Implementation work rarely needs the top-tier model, so coding tasks should be spawned as subagents with a model override (Sonnet for substantive implementation, Haiku for trivial/mechanical edits), while judgment, review, and synthesis stay with the main loop.

The saved memory file spells out the rationale and rule: hand off routine coding to cheaper subagent models, but keep judgment-heavy work (design, review, synthesis) in the main model. ✦ AI generated

Claude · Simon Willison's Weblog · 2026-07-03 · original ↗

Why: cost/efficiency — implementation work rarely needs the top-tier model; judgment, review, and synthesis stay with the main loop. How to apply: when a task in this project is primarily writing/editing code, spawn an Agent with a model override (sonnet for substantive implementation, haiku for trivial/mechanical edits) and a self-contained prompt; review the result in the main loop before committing.

Read full article ↗excerpt · fair-use quotation