2 min lesson
Plan with a smart model, execute with a fast one
Describe what "Plan with a frontier reasoning model" changes in practice.
Step 1 of 2
Plan with a smart model, execute with a fast one
Plan modeA mode that makes no edits: it researches the codebase and produces an editable plan you review before any code changes. Press Enter for the full definition. harnesses the agent to write a detailed Markdown of exactly what it will do instead of editing files immediately. The pattern worth coaching users toward: plan with a frontier reasoning model - today that's Claude Opus 5, which replaced Opus 4.8 in Cursor's picker, or the GPT-5.x line - where the big context window and processing power craft a plan the agent then adheres to, then switch to a fast in-house model like ComposerCursor's own fast coding model, tuned for the editor and priced well below frontier models; the recommended day-to-day model for executing a plan. Press Enter for the full definition. to execute it. The thinking is already done up front, so what you're optimizing for is speed. Name the pattern, not the generation: the picker turns over every few months.
If a user complains that Agent runs feel slow on big tasks, point them at this split before anything else.
"Plan with a frontier model so the agent writes out exactly what it'll do, then switch the model to ComposerCursor's own fast coding model, tuned for the editor and priced well below frontier models; the recommended day-to-day model for executing a plan. Press Enter for the full definition. to execute. Composer has enough context and juice to run the plan well, and because all the thinking is done up front, you're just buying speed."
The single most common question support fields is which model to pick. The honest answer is to let the user determine it for themselves: Best-of-N runs the same prompt with the same inputs across several models in parallel so you can compare the outputs side by side.
You can even run one model twice (2X it) to see the variance from the same prompt - that variance tends to surprise people. There's an upfront cost to running a prompt redundantly, but it's far cheaper than going down a rabbit hole with the wrong model and redoing the whole task.
Interactive widget. Tab through its controls; the result updates in the panel below as you change them.
Plan and reason with a frontier model (today Claude Opus 5 or the GPT-5.x line), execute with a fast in-house Composer model, and let Auto route when you're unsure. Best-of-N settles ties empirically.