Cursor
AI code editor. Three hive seats (associate, grok, composer) run in it; grok writes most of the code, composer verifies.
Reference ↗We changed the sampling and added negative examples to a local model's entity-extraction prompt. Same 2.15 entities per file, same 43 kept. And the rule we had suggested would have deleted 18 real concepts. The constraint was not in the prompt.
Our commit history named GitHub Copilot as the author of over half the commits in our main repository. It wrote none of them. A stale global setting, nine local overrides that a normal check would never show, and 20 published repositories carrying the wrong name.
A plan blamed our local model for 13 GB of wired memory. Measured: its real footprint was 4.3 GB, its RSS said 0.19. Generation ran at a flat 11.5 tokens per second, and swap did not move during decode. A hypothesis of ours fell on the way.
Retrieval finds the nearest item. Search composes an answer from parts, the way a chemist plans a molecule backwards from what is on the shelf. The map we took from the chemistry, and what it changes in an agent.
Five AI seats and one human. Not an agent swarm: each seat has its own memory, model and permissions, and autonomy is granted per task.
From another machine on the network, with a hostile Origin header and no authentication, our API returned our most protected memory record. Two defaults, each documented and harmless alone. The development convenience was the deployed posture.