← All IntelClip / AI AgentsThe production contract: model proposes, harness commits, receipt proves
From The Run Receipt Audit: Diagnosing Harness Failures in AI Agents · ≈2:39
Gives a crisp architectural contract for agent reliability — the model is not the production boundary, and transcripts are not evidence — plus the three rules: own the state, order the mutation, prove the action.
What’s in it
- Gives a crisp architectural contract for agent reliability — the model is not the production boundary, and transcripts are not evidence — plus the three rules: own the state, order the mutation, prove the action.
Clip transcript
around the agent unusually visible. Here's a production contract for the talk. A model proposes the harness commits and the receipts proves it. The model can may suggest a message, a tool, a edit or an command. But model is not the production boundary. The harness owns the state transition, the authority check, the ordered commit and the receipt is the evidence that survives the term. Open clause is the case study and the contract is the takeaway. If you remember only three things from this talk, make it these. Own the state, order the mutation and prove the action. A fact needs only one owner and one replay path. Shared mutable state needs one ordered commit path and transcript is not the proof. A transcript tells you what the agent said. A receipt tells you what the system allowed, attempted, executed and what the user visible edge confirmed.
Comments
Sign in to comment.
Loading comments…