Governed knowledge infrastructure
I built the Second Brain because search could find what I remembered to ask for, while the decisions I most needed to revisit were usually the ones I had forgotten.
I use it across multiple AI assistants to search my records and recover information I’ve forgotten. It distinguishes original records from summaries and extracted facts, uses reviewed context as its current reference, and routes proposed additions and uncertain entities for review.
I had years of meetings, AI sessions, notes, and interactions carrying more context than I could actively hold, while ordinary search kept rewarding the terms I already knew.
The additional risk is epistemic. If extracted facts, summaries, and source documents lose their distinct authority, an assistant can repeat a derived claim with the confidence of a primary record.
System output against fabricated inputs; no employer data.
Open full-size image Method: see How the evidence was made.The system makes recall, hybrid search, deep research, fact and entity operations, graph summaries, calendar context, and meeting preparation available to multiple AI assistants through one interface.
Direct search helps me find relevant records. Proactive recall looks for connections I may have forgotten. Reviewed context is the current reference. Proposed additions and uncertain entities wait for review; some matched corrections can apply through the scheduled reconciliation process.
I use different ranking objectives for known-item retrieval and forgotten-connection discovery because one compromise sort order weakens both jobs.
System output against fabricated inputs; no employer data.
Open full-size image Method: see How the evidence was made.I keep curated context, primary records, summaries, and extracted facts at distinct levels of authority, then let newer or more specific evidence challenge the current view without silently overwriting it.
I stage potential durable corrections for review so promotion, rejection, and deferral remain explicit human decisions with an audit trail.
I built a mobile-first interface around current schedule and action state, while authenticated tools make the same knowledge available inside active AI conversations.
A relevant result is not necessarily the current answer. I check its source and date, particularly when newer evidence may have changed the situation.