Features
Mentat is not a single product — it is a full stack: AI drafting, human curation, cryptographic settlement, and Solana-native economics, all MIT-licensed. Here is what each layer gives you.
AI authoring
Scout gathers context and sources, Draft writes the formal spec, Validator re-checks it against a rubric. The output is structured JSON — never free text — so it drops straight into the curator console and the on-chain schema.
Human curation
Curators review every draft with a side-by-side diff, validation scores, bulk approve/reject, and full version history. Nothing reaches Solana without a human sign-off — the adversarial layer AI markets need.
zkTLS settlement
Outcomes resolve when a zero-knowledge TLS proof attests to a canonical source. The Solana MarketSettlement program verifies the proof and triggers payout — no jury vote, no optimistic dispute window for the routine case.
Solana economics
MarketFactory and MarketSettlement are Anchor programs. Trades settle at sub-cent Solana fees with sub-second confirmation, which is what makes small, specialized markets economically viable at all.
Full list
A DSPy pipeline of Scout, Draft, and Validator agents turns a one-line idea into a full market specification — question text, resolution criteria, source allowlist, timestamps, and economics. Output is structured JSON ready for curation.
Outcomes resolve when a zero-knowledge TLS proof attests to a canonical data source — Reuters, CoinGecko, official APIs. The on-chain Solana program verifies the proof and triggers payout. No UMA jury, no optimistic dispute window for routine markets.
Human curators stay in the loop with side-by-side diff view, bulk approve/reject, validation scores, and complete version history. The console treats AI output as a draft, not a verdict.
MarketFactory and MarketSettlement programs are written in Anchor. Trading happens at Solana fee tiers — sub-cent transactions, sub-second confirms — not Ethereum L1 prices that price out small bettors.
Every market — binary or multi-outcome — conforms to the same standard: question, resolution criteria, source list, trigger condition, fallback, invalidation clause, economic parameters, state machine. Indexers, UIs, and integrations all speak one format.
The whole stack — Vue frontend, FastAPI backend, DSPy agents, Solana programs, Rust indexer, proof service — is MIT. Self-host the protocol; bring your own AI keys; settle on your own Solana cluster if you want.
Every AI prompt, curator decision, and proof submission is logged. The on-chain market account stores a BLAKE2 hash of the AI rationale, so anyone can verify the off-chain narrative against the on-chain bytes.
These features connect into one flow: AI draft → human curate → zkTLS resolve → Solana settle.