Architecture
The operations graph, data model, and retrieval pipeline that power Workipedia. This is how raw calls, messages, and emails become structured business intelligence.
Four layers, one operations graph.
Workipedia operates as a layered system. Raw sources flow in at the bottom, intelligence processes them in the middle, memory stores what matters, and surfaces deliver context where employees need it.
Seven core entities.
The data model is designed around traceability and governance. Every piece of knowledge traces back to a source artifact, and every schema change goes through a governed proposal process.
Atomic units of knowledge — a customer preference, a gate code, a contact method. Every fact traces back to its source artifact.
Structured data fields inferred from expert behavior. The schema of how the business actually operates.
The meta-schema — what kinds of facts the system can learn. Grows as the business reveals new patterns.
Vectorized memory fragments for retrieval. Summaries, transcripts, and contextual snapshots.
Governed change requests to the schema. Every proposed change goes through review before becoming live.
Real-time detection events from live calls — intent shifts, sentiment changes, outcome predictions.
Full audit trail of what the AI saw and why it suggested something. Traceability is not optional.
From raw source to schema of work.
The retrieval pipeline prioritizes confirmed facts first, then active work state, then recent communication history, then broader memory. Every AI-assisted response can answer: what did the model see, and why did it suggest this?
Calls, emails, messages, PDFs, scans, attachments — the messy reality of small business communication.
Multi-modal extraction pulls facts, entities, preferences, and patterns from raw source material.
Every extracted fact links back to its source artifact. No fact exists without provenance.
Expert employees confirm, reject, or correct facts through lightweight prompts at natural moments.
Batch synthesis reviews the day's signals, proposes schema changes, and updates memory.
The living, governed operating model of the business — procedures, fields, facts, and memory.
// Our advantage is not that other systems can send us clean facts.
// Our advantage is that we can find facts where other systems still
// see only emails, calls, PDFs, scans, and attachments.