Notes from the team building memory.
Product thinking, architecture deep dives, customer stories, and the occasional opinion on what enterprise AI should actually look like.
Why organizational memory is the next platform layer
Wikis and chatbots are point solutions to the wrong problem. The unit of organizational reasoning is the edge — not the document.
How we built the AI interview agent
The hardest part was not the model. It was the question policy — knowing when to push, when to reflect, and when to stop.
From six months to nine weeks: a ramp story
How Helix Bio used Mnemos to cut new-hire ramp time across R&D and Ops without adding headcount to the people team.
Permission-aware AI is the only kind that ships
Enterprises don't fail to adopt AI search because the answers are wrong. They fail because the answers include things the asker should not see.
The bus-factor conversation no one wants to have
Most companies say they care about continuity. Most companies measure it once a year, by accident, when someone resigns.
What SOC 2 actually checks, and why we passed clean
An honest walkthrough of what a Type II audit examines, what auditors care about, and how Mnemos prepared.
Stop writing runbooks. Start recording them.
Why voice-led capture beats document-first authoring for procedural knowledge — and how the data backs it up.
What we mean by 'organizational memory'
A short definition, a longer explanation, and the working principles we use to build the product.
How we think about the graph
A short tour of the Mnemos memory graph — what is an entity, what is an edge, and why we run it on Postgres.
The quiet cost of tribal knowledge
Public research on knowledge work consistently underestimates how much time is spent navigating around what is undocumented.