# Design exercise: Evidence-backed Verification

> Claims, source provenance, executable checks, screenshots, diffs, test outputs, and acceptance criteria. Implement designOutline() returning non-empty values for: acceptanceCriteria, evidence, inferenceBoundary. Each value must name a concrete mechanism or decision.

Canonical: https://learn.significanthobbies.com/curriculum/drills/practice-evidence-backed-verification

Claims, source provenance, executable checks, screenshots, diffs, test outputs, and acceptance criteria. Implement designOutline() returning non-empty values for: acceptanceCriteria, evidence, inferenceBoundary. Each value must name a concrete mechanism or decision.

## The mechanism

Verification turns an agent claim into inspectable evidence. Match each acceptance criterion to a source, command, artifact, or observed state and keep inference separate.

## Expected evidence

A design outline with acceptanceCriteria, evidence, inferenceBoundary plus an explicit failure mode or trade-off.

## Hints

- Name the failure mode before selecting the mechanism.

## Sources and practice

- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://arxiv.org/abs/2210.08726)
- [Enabling Large Language Models to Generate Text with Citations (ALCE)](https://arxiv.org/abs/2305.14627)
- [Google Testing Blog — Just Say No to More End-to-End Tests](https://testing.googleblog.com/2015/04/just-say-no-to-more-end-to-end-tests.html)
- [Study Evidence-backed Verification](https://learn.significanthobbies.com/curriculum/concepts/evidence-backed-verification)
- [Try the interactive drill](https://learn.significanthobbies.com/drills/practice-evidence-backed-verification)
- [All practice briefs](https://learn.significanthobbies.com/curriculum/drills/)