What problem does it solve? In multi-agent systems, different agents often encounter the same real-world entity (customer, company, product) from different sources and create duplicate or conflicting records. This Skill operates a shared identity graph so every agent deterministically resolves the same record to the same canonical entity_id, preventing duplicate charges, conflicting actions, and cascading errors. ## Core Features & Use Cases - Deterministic Identity Resolution: Normalize, block, score, and cluster incoming records against the identity graph, returning a canonical entity_id with confidence scores and per-field evidence. - Multi-Agent Merge/Split Coordination: Propose merges and splits with evidence, review other agents' proposals, detect conflicts, and maintain a full audit trail with optimistic locking and rollback. - Graph Integrity & Tenant Isolation: Simulate mutations before committing, track entity events (created, merged, split, updated), scope every query to a tenant, and mask PII by default. - Use Case: A billing agent and a support agent both encounter "Bill Smith" and "William Smith" at the same email. This Skill resolves both records to one canonical entity with 0.94 confidence, so the customer is never charged twice. ## Quick Start Ask the agent to resolve an incoming customer record against the identity graph and return the canonical entity_id with confidence and match evidence.
