What problem does it solve? Work declared done without direct verification has unknown correctness. Indirect signals like file timestamps, cached screenshots, build success, or agent self-reports create false confidence, and acting on a wrong inference costs far more than checking the source. ## Core Features & Use Cases - Direct Verification Discipline: After any task, check the real thing—run the feature, read the actual value, inspect the diff—rather than trusting proxies or derived state. - End-to-End Validation: For code and integrations, build it, run the actual feature path, and confirm data flows from input to output across the full communication chain. - Delegation Auditing: When verifying delegated work, inspect the actual output artifact (git diff, file contents, runtime behavior) instead of the delegate's summary. - Scripted Proof: Write a deterministic re-runnable script that performs the comparison, keeping its output as an artifact a reviewer can re-run. - Use Case: After an agent claims a bug fix works, run the feature yourself, inspect the git diff, and execute a comparison script rather than accepting the agent's report. ## Quick Start After finishing your next coding task, ask the AI to apply the prove-it-works principle to verify the result against the real artifact before declaring it done.
