From the team
Blog
Engineering deep-dives, product updates, and ideas from the team building Parametric Memory.
Building Parametric Memory With Parametric Memory: Notes From a Solo Founder
I built our SaaS with the help of an AI pair programmer that had our own product plugged in as its long-term memory. Four real moments from the substrate that changed how I work — including one user correction I gave the AI that's still constraining its behaviour today.
MMPM Is a Memory Grammar, Not a Schema: Design Your Own Atom Types for Any Domain
The seven atom types we shipped with were enough to run our SaaS. They are not the limit of what MMPM can hold. This post walks through designing a custom atom set for an AI security companion that watches for vulnerabilities in your stack — and shows the same five-move pattern you can use for any domain you care about.
Article 12, the EU AI Act, and Why Your Audit Logs Need Cryptographic Roots
The EU AI Act's record-keeping mandate becomes enforceable this August. The text doesn't say 'Merkle tree' anywhere — but it does say your logs must be automatic, traceable, and worth something to an auditor. Here's an honest read on what Article 12 actually requires, and how Parametric Memory helps compliance teams answer the questions that follow.
The End of Dashboard Fatigue: Why Your Business Needs a Memory, Not a Database
Moving away from rigid databases toward a Memory Substrate — a living, narrative memory of your business that an AI can query to provide total situational awareness.
Introducing Parametric Memory: Verifiable AI Memory with Merkle Proofs
Today we're launching Parametric Memory — persistent, cryptographically verifiable memory for AI agents. Here's what we built and why.