Sign in
Skip to solution
hardAI Engineering

When should you split work across multiple agents instead of one?

947 views
01

Understand the problem

Subagents, orchestrators and the honest trade-offs vs one capable agent with good tools.

multi-agentorchestrationsubagentsarchitecture
02

Attempt it yourself

Sketch your approach before reading the solution — that's what interviews test.

Nudge consolestandby

Stuck? Beam a request up — the console returns a conceptual nudge that guides your logic without spoiling the implementation.

03

Study the solution

Prefer one agent until you hit a real constraint: context isolation (a subagent can burn thousands of tokens exploring and return only a summary), true parallelism (fan out independent subtasks), or genuinely distinct roles/permissions (a reviewer that must not share the writer's context). Multi-agent costs are real —

Solution ready — 2 min read

Classified // press E to declassify

04

Read the code

Subagent as context compression
// orchestrator delegates exploration; only the summary enters its context
const findings = await runSubagent({
  goal: "Locate where invoice totals are computed and list every caller.",
  tools: [grep, readFile],                 // read-only, scoped
  budget: { steps: 30, tokens: 80_000 },
  returns: "a <=500-token structured summary with file:line references",
});

orchestrator.push(user("Exploration result:\n" + findings.summary));
// the subagent's 60k-token transcript is logged for debugging, not carried forward
05

Join the discussion

Discussion (0)

Sign in to join the discussion.

No responses yet. Be the first to share what you think.

Transmission complete // awaiting log

KEEP THE
STREAK ALIVE.

Dossier 64 of 80 decoded in the AI Engineering track. One more won't hurt.

Back to track