Proof

A memory layer over our own working sessions

We built a semantic memory engine over our own engineering corpus. It answers questions about years of work with citations, or says nothing at all.

sessions in the corpus
retrieval p50, after the index fix
The corpus drawn as a wheel of gold glyphs: concentric identity-jittered rings around a molten ember core, one glyph per five working sessions.
The corpus itself, drawn: the wheel on our home page carries one glyph per five working sessions, 1,232 at the current receipted count. The figure is derived from the number; a recount re-lays the wheel.

The problem

Every engineering organization loses its own history. Decisions get made twice. The reason a system is shaped the way it is walks out the door, or scrolls out of a chat window. For an AI-assisted shop the loss is worse: thousands of working sessions, each full of decisions, dead ends, and fixes, and none of it queryable.

We had 6,160 of those sessions. We treated them as a database.

The system

An ingestion pipeline chunks and embeds every working session as it happens. Retrieval is hybrid: lexical and semantic search fused with reciprocal rank fusion, then reranked. A synthesis layer answers natural-language questions against the corpus and cites the specific sessions it drew from.

Two design decisions did the most work:

Honest-empty. When the corpus has no answer, the engine says “nothing found.” It never pads, never fabricates a memory. A memory layer you cannot trust on the empty case is worse than no memory layer.

Recency-aware modes. “What did we decide” and “where are we now” are different questions. Current-state queries bias ranking toward newer material so resolutions outrank stale design chatter; historical queries stay unbiased.

The engine runs as an MCP server, so every agent in our fleet queries institutional memory mid-task, the same way it reads a file.

Receipts

What this means for you

Your organization already generates this corpus: tickets, PRs, chats, docs, call notes. Nobody has built the memory layer over it yet. We build the same class of system over your material: ingestion, hybrid retrieval, cited synthesis, wired into wherever your people or agents already work.

Receipt

Verified
How it's measured
What it doesn't claim

No receipt, no number. Every figure on this site resolves here.