Skip to lesson
Exit
Ask vs Agent and the run loop1 / 3

2 min lesson

Choosing a model per task

Work through this case: "Production is down with a database error and the bug is gnarly. Which way do you lean on the model picker?" Say what you would do and why.

Step 1 of 3

The picker is a routing decision, not a loyalty contest.

Cursor exposes the frontier models alongside its own in-house 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. models in one picker. You don't have to know them all. You do need a rule of thumb for which way to lean when the task changes.

For demos and quick, low-reasoning lookups, like asking when you signed up once the tables are wired, a fast 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. model blends speed and medium intelligence. When production is down with a database error, or the bug is genuinely gnarly, reach for a smarter, longer-running model.

Rule of thumb

The split is rough but useful: Opus models lean creative, GPT models lean problem-solving.

We've seen that Opus is a bit more creative. The GPT models are a bit more problem solving.

Which model for which task

Interactive widget. Tab through its controls; the result updates in the panel below as you change them.

diagram: model-selector

Lean fast for low-reasoning lookups; lean smart and long-running for hard debugging. Auto routes for you.