PEP intelligence
Political positions, jurisdictions, tenure and historical PEP status — structured with temporal context.
Intelligence
Entity intelligence, structured.
People, organisations, public roles and events — represented through source-linked claims rather than static records, then used by AI agents to help investigators resolve potential matches.
The graph
From records to intelligence.
A name tells you who might be a match. Averis builds the context around that name — connecting identities, relationships, events and evidence over time, with every material claim traceable to its source.
- Find information
- Verify where it came from
- Connect it to the right entity
- Reuse it next time
Averis GraphIntelligence graph
- Entity
- Public role
- Organisation
- Event
- Source
- Contradiction
- Unknown
Provenance path
Intelligence domains
Sanctions intelligence
Sanctions exposure connected to entities and relationships, with traceable claims.
Financial-crime intelligence
Adverse media and financial-crime intelligence linked through claims, not unsupported conclusions.
Entity and relationship intelligence
People, organisations, ownership and associates as a connected graph.
Regulatory intelligence
Regulatory events and classifications grounded in authoritative sources where available.
Court and legal intelligence
Court events and legal proceedings with evidence and provenance preserved.
Corporate context
Company registrations, directorships and organisational history.
Historical intelligence
Past roles and relationships retained — not overwritten when circumstances change.
Evidence and provenance
Every material claim connected to the evidence and sources that support or challenge it.
Domains describe the intelligence model. Coverage expands by jurisdiction and source — depth before breadth.
Evidence
Every conclusion should have a trail.
Averis Graph preserves not only what is known, but why. Provenance, support status and contradictory information are kept — and a source link records attribution, not validation.
- 01Source
The register, document or publication of origin.
- 02Evidence
The specific extract that supports or challenges a claim.
- 03Claim
The assertion, with confidence and lifecycle status.
- 04Entity
The person, organisation or relationship described.
Claim lifecycle
Supported
Evidence supports the claim.
Challenged
Contradictory evidence exists.
Corroborated
Independent evidence supports the claim.
Superseded
A newer claim replaces this state.
Retracted
Determined to be incorrect.
AI agents
AI agents turn the graph into an active investigation system.
- MVP today
- In development
Find
Research agents
Find relevant information in permitted sources and capture facts with their source references and observation context.
- Collect from registered sources (MVP today)
- AI extraction checked against the source (MVP today)
- Targeted research for missing facts (In development)
Connect
Enrichment agents
Help connect information to the right entities, add context and surface conflicting claims or missing attributes.
- Link records to stable entity IDs (MVP today)
- Bounded enrichment; flag conflicts (MVP today)
Human accountability
Agents gather and organise evidence; validation controls graph changes, and the accountable investigator makes the final disposition.
Investigate
Investigation agents
Compare a customer with candidate entities, gather evidence for specific questions and organise supporting, contradictory and missing information.
- Compare and sort evidence (MVP today)
- Recommend; human decides (MVP today)
- Targeted evidence gathering (In development)
Shared memory
Every agent reads from and adds to the same graph, so research done once can be reused by later investigations instead of being reconstructed from scratch.