About rightmodel

I built rightmodel because developers, including me, default to the biggest model too often. Renaming a variable gets the same model as designing a database schema. The waste is real and the habit is hard to break without something that makes the right choice obvious.

I'm Regnard Raquedan, a Senior Solutions Architect at GitLab and a Google Developer Expert. I built this as a personal project on weekends. It is not a startup.

rightmodel is free and intended to stay that way. No signups, no ads, no upsells. The classification logic is open source, so if a recommendation looks wrong, open an issue or send a pull request with a better signal pattern.

rightmodel is the canonical implementation of the Explanation Caching pattern from the Precomputed AI architecture. The decision logic is deterministic; the LLM writes the reasoning layer ahead of time, and the app serves precomputed explanations alongside the result. The compiled classification ruleset, task archetypes, pricing snapshots and precomputed explanations are the versioned artifacts. They are served without live inference on the normal path. Escalation to a live model via deep analysis is declared, disclosed and opt-in.

Cite the pattern as Raquedan, R. (2026). Precomputed AI: Reason Ahead of Time, Serve Instantly. https://precomputedai.com.

Find me at regnard.raquedan.com, on LinkedIn or via my GDE profile .