Blog
Measured notes from Jepela: what the engine does, what it gets wrong, and what changed. Every number says where and when it was measured. Atom feed.
When not to use an LLM for a decision2026-10-15 · If your code needs one judgment from a known set of answers, a text generator is more than you need. When to use a decision engine, and when not.What our engine gets wrong, and why limits go in code2026-10-15 · The Jepela engine does not compare numbers or read negation, and lines move answers by being there. Measured, with what we check in code instead.Jepela accounts are open: a decision API that remembers2026-10-15 · Since 2026-10-15 businesses can sign up for Jepela, a decision API with memory: typed answers with probabilities, and output is free.Forgetting with proof2026-10-15 · Jepela's forget removes a fact from a subject's memory, then checks that recall no longer finds it. What it removes, what stays, and a measured run.