CCA-F start here · Trap gym · The coordinator's split

The coordinator's split

A multi-agent report comes back incomplete, wrong or slow, and the options offer to fix the subagents. Often the subagents did exactly what they were told. The trap is treating the symptom: blaming the subagent for a fault the coordinator made when it split and briefed the work.

D1 Agentic ArchitectureExam guide 1.2, 1.3 and 1.6About 15 minutes

At a glance: If whole topics are missing from the result and every subagent did its job, the coordinator split the task too narrowly, so fix the coordinator, not the subagents.

Start here: the head chef and the order tickets

A head chef is catering a dinner. She talks to the client, then writes a ticket for each cook.

The chef decides. Which dishes to make, what goes on each ticket, and whether the cooks start together or one after another. Only she heard the client say “one guest is vegetarian, and dinner is at seven”.
The cooks deliver. Each cook reads only their own ticket. They never heard the client. A great cook given the ticket “soup” makes great soup, and nothing else.

If the dinner has no main course, every cook still did their job: the chef never wrote a ticket for it. If the soup has bacon in it, the cook didn't know about the vegetarian; it wasn't on the ticket. Retraining the cooks fixes neither. In Claude's multi-agent systems the chef is the coordinator, the cooks are subagents, and the ticket is the Task prompt. A subagent starts with an empty context and knows only what that prompt says.

The request topic, audience, rules Coordinator 1. The split which topics 2. The brief what each knows 3. The timing together or in turn Gap check (optional): anything missing? send it out again Task prompts results Subagents: each starts empty and knows only its prompt Visual arts Music Writing Film The report written by the coordinator
The one question to ask: did each subagent do what it was asked? If yes, the fault is upstream, in what the coordinator asked.

Words in the question that tell you which side you're on

The coordinator's fault

  • “all subagents complete successfully”, “within its topic”
  • “the coordinator split the work into…”
  • “the user told the coordinator…”, “agreed earlier”
  • “no search needs another's results”
  • “follow the steps exactly”

The subagent's own fault

  • the subagent had the facts in its prompt and still got it wrong
  • its results are poor for the topic it was given
  • it uses tools outside its role
  • only then: improve its prompt, examples or tools

Try it: replay the run

A coordinator researches “How is AI changing the creative industries?” for a museum board. Pick what went wrong, then pick a fix. The simulator replays the run: who works when, what each subagent was told, and what the report covers. The diagram above shows where your fix acts.

1. What went wrong

2. Your fix
coordinatorsubagent, good resultsubagent, weak result


    

Times and counts are illustrative, chosen to show the shape. They are not measurements. The exam guide's points are that narrow decomposition leaves topics uncovered, subagents get context only through their prompt, parallel work goes out as several Task calls in one response, and briefs should be goals plus quality criteria.

Things to try: Whole topics missing + Improve the subagents, then + Widen the split. Then + Add a gap check: it works, but look at the clock. Last, The user's rules ignored + Improve the subagents: fewer old sources, never zero.

The three traps

TrapWhat the wrong option looks likeWhy it's wrong
Blaming the subagentBetter search terms, more sources per subagent, a stricter subagent system prompt, a new toolThe subagents did what they were asked. The missing topic or fact was never in their Task prompt.
Catching it lateA gap check after synthesis, a reviewer, a filter that drops bad resultsA good safety net, but it pays for a wasted round and leaves the cause in place for the next run.
Right layer, wrong leverParallel calls for a coverage gap; a wider split for missing context; more steps for a recipe that is too rigidSplit, brief and timing fix different symptoms. Match the lever to what went wrong.

Practice: three exam-style questions

Answer first, then open “Think it through”.

Rule to remember

Every subagent did its job and the result is still wrong? Fix the coordinator: the split, the brief or the timing.

Exam guide 1.2: “Risk: overly narrow decomposition → incomplete coverage of broad topics.” Exam guide 1.3: “Subagent context must be provided explicitly in the prompt (no automatic inheritance / shared memory).” and “spawn parallel subagents by emitting multiple Task calls in one response; write coordinator prompts as goals + quality criteria, not step-by-step procedures.”

← All traps