Jinn learns it once. Applies it everywhere.

The routing table.

Expensive models only where the work genuinely needs one, fast models where volume matters — so your plan buys results, not waste. Overrides are allowed, but every one is logged with a reason.

• Visibility checks, run constantlymonitoringFast, small modelsThe always-on checks that watch how AI engines talk about your brand run constantly, so they run on fast, small models — by rule, not by accident. A bigger plan buys more checks across more engines, never a bigger model doing the same check.
• Judging what an engine got rightfidelityMid-weight · frontier at premiumJudging whether an AI engine described your brand correctly runs on a mid-weight model, and premium plans step it up to the most capable class.
• High-volume short-form copypin_copyFast, small models · every tierShort, high-volume copy — a batch of 75 pins, several AI calls each. Fast, small models on every tier: short copy in your brand voice doesn't need an expensive model, and a batch that size couldn't afford one.
• Long-form strategy documentsdeliverableWorkhorse to frontier, by roleRoutine sections run on the workhorse class; the parts that have to think hardest escalate to the most capable model available. If a model errors mid-run, the call steps down one class with a logged warning — never a silent swap.
• Strategy briefsbriefAlways frontierStrategy briefs always get the most capable model. You asked for them and they're rare, so the budget holds.

When a vendor ships a better model, the upgrade is one entry in one table — the whole suite moves at once. You wake up to better output without touching a setting.