---
name: prove-it
description: Checks an AI result against something real before you trust it or pass it on, using the source, the actual number, or a rerun with one thing changed, and says what evidence would change the answer. Use when someone is about to send, publish, decide on or reuse an AI output, asks "is this right?", "can I trust this?", "check this", "verify", or when an output looks polished and contains numbers, names, quotes or claims that matter.
license: Apache-2.0 (instructions) and CC BY 4.0 (teaching text). From AI Practice Commons by Women Defining AI; method from the WDAI Build Cycle (beta).
---

# Prove it

The more finished something looks, the less people check it. Help the person run a quick check against something real.

## How this skill behaves

They predict or point first; the check uses something outside the AI, never the AI grading itself. "Just do it" runs the checks and reports.

## Steps

1. **Point to the risk.** Ask which claim, number or step would hurt most if it were wrong. If they're not sure, ask them to predict what a correct version should say before looking closely.
2. **Pick an outside check.** For each risky claim, choose the cheapest real check:
   - **the source:** open the document, page or notes it came from and find the line;
   - **the real thing:** open the file, read the actual number, click the link, run the formula;
   - **a rerun:** change exactly one thing, run the same input again, and compare;
   - **a person:** someone who would know.
3. **Run it and show the evidence.** Report what was checked, what matched, and what didn't. Label anything you couldn't verify as unverified rather than smoothing it over.
4. **What would change the answer?** Name the evidence that would overturn the result, so they know what to watch for.
5. **Decide what still needs a person.** Ask what they'll check themselves or hand to someone before it goes out.

## Output

A short check table (claim → how it was checked → result), anything still unverified, and what needs a human decision.

## Next

For a workflow that will run again and again, point to the field skill `evals-skills` (Hamel Husain) for proper testing. For a light check after any substantive answer, recommend Anthropic's `discernment-nudge`.

<!-- AI Practice Commons metadata (commons.yaml): ids, links and review state -->

```yaml
id: prove-it
schema: skill/1
layer: garden
version: 0.1.0
status: beta
kind: build-cycle
practises: [cmp-check-the-result]
concepts: [con-verification, con-hallucination, con-evals]
builds_on: [build-brief]
next: [make-it-repeatable]
field_next: [fld-anthropic-discernment-nudge, fld-evals-skills]
attribution: "'Change one thing, rerun, compare' from WDAI's Build Cycle; informed by Anthropic's AI Fluency Index and pstack principle-prove-it-works (MIT, Lauren Tan)."
origin: { kind: agent-assisted, by: "Claude for Helen, 2026-10-16" }
```