Every fact has a receipt
Click any entity, relationship, or value and see the highlighted sentence in the original document, who approved it, and when.
Platform
Enterprise Search One search bar for everything you know Knowledge Graph Every fact carries a receipt Agent Studio AI teammates that follow policy App Builder New One prompt to a live applicationPlatform · Knowledge Graph
Your documents, turned into a network of facts.
Search finds documents. The Knowledge Graph understands what's inside them: the people, organizations, contracts, obligations — and how they connect. It is built to a standard most graph products never attempt: every fact on the map carries a receipt.
Automatic extraction, human control
AI proposes what it finds; your reviewers approve what enters the graph. Extraction that doesn't meet the quality bar is refused, not published.
One entity, complete
Duplicates are recognized and merged — “Acme Corp,” “ACME Inc.,” and “Acme Corporation” become one 360° view, reversibly and auditably.
Travel through time
The graph is bitemporal: it remembers what was true and when you learned it. Scrub back to any date and see the world as you believed it to be.
Contradictions surface themselves
When two sources disagree on an amount, a date, an obligation — LACE flags the conflict and shows both pieces of evidence side by side.
Built for federal standards
Extraction grounded in the BFO/CCO ontology standards adopted as the DoD and Intelligence Community baseline — exportable as a compliance artifact.
In practice
Drop two versions of a policy into LACE and get an instant conflict map: every changed obligation, amount, and date — each with both source passages side by side. Then scrub the timeline back and watch your enterprise evolve.
Under the hood
A graph with an evidence ledger underneath.
Bitemporal assertions
Facts record when they held in the world and when LACE believed them. Corrections close and supersede assertions — history is never rewritten.
Schema packs
Versioned, executable ontology contracts: classes, relations, identity rules, and validation — drafts are editable, publishing is governed and immutable.
Governed materialization
Candidates flow through validation, grounding, and review before they become graph. Low-confidence or conflicting work queues for humans — never silently committed.
FAQ
What enterprise teams ask.
What makes the LACE knowledge graph evidence-locked?+
Every materialized entity, relationship, and value retains a link to the source passage that supports it, along with review and timing information. Users can move from a fact back to its evidence.
What is a bitemporal knowledge graph?+
A bitemporal graph records both when a fact was true in the world and when the system learned or recorded it. This supports point-in-time questions without erasing prior history when information changes.
How does LACE handle conflicting facts?+
When sources disagree, LACE preserves both evidence paths and flags the conflict for review instead of silently selecting one version. Corrections supersede assertions without rewriting history.
Does LACE support BFO and Common Core Ontologies?+
Yes. LACE supports versioned schema packs aligned to Basic Formal Ontology and Common Core Ontologies for programs that require standards-conformant knowledge modeling and reviewable conformance artifacts.
MCP Server
Works where you work.
The whole platform is an MCP server. Connect it once, and the AI tools your team already lives in can search your knowledge, ask the graph, and put governed agents to work — same permissions, same citations, same audit trail, wherever the question is asked.
- Claude Cowork Delegate the busywork
- Claude Code In your terminal
- ChatGPT Ask in chat
- Codex Ships the code
- Microsoft Copilot Across Microsoft 365
- Cursor In your editor
One endpoint — every MCP client
Next step
See your documents become a graph.
We set up a pilot on your documents and one workflow your team actually runs. You judge the working output — in weeks, not a quarter-long project.