Shane Deconinck Trusted AI Agents · Decentralized Trust

With the rapid evolution of AI agents, standards are emerging for how they authenticate, connect to tools, and communicate with each other.

Here are interactive walkthroughs of the most important ones: what they solve, how they work, and where the gaps remain.

User OBO Agent Agent Gateway Cedar policies MCP Tools A2A Agents across organizational boundaries TSP Trust Spanning Protocol

Everything above the line works within your trust domain. TSP is the emerging layer for when agents need to verify strangers.

Understanding AgentGateway: The Security Gateway for MCP and A2A

Explainer on AgentGateway for securing AI agent traffic with centralized auth and policies

Understanding AgentGateway: The Security Gateway for MCP and A2A

Understanding TSP: The Trust Spanning Protocol Explained

Explainer on Trust Spanning Protocol for decentralized identity and cross-org agent trust

Understanding TSP: The Trust Spanning Protocol Explained

Understanding MCP: Anthropic's Model Context Protocol Explained

Interactive explainer on Anthropic's MCP protocol for connecting AI agents to tools

Understanding MCP: Anthropic's Model Context Protocol Explained

Understanding A2A: Google's Agent-to-Agent Protocol Explained

Interactive explainer on Google's A2A protocol for agent-to-agent communication

Understanding A2A: Google's Agent-to-Agent Protocol Explained

Understanding OAuth On-Behalf-Of: The OBO Token Exchange Flow Explained

Interactive explainer on OAuth OBO flow and RFC 8693 token exchange for AI agents

Understanding OAuth On-Behalf-Of: The OBO Token Exchange Flow Explained