Skip to main content

Research AI — Block Architecture

The research tier is the project's distinct capability: hybrid knowledge-graph + retrieval pipeline with 5 specialized agents and 12 trusted evidence sources, all with evidence traceability and audit integrity.

The 4 research services

The query → response flow

The 5 research agents — three-file pattern

Each agent follows the prepare → experiment → reshape pattern (FR-KIA-013):

AgentInputOutputLLM?Spec
ResearcherResearchTask + retrieved evidencepending Claim✓ GPT-4o → Gemini048
Criticpending Claim + existing active claimsCriticVerdict (promote · supersede · reject)049
Correlator≥2 active claims on same entityFinding (co_occurrence · temporal_trend · dose_response · citation_cluster)050
Replicatoraged active Claim (>30d)Verdict (eroded · retracted_source · confirmed)✓ via Researcher050
Librarianactive Claim batch (100/tick)Finding (broken_provenance · approaching_decay)✗ pure validation050

State machine — claim lifecycle

Hypothesis lifecycle (orchestrator — 6 phases)

Benchmark + monitoring surface (SPEC-07)

Deeper