<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Mentat — blog</title><description>Deep dives on prediction market design, zkTLS settlement, AI authoring pipelines, and Solana protocol engineering.</description><link>https://mentat.cryptuon.com/</link><item><title>Curators are the adversarial layer AI markets need</title><link>https://mentat.cryptuon.com/blog/human-curation-loop/</link><guid isPermaLink="true">https://mentat.cryptuon.com/blog/human-curation-loop/</guid><description>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.</description><pubDate>Sat, 30 May 2026 00:00:00 GMT</pubDate></item><item><title>Designing settlement logic for Solana prediction markets</title><link>https://mentat.cryptuon.com/blog/solana-settlement-design/</link><guid isPermaLink="true">https://mentat.cryptuon.com/blog/solana-settlement-design/</guid><description>The MarketFactory and MarketSettlement programs are the smallest possible programs that do their job. Here is what&apos;s in them and why.</description><pubDate>Sat, 16 May 2026 00:00:00 GMT</pubDate></item><item><title>Inside the Scout-Draft-Validator pipeline</title><link>https://mentat.cryptuon.com/blog/scout-draft-validator/</link><guid isPermaLink="true">https://mentat.cryptuon.com/blog/scout-draft-validator/</guid><description>How Mentat&apos;s DSPy agent chain turns a one-line idea into a structured market specification — and what we learned tuning it.</description><pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate></item><item><title>Mentat vs Azuro: liquidity primitives vs full-stack market protocols</title><link>https://mentat.cryptuon.com/blog/mentat-vs-azuro/</link><guid isPermaLink="true">https://mentat.cryptuon.com/blog/mentat-vs-azuro/</guid><description>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.</description><pubDate>Sun, 19 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Where prediction markets are in 2026</title><link>https://mentat.cryptuon.com/blog/prediction-markets-2026/</link><guid isPermaLink="true">https://mentat.cryptuon.com/blog/prediction-markets-2026/</guid><description>An honest snapshot of the prediction market industry after the 2024 cycle, Kalshi&apos;s CFTC win, and the slow arrival of cryptographic settlement primitives.</description><pubDate>Sun, 12 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Mentat vs Polymarket: cryptographic settlement vs corporate dispute desks</title><link>https://mentat.cryptuon.com/blog/mentat-vs-polymarket/</link><guid isPermaLink="true">https://mentat.cryptuon.com/blog/mentat-vs-polymarket/</guid><description>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.</description><pubDate>Sat, 04 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Why prediction markets need zkTLS, not oracles</title><link>https://mentat.cryptuon.com/blog/zktls-versus-oracles/</link><guid isPermaLink="true">https://mentat.cryptuon.com/blog/zktls-versus-oracles/</guid><description>Oracle networks were a 2017 answer to a problem zkTLS proofs solve more directly in 2026. Here&apos;s the architectural argument for cryptographic settlement.</description><pubDate>Sun, 22 Mar 2026 00:00:00 GMT</pubDate></item></channel></rss>