↓Skip to main content

Parallel research with subagents

Playbook
·3 mins
Ask once, let four specialized agents search in parallel, then read the merged brief before diving into sources.

One biomarker question cost an hour in serial chat: search, open PDF, lose the tab, search again, wonder which hit was newer. /research replaced that stack with a parallel wave—literature, preprints, open web, registries—then a synthesizer that merged overlaps and flagged conflicts before I touched raw logs. Same clock time, wider terrain, one artifact to cite.

When I reach for this #

The question spans more than one source type. Or I already know serial “search, read, search again” burns time. Or I want a single artifact with sections I can cite instead of a scroll of chat.

What I need before starting #

  • Claude Code with the /research skill installed (or equivalent workflow you use)
  • A research question stated in one or two sentences — not a whole brief yet
  • Optional: a --type hint if the skill supports skipping clarification (explore, technical, internal, quick, etc.)

What I do #

The /research skill clarifies scope, dispatches parallel researcher subagents, waits for all of them, then runs a synthesizer that merges overlaps and flags conflicts.

1. State the question plainly #

Write what you need decided or summarized. Include constraints: population, timeframe, geography, or “peer-reviewed only” if that matters. Vague questions get vague parallel passes; each subagent will interpret gaps differently.

2. Answer the scope pass honestly #

The skill usually asks what kind of evidence you want. Internal-only work routes differently from open-web exploration. Picking the wrong lane wastes a wave of searches.

3. Let the parallel wave run #

Typically several researchers fire: academic indexes, preprint servers, general web, and sometimes trial or registry search. They work independently. Duplication across agents is fine; synthesis is where duplicates collapse.

4. Read synthesis before diving into raw logs #

The synthesizer’s job is a merged view — claims, disagreements, gaps. Use the per-agent traces when you need a primary source or to verify a bold statement.

5. Drill down in a follow-up session #

Parallel research gives breadth. Depth still comes from a focused second pass on the two papers or datasets that actually matter.

What goes wrong #

  • Over-broad questions — every agent returns a shallow skim. Fix: narrow the question or add must-include terms before re-running.
  • Ignoring conflicts — two sources disagree and the synthesis flags it, but you only read the executive summary. Fix: open the conflicting sources; synthesis is a map, not a verdict.
  • Stale or paywalled gaps — open web agents find abstracts; full text may sit behind access you don’t have. Fix: note “could not verify full methods” in your own notes.
  • Skipping the type hint — you know you want a quick scan but sit through the full interview. Fix: pass --type quick (or your skill’s equivalent) when supported.

Notes #

Parallel research costs more tokens than one lazy search. The trade is coverage and structure. For a yes/no with one authoritative doc, a single targeted query still wins.

If your installation names the skill differently, look for the workflow that says it dispatches multiple researchers and blocks until all return — same pattern, different label.