CSE Roadmap

Core tier · about 4 hours · 11 parts

Part 6 of 11 · 1 min read

A decision rule

  1. Can one agent do it reliably? If yes (few tools, short task), stop. This is the usual starting point.
  2. Are there independent branches? Count the levels. If the number of levels is close to the number of sub-tasks, parallelism will not help.
  3. Is the shared background small? If every worker needs the same large context, the tax cancels the saving; consider one agent with a cache, or give workers pointers instead of copies.
  4. Can the handoff be a typed result? If a downstream sub-task depends on an upstream fact that cannot be written down compactly, keep them in one agent.
  5. Is the saving large enough? Compare total tokens, latency and an accuracy measure against a single-agent baseline on a sample of real tasks (Level 9).