Agent ID Technical Demo
The demo is an interactive implementation of an agent ID protocol. It details and documents the specific steps each entity takes to allow an AI agent to securely access a web service on behalf of its deployer.
Currently the demo follows a scripted set of steps that show how each component of the agent ID is assembled and used. Next, we will bring each entity to life, letting a viewer inspect network requests and server code as the process runs in real time.
Walkthrough
Our technical lead Sam walks you through our technical demo.
Navigating the agentID Technical DemoVideo 1 
Creating and using the agent ID in an exchange between an internet service and an AI agentVideo 2 - Coming soon
Using the agent ID for incident response
Walkthrough video is on its way.
Using the agent ID for incident responseVideo 3
Purposes
Explanation: Designing protocols can be complicated. The interactive diagram helps explain how agent IDs work and why they are important at a high level.
Demonstration: Stepping through the protocol shows a more detailed view of what information is exchanged, where it comes from, and how it is secured.
Implementation: [In progress] Viewing the implementation of each step by each entity provides a concrete reference implementation of the protocol, paving the way for smooth adoption.
What's next
We have an exciting list of agent governance use-cases that the technical demo will enable, including:
- Integrating more identity and authorization protocols to promote easy adoption.
- Tabletop exercises exploring how to respond to cybersecurity incidents involving AI agents.
- Simulating many agents and services operating in this controlled environment in order to study what configurations or interventions lead to the best outcomes.
Design & Code
- Read the design doc — requirements and architectureTBA
Builds on our policy memo.
- View the code behind the technical demo
