# Evidence checklist prompt for AI agents

Paste this into Claude, ChatGPT, Copilot, Cursor or any agent that can save files.
Replace the two lines in brackets with your job and a file name.
Then open the file in LeanMD, turn on Watch (Ctrl+Shift+W) and switch the Outline to Tasks.

Guide: https://leanmd.io/evidence-checklist.php

## The prompt

```text
Task: [describe the job in one or two sentences]

Create and maintain a single file: [checklist.md]

Rules:
- Use Markdown headings for the phases or areas of the work.
- Under each heading, use task checkboxes: - [ ] or - [x]
- Under every task, include:
  - Done: what was done
  - Issues: problems found
  - Evidence: command output, file counts, test results, links or timestamps
- Only mark a task [x] when you have recorded evidence that it succeeded.
- If you discover a problem, add a new task or note under the relevant heading instead of silently fixing it.
- On every update, overwrite the same file with a clean, complete version. Do not create new files or append duplicate sections.
- Keep the headings and task order stable between updates.
- Keep a short "Current status" line at the top.

Start by writing the full checklist with every task unchecked, then begin the work and update the file as you go.
```

## Example task lines

- Server migration: `Task: Migrate the shares on old-fileserver to new-nas, keeping permissions and a 30-day backup retention.`  
  Evidence: share sizes, robocopy logs, file counts on both sides
- Code refactor: `Task: Remove the deprecated payment API from the billing module, keeping every test passing after each step.`  
  Evidence: test run output, the commit or diff for each step
- Website launch: `Task: Prepare the website launch: final content, redirects, sitemap, and a confirmed download checksum.`  
  Evidence: URLs checked, redirect responses, the SHA-256 value
- Research summary: `Task: Compare three backup tools for a 20-person office and recommend one.`  
  Evidence: links to sources, prices with the date they were checked

## Optional rules

Force evidence before a box is ticked:

```text
Never mark a task [x] unless its Evidence line contains a concrete artifact (command output, checksum, log line, test result, file count or source link). If evidence is missing, leave it [ ] and explain what is still needed.
```

Make problems visible instead of quietly fixed:

```text
If you find a problem, do not just fix it. Add a new unchecked task describing the problem, then a follow-up task for the fix. Only check the fix task after you record evidence.
```

Keep a short update log:

```text
At the bottom, maintain a "## Update log" section with one line per save, for example:
- 2026-11-12 09:15: Corrected retention from 14 to 30 days (evidence: line 13)
```