2 min lesson
The core surfaces: Tab, Agent, Ask
Work through the cases in "The core surfaces: Tab, Agent, Ask", pairing each signal with the move that fits.
Step 1 of 2
An SA who fumbles the difference between Tab, Agent and Ask loses the room in the first ten minutes, because the room is full of engineers who already use one of them daily.
Cursor is not one feature with a chat box bolted on. It is three distinct interaction surfaces, each with its own latency budget, its own trust model and its own place in a developer's hands. Conflating them is the most common reason a rollout stalls: the team tries to do everything through Agent, gets burned by an over-eager edit and quietly retreats to plain autocomplete.
Your job is to make the boundaries crisp. When you can name the right surface for a given moment faster than the senior engineer in the room, you have earned the credibility to advise on the harder stuff.
Next-edit prediction: multi-line and cross-file completions that anticipate the change you're already making.
The everyday speed layer. Zero ceremony, sub-second, fires as you type.
Wins when a developer knows exactly what they want and just wants the keystrokes back.
Multi-step, multi-file autonomous edits driven by natural-language intent. Plans, reads the codebase, runs commands, applies a diff you review.
The headline AI-native workflow and the thing CTOs have heard about.
Wins on a real task with a verifiable end state: a refactor, a failing test, a ticket.
Question-answering and exploration over the codebase with no edits applied.
The understand-before-you-touch surface. Read-only by design.
Wins for onboarding, code archaeology and why does this work this way?