Part 7 of 11 · 2 min read
Answering multi-agent questions in an interview
When would you use multiple agents instead of one?
"When the work splits into independent branches that can run in parallel, when one agent's context or tool list is too large to work reliably, or when different parts need different tools or models. I would not use them for tightly coupled work. The latency gain disappears there, and every dependency becomes a handoff that can lose information. In the example's model, independent sub-tasks ran at 0.23 of the single agent's latency, and a dependent chain ran at 1.46." Follow-up: "How do you decide?" I count the levels and edges of the task graph, estimate the shared background, and then measure tokens, latency and accuracy against a single-agent baseline on real tasks.
Why can a multi-agent system cost more tokens?
"Each worker pays for its own system prompt and a copy of the shared background, may repeat work because it does not see the whole picture, and the orchestrator pays for briefs and results. Anthropic reported about 15 times the tokens of chat for its research system. Against a single agent, it depends on caching. Without a cache, short worker contexts are cheaper. With a cache, the single agent's long context is cheap, and the split costs more for small tasks or a large shared background. In the example's model, the ratio crossed 1.0 at about 10,000 tokens of shared background." Follow-up: "What do you do about it?" Pass pointers instead of copies, return typed results, share a cached prefix across workers, and spend the extra tokens only where the task is valuable enough.
Why is coding harder to parallelise than research?
"Research sub-tasks, such as searching a source and summarising it, mostly do not depend on each other. Coding sub-tasks, such as changing an interface, updating its callers, and fixing the tests, share state and depend on each other's output. In graph terms, coding has long dependency chains, so there are few levels to parallelise and many edges to hand over. Anthropic's write-up makes the same point." Follow-up: "What can you still parallelise?" Independent searches, reviews, test runs and exploring alternatives (module 5 of this level).
How would you show that splitting an agent was worth it?
"I would run both designs on the same sample of tasks. I would compare accuracy, total tokens across all agents, and latency, and report the difference with its spread. I would not accept a better demo as evidence. The parametric model in this module shows why the answer can flip: if the model is robust, the reliability benefit of splitting vanishes for dependent tasks." Follow-up: "What would make you go back to one agent?" A measured accuracy gain below the extra cost, or handoff errors showing up in traces.