini (Gems) in Workspace or ChatGPT
- Google Gemini
Google's AI assistant, built into Workspace (Gmail, Docs, Sheets).
See pricing · Official site ↗
- ChatGPT
General AI assistant: writes, summarises and answers from files you give it.
Free plan; paid plans available · Official site ↗
Prices from each tool's own pricing page, checked Oct 2026.
What you'll need
- ☐A ChatGPT or Claude account
- ☐Your own documents, templates or examples
- ☐The agent instructions (prompt)
- ☐A habit of checking every output before you use it
Can I do this myself?
Yes. You can try this today with a chat assistant and your own files.
Similar cases
An internal agent at Bunnings saved staff 500,000 hours of admin
500,000 staff hours of admin saved (Google's figure; it didn't say how this was measured).
Asurion's invoice agent lifted hands-free invoice processing from under 20% to 70%
Touchless invoice processing rose from below 20% to more than 55% in the first week, and then to over 70%.
A Melbourne pasta maker's AI agent took over 70% of a retired admin's job
About 70% of a four-day-a-week admin role is now handled by the agent, saving more than 20 hours a week.