Potential Topics
The agenda will be co-created the day of the event by attendees using Open Space Technology. These are ideas folks have submitted as they register, shared to give perspective on what participants are thinking about discussing.
đ Open Space Technology
We use Open Space Technology to co-create the agenda live the morning of the event. Below is the list of what attendees shared with us as they registered about topics they hope to learn about, want to present about and topics to discuss with others at the event. It is important to note this list is not used to "create the agenda" that is done by everyone gathered in person October 24th beginning at 9am.
We use Open Space Technology to co-create the agenda live the morning of the event. Below is the list of what attendees shared with us as they registered about topics they hope to learn about, want to present about and topics to discuss with others at the event. It is important to note this list is not used to "create the agenda" that is done by everyone gathered in person October 24th beginning at 9am.
Identity & Trust Infrastructure
- The role of decentralized identity in personal AI agents
- The role of SSI in agentic identity and inter-agent protocols
- Trust & identity
- Identity, trust in general for AgenticAI
- Trust and identity frameworks for Agentic AI
- How to anchor agents to ground truth
- DIDs and DIDCOMM are central to the overall Web 7.9 Agentic OS architecture
- How is trust maintained across a network of downstream services?
Agentic Commerce & Markets
- How will agentic commerce work? What are the UX, liability, and payment implications?
- AI agent marketplaces and negotiation mechanisms
- Equitable compute/resources for agentic AI markets
Security, Access & Policy
- AI permissions vs Human permissions
- Managing access rights
- Access control to data
- Agents access control who are accessing on behalf of users
- Particularly interested in delegation issues as well as dynamic authorization
- I would like to see how state management tokens are held in a secure way so that there is no privacy loss
- How will cryptographic tokens represent delegation?
- How to express security policies to authorize access, enforce restrictions, and track obligations?
- Access control and delegation in agentic systems
- Cryptographic tokens for delegation and dynamic authorization
- MCP security frameworks and evaluation
- How to ensure fairness and accountability across the agentic web
- Security, Identity, & Trust (human-in-the-loop by default): Credential safety for UI-driven agents with E2E channels and explicit user approval
Protocols & Standards
- MCP MCP MCP MCP!
- MCP security
- Why OAuth is not a fit for MCP
- I think I'm interested most in learning about MCP and how OAuth might relate to it, and specifically, how/whether browsers can help
- A2A protocol and cross app for Agentic AI
- ERC-8004, A2A, MCP
- The current state of standard and to see if an issue we see is being discussed or not
- Agent to agent negotiation
- MCP, A2A, ERC-8004, and beyond
- Why OAuth isn't a fit for MCP
- Browser integration and the role of credential managers
- Agentic Internet registries and credential registries
- Project NANDA & Agentic Registries
Credential Management & Registries
- Agentic Internet Registries
- The role of credential managers in the agentic AI ecosystem
- How to incorporate an access layer and a payment layer in a decentralized way
Web & Browser Integration
- I'm interested in learning how / whether the web and browsers can help
- My goal for XMLUI is that a developer using agents to build XMLUI apps will enjoy a level of MCP support that reliably steers agents to correct patterns. I don't think this requires more or different protocols, it does require discovery and application of practical techniques. agentic experiences, and in what ways they may need to change
- Browser-native Agents (beyond APIs): Computer-Use agents that operate UIs like humansânavigating, clicking, form-fillingâexpanding automation to services without clean APIs
Governance & Infrastructure
- How will we govern agentic AI? What tools are needed that don't exist today? What are the limits of identity for governance?
- What are the risks of delay while security and culture evolves to keep pace with existing progress?
- Policy derivations with AI agents
- Decentralized agentic swarms
- Infrastructure requirements for the agentic web
- Governance models and limits of identity in AI governance
- Enterprise Guidance & Benchmarks (operating models): What's actually working in agentic AI deployments and governance frameworks
- Infra Economics (design for throughput, cost, energy): Optimizing SLAs around end-to-end assurance, data quality, and resilience
Human-Agent Experience & Design
- Semantic interoperability
- Modeling social and collaborative agentic situations
- Agentic DevEx (from "vibe coding" to ADEs): Agentic Development Environments that let engineers delegate tasks to agents with deterministic intervention
Research & Collaboration
- Project NANDA
- There is a ton of work going on in very different places. I'm hoping to leave this day with a better sense of who is doing what
- Ongoing work at Project NANDA and other research initiatives
- Mapping who's working on what across the ecosystem
đ Recommended Reading
We ask attendees when they register for suggestions. Here are some recommended resources:
We ask attendees when they register for suggestions. Here are some recommended resources:
- A Survey of AI Agent Protocols
- On Being Agentic
- Upgrade or Switch: Do We Need a Next-Gen Trusted Architecture for the Internet of AI Agents?
- HTTP, APIs and identity articles at code.sgo.to
- WS-REST 2014 Keynote
- Collaboration vlog at collab101.org
- Bot or Not? Why Incentives Matter More Than Identity
- Roads, Robots, and Responsibility: Why Agentic AI Needs Identity Infrastructure
- AI Permissions vs. Human Permissions: What Really Changes?
- Articles at gluufederation.medium.com
- Draft OAuth AI Agents on Behalf of User
- The First Person Project White Paper at firstperson.network
- Email Verifications Protocol
đĄ Have a Topic to Add?
These topics will be discussed during the agenda creation in the opening circle. If you have additional topics you'd like to explore, bring them to the workshop and propose them during the agenda-setting session.
These topics will be discussed during the agenda creation in the opening circle. If you have additional topics you'd like to explore, bring them to the workshop and propose them during the agenda-setting session.