Cortex Grid demo
Resolve entities across fragmented sources
Connect people, accounts and artefacts into one reviewable graph, with each link cited.
The challenge
The same actor appears differently in each source, so connections are missed or asserted without support.
The scenario
Several accounts may belong to one actor, and the connection must be shown rather than claimed.
What goes in
- Multi-source evidence
- Records referring to the same actors differently.
What you can ask
Illustrative prompts. Results depend on your own data and are not deterministic.
- “How are these accounts connected?”
- “What supports this link?”
- “Which connections are inference?”
How Clearception approaches it
How the work is structured. Each step shows what its output is grounded in.
Extract identifiers
ObservedCollect the identifiers each source uses.
Propose links
AI-inferredSuggest connections, each with supporting evidence.
Bound confidence
AI-inferredCap link confidence by the strength of support.
What you get
The shape of what comes back — not a promised result.
Entity graph
AI-inferredConnections with citations and confidence per link.
Why it matters
- Links you can check
- Every connection opens onto its support.
Related demos
Cortex Grid
Build a timeline from digital evidence
Assemble a chronology from fragmented digital sources with custody preserved throughout.
5 minute walkthrough
- Chain of Custody
- Timeline Construction
- Evidence Trail
Cortex Grid
Assess whether media has been manipulated
Examine media for manipulation signals and report Content Credentials where present.
4 minute walkthrough
- Media Authenticity
- Evidence Trail
- Confidence Ceilings
Lawgorithm
Take in and organise a discovery set
Deduplicate, classify and index discovery material on arrival, with provenance recorded.
4 minute walkthrough
- Document Intelligence
- Chain of Custody
- Evidence Trail
Want to try this with your own work?
Open Cortex Grid and bring your own data. No signup is needed to read these demos.