Define the research-critique coordinator input contract

The accepted input remains: user brief, research worker, critique worker, merge policy. Keep parsing and normalization in functions that do not score, train, or call a model. That split lets a test fail the boundary without blaming the core logic. The user-facing decision stays: delegate research and critique to two bounded workers, then merge under a coordinator policy.

const workers={research:{maxSteps:2}, critique:{maxSteps:1}};
console.log({workers, sharedMutableState:false});

Expected evidence: worker budgets. If the contract is silent on a bad value, later debugging will look like an algorithm bug when it is really a data bug.

Write one assertion for a neighboring valid input to the research-critique coordinator so tightening the boundary does not over-reject. Document field names and types the way a teammate would need them on day two of multi-agent-in-code—not as comments you plan to delete.

List every field in two workers with separate step budgets and mark each as required, optional, or forbidden. Required fields must fail loudly when missing; optional fields need defaults you can quote in a test; forbidden fields (secrets, raw PII, path escapes) must never be accepted silently. This list is the contract for the research-critique coordinator.

Add one sentence about encoding, units, or timezones if relevant to user brief, research worker, critique worker, merge policy. Contracts that ignore units create “correct” programs that still ship wrong decisions when someone tries to delegate research and critique to two bounded workers, then merge under a coordinator policy.

Write the error string you want for the most likely bad input. Prefer ValueError('threshold out of range')-style messages over generic invalid input. The contract’s job is to make workers sharing mutable state, or coordinator ignoring critique veto harder to confuse with a model or algorithm bug later.

At the data contract stage for multi-agent-in-code, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about two workers with separate step budgets that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: single agent without critique pass.

For this page specifically, success looks like malformed inputs rejected with field-named errors while still centering the user decision to delegate research and critique to two bounded workers, then merge under a coordinator policy. If you cannot point to a file, command, or assertion that proves that for the research-critique coordinator, stay on this page instead of advancing.

Glossary: tool · Glossary: structured output · Cheatsheet: production ops signals

Previous · Next