{"version":"1.0","type":"rich","provider_name":"Acast","provider_url":"https://acast.com","height":250,"width":700,"html":"<iframe src=\"https://embed.acast.com/$/655148df2861630012a1d01b/6826da01ee813e8be20957fb?\" frameBorder=\"0\" width=\"700\" height=\"250\"></iframe>","title":"Sean Roberts: How to create better UX with AI Agent Experience (AX)","thumbnail_width":200,"thumbnail_height":200,"thumbnail_url":"https://open-images.acast.com/shows/655148df2861630012a1d01b/1747376593437-85bcce9b-30f6-461b-a5d6-0d95c0796b88.jpeg?height=200","description":"<p>Links</p><p>- Codecrafters (sponsor): https://tej.as/codecrafters</p><p>- Agent Experience: https://agentexperience.ax</p><p>- Arrazo: https://spec.openapis.org/arazzo/latest.html</p><p>- Netlify: https://netlify.com</p><p>- Sean on X: https://x.com/JavaSquip</p><p>- Tejas on X: https://x.com/tejaskumar_</p><p><br></p><p>Summary</p><p><br></p><p>This episode dives deep into the emerging field of Agent Experience (AX), exploring how software agents, including LLMs, will interact with the web and online services. The conversation highlights the distinction between the \"human web\" and the \"agent web,\" emphasizing the need for new approaches to ensure agents can effectively understand context and execute tasks.</p><p><br></p><p>Key topics include contextual alignment protocols like MCP (Machine Context Protocol), and standards such as `llms.txt` and `agents.json`, alongside efforts like Arrazo, which aim to provide structured information and enable complex workflows for agents. A significant portion of the discussion focuses on the challenges of authentication for agents, moving beyond human-in-the-loop processes and complex systems like OAuth2 towards more agent-friendly, secure, and auditable solutions, possibly involving dedicated agent user identities.</p><p><br></p><p>The dialogue also covers practical considerations like providing data to LLMs efficiently, the importance of API accessibility for agents, and the need for businesses to adapt to this new paradigm of interaction. Finally, the conversation underscores that AX is a rapidly evolving area, transitioning from theoretical concepts to practical applications, with a strong call for community collaboration to develop best practices and robust solutions for the future of agent-driven web interactions.</p><p><br></p><p>Chapters</p><p><br></p><p>00:00 Intro</p><p>03:35 Exploring Agent Experience (AX) and Its Importance</p><p>06:23 Understanding the Role of Model Context Protocol (MCP)</p><p>09:22 The Principles of Great Agent Experience</p><p>12:24 Agent Accessibility and Its Challenges</p><p>15:34 Contextual Alignment: Enhancing Agent Interaction</p><p>18:31 Human-Centric Design in Agent Experience</p><p>21:23 The Future of AI and Agent Experiences</p><p>24:25 Improving Human Accessibility Through Agentic Experiences</p><p>27:29 Primitives of Agent Accessibility</p><p>30:22 Avoiding Human in the Loop Patterns</p><p>33:19 Authentication in an Agentic World</p><p>38:34 Navigating API Token Strategies</p><p>43:30 Contextual Alignment: The Next Frontier</p><p>55:50 Understanding Agents vs. Bots</p><p>01:00:19 Optimizing Contextual Alignment for Agents</p><p>01:14:11 Understanding Website Infrastructure and Cost Implications</p><p>01:14:37 The Role of LLMs in Web Navigation</p><p>01:17:54 Quantifying ROI in Web Technologies</p><p>01:19:43 Introduction to Arazo and Workflow Management</p><p>01:24:26 Measuring Human vs. Agent Interaction</p><p>01:30:28 The Emergence of Agent Experience (AX)</p><p>01:38:09 Five Principles of Agent Experience (AX)</p><p><br></p>","author_name":"Tejas Kumar"}