# 5. No Fake Progress Reports

On long runs, any AI can drift into reporting what it intended to do rather than what it did.

**When to use:** Add to every long or unattended run. Pairs perfectly with The Overnight Run below.

## The prompt

```
Before reporting progress, audit each claim against a real result from this session. Only report work you can point to evidence for; if something is not yet verified, say so explicitly. Report outcomes faithfully: if something failed, say so with the output; if a step was skipped, say that; when something is done and verified, state it plainly without hedging.
```

**Why it works:** In Anthropic's testing this instruction nearly eliminated fabricated status reports, even on tasks designed to provoke them.

---

Adapted from Anthropic's official Claude Fable 5 prompting guide.
Full guide with all 12 prompts: https://www.waboom.ai/resources/claude-fable-5