Build the first working research-critique coordinator

Build only what the claim requires: critique can veto an unsupported research draft; coordinator never exceeds worker budgets. Prefer boring, deterministic code over frameworks you cannot yet explain. Run the path twice; identical output on this fixture is a feature, not a lack of creativity.

export async function run(input: unknown, deps: Dependencies) {
  const started = performance.now();
  const validated = deps.parseInput(input);
  const raw = await deps.execute(validated); // run independent workers with Promise.allSettled, then synthesize only accepted evidence
  const value = deps.parseOutput(raw);
  return { value, durationMs: Math.round(performance.now() - started) };
}

Expected evidence: Research returns two sourced claims; critique rejects one unsupported claim; synthesis keeps one.. Read each printed intermediate as part of the argument that the path works—not as decoration.

Narrate the journey from raw input to result for a single example from two workers with separate step budgets. If you cannot name an intermediate, the implementation is still too opaque for this lab. Only after this path is solid should you generalize data sources or UI.

While implementing the research-critique coordinator, print or log at least three intermediates that map to the claim (critique can veto an unsupported research draft; coordinator never exceeds worker budgets). Good intermediates are values a teammate could recompute with a calculator or diff. Bad intermediates are framework traces you cannot explain.

Re-run with two workers with separate step budgets twice. If the second run differs, either the path is nondeterministic (document the seed) or you have hidden global state—both are lab bugs until named.

Stop adding features once the path supports delegate research and critique to two bounded workers, then merge under a coordinator policy. Extra UI, extra tools, or extra models belong in later chapters. The mastery bar for this page is simply: a deterministic end-to-end path with intermediates.

At the implementation 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 a deterministic path with printed intermediates 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