AI's missing layers - owned by the engineers improving them

What you capture when you integrate.

Hokusai routes coding tasks for a per-decision fee. The fees back the token. You capture a position in that fee stream — plus a smarter router that lowers your inference costs along the way.

Integration

Drop-in middleware.

Route tasks through Hokusai, execute them in your harness, then report the result back so the shared router can keep improving.

import { route } from '@hokusai/router'

const { model, reasoning } = await route({
  task: userTask,
  context: harnessContext,
})

const result = await models[model].run(userTask)
await route.reportOutcome(result) // mints tokens proportional to performance lift

What else the factory makes

The router is the first decision layer built on Hokusai. The same protocol applies to every model where shared, incentive-aligned learning beats siloed effort.