2 min lesson
The authentic-usage test
Rebuild the parts of "The authentic-usage test", then say why each one matters.
Step 1 of 2
Interviewers spot superficial familiarity fast. Generic praise like "I love how fast it is" signals elimination, because a routing-and-inference candidate who only skimmed the product can't reason about the path they'd be hired to own.
Specificity is the whole test. Name the surfaces, describe a real task on a real repo and say what worked and what frustrated you. For this role especially, your critiques should land on the inference experience: a Tab completion that arrived late, an Agent run that stalled mid-stream, a model swap that changed answer quality.
- Tab
- Inline multi-line completion with the tightest latency budget of any surface
- Cmd+K
- Inline edit or generate on a selection. Interactive, so it expects a fast first token
- Agent
- Multi-step, multi-file edits. Long-running and tolerant of latency, but sensitive to mid-stream failure
- Chat
- Conversational with codebase context. Streamed and quality-sensitive across model choice
Each surface has a different latency, cost and quality profile, and the gateway you'd own routes for all of them.
"I run Cursor daily on a TypeScript monorepo. Tab is the surface I'd defend hardest. When first-token latency creeps over ~120ms it stops feeling like autocomplete and I start typing past it. Agent is where I lean on it for refactors and the failure I notice most is a run dying mid-stream with partial edits, which is a failover and idempotency problem more than a model problem."