Subagent context
A subagent ignores what the user said, repeats research that was already done, or loses the sources. The options offer shared memory, a stricter system prompt or a shorter summary. The trap is forgetting that a subagent starts with an empty memory: if a fact isn't in its Task prompt, it doesn't know it.
D1 Agentic ArchitectureExam guide 1.3About 12 minutes
Start here: the contractor who missed the meetings
You hire a contractor to finish a room. They were not at last week's meetings, so they don't know the client hates grey. If you don't write it in their brief, they will paint it grey. And if your brief says “use the paint we agreed”, they still don't know which paint.
Claude's multi-agent systems work the same way. The coordinator is the agent that talks to the user and splits the work. It hands a job to a subagent through the Task tool, and the text it writes in that call is the Task prompt. The subagent has isolated context: it does not see the coordinator's conversation, the user's rules or another subagent's results unless the Task prompt spells them out. And the coordinator can only use the Task tool if its allowedTools list (the tools the agent is permitted to call) includes "Task".
- No: write it in. Put the complete earlier findings, the user's rules for this request, and the sources (URLs, document names, page numbers) in a structured format that keeps content apart from metadata.
- The subagents don't depend on each other but run one after another: send several Task calls in one response.
- The coordinator can't spawn subagents at all: check that its
allowedToolsincludes"Task". - Yes, it was in the prompt and still went wrong: now look at the subagent itself.
Words in the question that tell you which side you're on
Write it into the Task prompt
- “ignores what the user said”
- “repeats work already done”
- “loses the sources”, “can't trace a figure”
- “doesn't know the earlier findings”
- “the issue we've been discussing”
Send parallel Task calls
- “subagents run one after another”
- “independent searches”
- “takes too long”, “most of the time goes on waiting”
- “no search needs another's results”
Try it: brief the writers
A drug-review committee asks for a summary of Dravelin, a made-up migraine drug. In earlier turns the chair told the coordinator to leave out trials under 200 patients, and a research subagent found three trials, each with its source. Now the coordinator hands the writing to three subagents: efficacy, safety and cost. Choose what goes in each Task prompt, how they are spawned, and whether the coordinator may use the Task tool at all.
The drug, trials, sources and times are made up and illustrative, chosen to show the shape. They are not measurements. The exam guide's points are that subagent context must be passed explicitly in the prompt, that complete findings go in a structured format separating content from metadata, and that parallel subagents are spawned as several Task calls in one response.
Things to try: Nothing: “use what we found above”, to see that a subagent has no “above”. Then Just the task: it searches again and brings back the excluded trial. Then findings as prose: the facts survive but the sources don't. Last, structured findings + one Task call per turn, then switch to parallel and watch the clock.
The traps
| Trap | What the wrong option looks like | Why it loses |
|---|---|---|
| Doesn't exist | Give the subagents shared memory, or let them read the coordinator's history | Works in some other frameworks, but here subagents inherit nothing automatically. The prompt is the only channel. |
| Wrong home | Put this user's rules in the subagent's system prompt | Fine for rules that never change. Facts that belong to one request, like this chair's size rule, go in that request's Task prompt. |
| Loses information | Summarise the earlier findings in one short sentence to save tokens | The guide asks for complete prior findings. A one-line summary drops the numbers and the sources. |
| Wrong shape | Let the subagents talk to each other directly | Works in a mesh design, but the hub-and-spoke pattern keeps all communication going through the coordinator. |
| Waiting in a queue | One Task call per turn for jobs that don't depend on each other | Same results, several times the wait. Several Task calls in one response run them in parallel. |
Practice: three exam-style questions
Answer first, then open “Think it through”.
Rule to remember
Exam guide 1.3: “Subagent context must be provided explicitly in the prompt (no automatic inheritance / shared memory).” and “Include complete prior-agent findings in the subagent prompt; use structured formats to separate content from metadata (URLs, doc names, page numbers) for attribution; spawn parallel subagents by emitting multiple Task calls in one response”. Also 1.3: “Task tool spawns subagents; allowedTools must include "Task".”