Plan · Run◆ inside Pass

Desk

Request in, result out

The Desk architects every request. It reads the task before any model is called, answers from what's already solved, and otherwise takes the cheapest path that still clears the bar — then hands back a receipt. Under 50 ms of overhead.

What the Desk does

It decides, checks, and learns

Decides

Task, language and difficulty — classified structurally, no model call. Then the best model in your tier by learned first-try odds, minus price and latency.

Checks

High-stakes answers verified; an honesty gate catches the wrong language, refusals when data exists, unsupported numbers. Fail → one model up.

Grounds

Your documents when Knowledge is on; live web search when it's about now, with sources on the receipt.

Depth is added per request, exactly when the answer needs it.

One request, seven moves

The path every request takes

Each move runs in the same call, in order — most of them without a model at all.

1Understand 2Reuse 3Ground 4Fit 5Route 6Verify 7Receipt

Put your first request on the Desk

Magic-link in, connect a key, ask — you're running in a couple of minutes.