Active development. APIs and behaviour may change. Production use at your own risk. GitHub
Mentat

Blog

Notes from the proof layer.

Long-form technical writing on Solana prediction market design, zkTLS proof verification, AI authoring pipelines, and honest competitor comparisons.

2026-05-30 curationai-safety

Curators are the adversarial layer AI markets need

Letting AI generate markets without human curation is a category error. Here is why the curator console is not a temporary scaffold — it is permanent infrastructure.

Read post →

2026-05-16 solanaanchor

Designing settlement logic for Solana prediction markets

The MarketFactory and MarketSettlement programs are the smallest possible programs that do their job. Here is what's in them and why.

Read post →

2026-05-02 aidspy

Inside the Scout-Draft-Validator pipeline

How Mentat's DSPy agent chain turns a one-line idea into a structured market specification — and what we learned tuning it.

Read post →

2026-04-19 competitiveazuro

Mentat vs Azuro: liquidity primitives vs full-stack market protocols

Azuro is a liquidity layer that powers on-chain bookmakers. Mentat is a vertically integrated prediction market protocol with cryptographic settlement. They occupy adjacent slots in the stack, not the same one.

Read post →

2026-04-12 industryanalysis

Where prediction markets are in 2026

An honest snapshot of the prediction market industry after the 2024 cycle, Kalshi's CFTC win, and the slow arrival of cryptographic settlement primitives.

Read post →

2026-04-04 competitivepolymarket

Mentat vs Polymarket: cryptographic settlement vs corporate dispute desks

Polymarket has the deepest USD liquidity in prediction markets and a centralized arbiter when settlement gets contested. Mentat replaces both the oracle and the desk.

Read post →

2026-03-22 zktlsarchitecture

Why prediction markets need zkTLS, not oracles

Oracle networks were a 2017 answer to a problem zkTLS proofs solve more directly in 2026. Here's the architectural argument for cryptographic settlement.

Read post →