# Proof of AI

URL: https://docs.hanzo.ai/docs/proof-of-ai

> How Hanzo verifies AI computation on-chain, how node operators get paid, and how the cloud pays the open-source developers it runs on.

Proof of AI (PoAI) is how Hanzo makes AI computation **verifiable** instead of
asking you to trust a black box. It underpins two things:

- **Verifiable inference** — a result anyone can re-check.
- **An open-source payout** — a commitment that 25% of attributable cloud
  revenue flows back to the developers whose code the cloud runs.

This section documents what works today and what is on the roadmap. We label
both, because verifiability is the entire point.

## What PoAI proves, and how

Floating-point AI is non-deterministic — the same model and input can yield
slightly different numbers on different hardware. You cannot reach consensus on a
number that changes every run. PoAI removes the non-determinism:

- **Integer-only inference.** Models run in `int8` with `int32` accumulation,
  arithmetic right-shift scaling, saturating outputs, and frozen lookup tables
  instead of `exp()`/`rsqrt()`. The forward pass is **bit-for-bit identical**
  across CPU, Metal, CUDA, and AMD.
- **Verification by recomputation.** The integer transformer is a registered EVM
  precompile at `0x0300...0003`. Every validator re-runs the identical
  computation during block execution; a mismatched output is rejected. No
  committee, no trusted hardware, no proof to forge.

### Live today

- A deterministic `int8` transformer (`gemm_i8` keystone) implemented
  byte-identically in Go, Rust, and C++, with GPU kernels (Metal/CUDA/HIP) that
  pass the same known-answer tests.
- A **registered** on-chain inference precompile at `0x0300...0003`, shared by
  the Lux, Zoo, and Hanzo EVMs.
- Cross-language golden-token tests gating CI.

### Roadmap

- **Production-size models.** The precompile runs a small reference model today;
  a zen-nano port is in progress. The model line is small,
  fully-verifiable models plus sampled verification of large ones.
- **Cryptographic proofs.** zkML proofs and TEE confidential execution are
  designed and stubbed for a later release. Today's guarantee is determinism you
  can re-run.
- **Hardware attestation for large models.** AMD SEV-SNP attestation is
  implemented end-to-end; Intel TDX and NVIDIA GPU confidential compute are
  scaffolded. See [Node Operator](https://docs.hanzo.ai/docs/proof-of-ai/node-operator).

## A note on consensus

Hanzo and Lux chains can run Quasar, a post-quantum threshold-certificate
consensus. Quasar finalizes the inference precompile's output the same way it
finalizes any chain state — it does **not** itself inspect model output.
"Verifiable inference" comes from the deterministic precompile, not from
consensus.

## In this section

- **[Node Operator](https://docs.hanzo.ai/docs/proof-of-ai/node-operator)** — run Hanzo Node, receive
  work, get paid, and the trust/attestation requirements.
- **[Open-Source Payouts](https://docs.hanzo.ai/docs/proof-of-ai/oss-payouts)** — how the cloud
  attributes usage to your dependencies and pays their authors.

- [Node Operator Guide](https://docs.hanzo.ai/docs/proof-of-ai/node-operator): Run Hanzo Node, advertise capabilities, receive work, and get paid — plus the trust and TEE attestation requirements, with an honest line between what works today and what is roadmap.
- [Open-Source Payouts](https://docs.hanzo.ai/docs/proof-of-ai/oss-payouts): How Hanzo Cloud attributes usage to the open-source packages it runs and pays their authors — the 25% commitment, the attribution pipeline, and how to participate, with an honest line between live and roadmap.