Outside, the night was cold and the streetlights painted the shop’s windows a flat gold. Lila locked the door, feeling a small, particular satisfaction: a tool that listened had taught them a way to speak more clearly to each other—and, in turn, to the metal they shaped.

Over the next week, the language pack revealed itself in increments. It adjusted toolpath names to match the team’s slang—“finishing” became “polish run” where they preferred it; “rapid retract” became “respectful retract” on slow fixtures. The suggestions adapted to particular cutters; if a certain batch of endmills ran a little dull, the system suggested slightly higher axial depths to reduce rubbing. It began to catalog the shop’s idiosyncrasies: how Mateo always favored climb milling on aluminum, how Sara in quality favored chamfers on certain fillets. The more it observed, the less generic the suggestions became.

Priya didn’t argue. She showed version diffs: recommendations that improved cycle time or reduced rework, and a few that failed—annotated and rolled back. The model had a curator team, a human feedback loop. That was the key. The language pack behaved like a communal machinist: it could suggest, but humans curated its best moves.