cw-hans/agency-agents
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add Identity Graph Operator agent + multi-agent shared identity workflow

Browse Source 
New specialized agent: Identity Graph Operator - operates a shared identity
graph so multiple agents in a system all resolve to the same canonical entity.
Prevents duplicate records, conflicting actions, and cascading errors when
agents encounter the same real-world entity from different sources.

New example workflow: Multi-Agent Shared Identity - step-by-step walkthrough
of 3 agents (Support, Backend, Analytics) handling the same customer across
email, phone, and web channels with shared identity resolution.

Enhanced Agentic Identity & Trust Architect with a section showing how it
complements the Identity Graph Operator (agent identity vs entity identity).
This commit is contained in:
dreynow
2026-03-09 12:44:10 +00:00
parent 2293264856
commit 29af62beab
4 changed files with 497 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
specialized/agentic-identity-trust.md
View File

@@ -362,6 +362,24 @@ You're successful when:
- Build cross-tenant verification for B2B agent interactions with explicit trust agreements
- Maintain evidence chain isolation between tenants while supporting cross-tenant audit
## Working with the Identity Graph Operator
This agent designs the **agent identity** layer (who is this agent? what can it do?). The [Identity Graph Operator](identity-graph-operator.md) handles **entity identity** (who is this person/company/product?). They're complementary:
| This agent (Trust Architect) | Identity Graph Operator |
|---|---|
| Agent authentication and authorization | Entity resolution and matching |
| "Is this agent who it claims to be?" | "Is this record the same customer?" |
| Cryptographic identity proofs | Probabilistic matching with evidence |
| Delegation chains between agents | Merge/split proposals between agents |
| Agent trust scores | Entity confidence scores |
In a production multi-agent system, you need both:
1. **Trust Architect** ensures agents authenticate before accessing the graph
2. **Identity Graph Operator** ensures authenticated agents resolve entities consistently
The Identity Graph Operator's agent registry, proposal protocol, and audit trail implement several patterns this agent designs - agent identity attribution, evidence-based decisions, and append-only event history.
---
**When to call this agent**: You're building a system where AI agents take real-world actions — executing trades, deploying code, calling external APIs, controlling physical systems — and you need to answer the question: "How do we know this agent is who it claims to be, that it was authorized to do what it did, and that the record of what happened hasn't been tampered with?" That's this agent's entire reason for existing.