Source-level evidence
Every signal, score and recommendation links back to the underlying record — the email, the filing, the transaction, the document — with the source visible at a click.
From red flags to investigable networks.
Compass supports authorized teams in reconstructing relationships across people, companies, assets, accounts, transactions and events — with source-level evidence and explainable reasoning.
The problem
Investigations live across systems. Networks live across investigations.
Case files, transaction histories, registry data and intelligence sit in disconnected systems. Reconstructing the network behind a red flag is manual, time-consuming and rarely complete.
How Compass works
From red flag to evidence graph.
- 01
Ingest case data, transactions, registries, open sources and authorized datasets
- 02
Resolve people, companies, assets and accounts into a unified investigation graph
- 03
Surface non-obvious relationships, recurring patterns and hidden hubs
- 04
Document hypotheses with source-level evidence for every link
- 05
Export structured findings for case management and reporting
Non-obvious relationship
A flagged account. A dormant company. A shared device.
Direct review of the account shows isolated activity. Compass connects it to a dormant company through a shared device fingerprint and a recurring legal representative — opening a network the analyst could then investigate with full evidence trail.
Outputs & benefits
What you get out.
- Network reconstruction across people, companies, assets and events
- Hypothesis support with source-level evidence
- Pattern detection across cases and time
- Structured exports for case management
- Full audit trail of analyst actions
Order of magnitude
−60%
Time to reconstruct a network
3×
Non-obvious links surfaced per case
100%
Evidence traceable to source
Trust by design
Evidence, explainability, audit — built into every output.
Explainable recommendations
No black-box outputs. Each priority states why it was promoted, which signals contributed, which were declassed, and which model version produced it.
Audit trail by default
Signals, model versions, reviewers and actions are logged and reconstructable later — ready for internal control, regulators and your own governance.
Human-in-the-loop
Compass recommends. Authorized people decide. Every consequential action requires a named reviewer who can confirm, override or annotate the reasoning.
Human-in-the-loop
Compass assists authorized investigators. It does not make legal, investigative or prosecutorial decisions. Every link, hypothesis and export is reviewed by a qualified analyst and supported by source-level evidence. Designed to support GDPR and EU AI Act obligations.
See it on your data.
30 minutes. We'll wire Compass to a representative slice of your environment — and walk you through the relationships, signals and actions it would surface today.