The bounded agent contract
A coding agent needs an assignment with edges, evidence, and a stopping point.
2 min read · Review draft
Reading path / Task design
Give the agent a bounded job
Turn an intention into an assignment another engineer can inspect. Start with scope; finish with an evidence packet.
A suggested sequence
- 01
The bounded agent contract ↗
A coding agent needs an assignment with edges, evidence, and a stopping point.
- 02
Repository context needs an owner and an expiry path ↗
Agent instructions remain useful when they point to executable truth, fit the directory they govern, and change with the code.
- 03
Budget context as evidence ↗
More repository text is not automatically more understanding; retrieval needs selection, provenance, and tests.
- 04
Multi-agent systems need integration contracts ↗
Role names do not integrate agents; typed artifacts, ownership, versions, and failure semantics do.
On this shelf
Search the full journal ↗Repository context needs an owner and an expiry path
Agent instructions remain useful when they point to executable truth, fit the directory they govern, and change with the code.
3 min read · Review draft
Budget context as evidence
More repository text is not automatically more understanding; retrieval needs selection, provenance, and tests.
3 min read · Review draft
Multi-agent systems need integration contracts
Role names do not integrate agents; typed artifacts, ownership, versions, and failure semantics do.
3 min read · Review draft
Where a vibe prototype stops
A visible demo answers one question; a maintainable service answers many more.
2 min read · Review draft