From Prompts to Contracts: Moving Deterministic Agent Behavior Out of Prompts and Into Code

arXiv·medium signal

This harness-engineering paper (arXiv 2607.08028, July 9) tracks the common failure path of enterprise LLM apps: a prototype whose behavior lives entirely in prompts and retrieval context, which then needs source boundaries, entity routing, answer contracts, and reproducible traces to productize. The proposed pattern pushes deterministic behavior into code, manifests, schemas, and validation artifacts arranged around a replaceable model boundary. Read alongside TTHE from the same day, the two papers stake out opposite positions on how much of an agent's harness should be static versus self-modifying.