# AI Risk Index — airiskindex.io

The most methodologically rigorous, fully transparent AI job-exposure index.
Task-based scoring of occupations on AI-driven automation exposure, with three
separate sub-scores per occupation — **exposure**, **substitution**, **augmentation** —
each with confidence intervals, versioned methodology, and a public API.

- Methodology (source of truth): [`docs/methodology/METHODOLOGY.md`](docs/methodology/METHODOLOGY.md)
- Research corpus grounding v1: [`docs/research/`](docs/research/README.md)
- Contributor rules: [`CLAUDE.md`](CLAUDE.md)

## Quick start

```bash
pnpm install
docker compose -f infra/docker-compose.dev.yml up -d   # postgres 16 + redis
cp infra/.env.example .env                             # fill values
pnpm db:migrate && pnpm db:seed
pnpm dev                                               # web on :3000
```

Checks: `pnpm typecheck && pnpm lint && pnpm test`

## Layout

Monorepo (pnpm + Turborepo): `apps/web` (Next.js site + public API), `apps/worker`
(BullMQ jobs incl. the multi-model LLM rater), `apps/etl` (Python pipeline),
`packages/scoring` (pure, deterministic scoring engine), `packages/db` (Prisma),
`packages/ui`, `packages/config`. See CLAUDE.md §3.