Shane Deconinck Trusted AI Agents · Decentralized Trust
Just launched: trustedagentic.ai · a structured approach to your agentic transformation

New Explainers: Agentic AI Infrastructure

· 1 min read

I’ve been building interactive explainers on the protocols that make agentic AI work:

UserOBOAgentAgentGatewayCedar policiesMCPToolsA2AAgentsacross organizational boundariesTSPTrust Spanning Protocol
  • OBO (OAuth On-Behalf-Of): How agents get delegated user authority
  • AgentGateway: Centralized policy enforcement
  • MCP (Model Context Protocol): How agents connect to tools
  • A2A (Agent-to-Agent): How agents talk to other agents
  • TSP (Trust Spanning Protocol): Trust across organizational boundaries

Each covers what the protocol solves, interactive step-through demos, security risks, and what’s still missing.

I'm building the PAC Framework™ to help organisations adopt agentic AI with trust at the center: where to deploy agents, how to hold them accountable, and how to keep them under control. More at trustedagentic.ai.

Stay in the loop

A few times per month at most. Unsubscribe with one click.

Your email will be stored with Buttondown and used only for this newsletter. No tracking, no ads.

Signed by did:webvh:QmfFkciJnt8xMBXk2cQgpGd9xD8To9tvXzbtabc5rLGVNP:shanedeconinck.be
↑ Back to top