DidWork

Verify that an agent's claimed outcome actually happened, using independently gathered evidence

Install

KitScout test notes

Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.

Similar tools

• wait-what
• karpathy-guidelines 232,934 ★
  Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code t
• discernment-nudge 194,218 ★
  After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted art
• timeline-report
• weekly-digests