# Review what your AI agent did each week

> Researched. Small business · Intermediate · Operations. Updated 2026-11-02.

Canonical page: https://www.aisetupsthatwork.com/setups/review-what-your-ai-agent-did-each-week/

## What it does
Spend 15 minutes a week reviewing what your AI agent did: sort its actions into fine, fixed and should-not-have-happened, then tighten one rule for each problem.

## Who it's for
Anyone running an AI agent on email, calendar or a store who wants to stop babysitting it daily without losing control.

## Tools
- ChatGPT or Claude
- The agent's activity: sent folder, drafts, calendar changes or its own log

## Steps
1. Pick a fixed 15 minutes each week.
2. Gather what the agent touched: sent folder, drafts, calendar changes, order notes or the agent's activity history.
3. Remove personal details you do not need, then paste it into the prompt below with your rulebook.
4. Read the should-not-have-happened list first. OpenAI says a signed-in agent can access sensitive data and perform actions, so treat these seriously.
5. For each problem, change one thing: tighten a rule, remove an app connection, or move the action behind approval.
6. Keep the weekly reports. Fewer problems over time is how you know you can trust it with more.

## Copy-paste prompt
Adapt bracketed fields to your situation.
```text
Review what my AI agent did this week. Use only what I paste.

My rulebook: [PASTE RULES]
Agent activity this week: [PASTE ACTIONS, DRAFTS, SENT ITEMS, CHANGES]

Sort every action into:
1. Fine
2. Needed fixing (what was wrong)
3. Should not have happened (which rule it broke)

Then give me:
- The one rule change that would have prevented the most problems
- Anything that looks like it acted outside its permissions

Keep it under 300 words.
```

## Guardrails
- What it touches: Chat input you provide (ChatGPT or Claude; The agent's activity: sent folder, drafts, calendar changes or its own log).
- Needs your OK: Send, pay, publish, and account changes stay with you. Treat agent output as drafts first.
- Safety level: Read-only
- Reviewing only what the agent reports about itself; check the real sent folder too.
- Fixing problems in a chat instead of in the agent's standing rules.
- Skipping weeks once things look fine.

## Tips
- Same day, same time each week makes it stick.
- Read problems first, wins second.
- If the same problem shows up two weeks running, move that action behind approval.

## Estimates (labeled, not measured)
- Time saved: About 15 minutes a week.
- Money saved: Not stated in sources.
- Tool cost: Free tiers can run the review. Prices: Not stated in sources.

## Sources
Summaries use the public sources below, not independent verification.
- OpenAI: https://help.openai.com/en/articles/11752874-chatgpt-agent (ChatGPT agent: when signed into sites or apps it can access sensitive data like emails, files or account settings and perform actions (read 2026-11-02 from a search result excerpt of the page))
- Anthropic: https://support.claude.com/en/articles/10166901-use-google-workspace-connectors (Use Google Workspace connectors: Gmail drafting, approval before send, reply or forward by default (read 2026-10-31 through a page fetch tool, not a direct browser open))

## Get the free starter pack
Five beginner copy-paste AI setups, free by email: https://www.aisetupsthatwork.com/starter-pack/?utm_source=ai-agent&utm_medium=markdown&utm_campaign=setup-review-what-your-ai-agent-did-each-week

Related:
- [Set guardrails before an AI agent gets access](https://www.aisetupsthatwork.com/setups/set-guardrails-before-giving-an-ai-agent-access/index.md)
- [Make your AI agent stop for approval](https://www.aisetupsthatwork.com/setups/make-your-ai-agent-stop-for-approval-before-it-sends/index.md)
- [Pick your first AI agent job](https://www.aisetupsthatwork.com/setups/pick-your-first-ai-agent-job/index.md)