Search News You Can Use - SEO Podcast with Marie Haynes

AI protocols that marketers need to know about - with Liz Micik & Marie Haynes

Search News You Can Use - SEO Podcast with Marie Haynes

Show Notes

In this episode of the "Real People Using AI" series, host Marie Haynes sits down with SEO content strategist and AI transition consultant Liz Micik to discuss the massive shift from a chat-based internet to the "Agentic Web." They break down Google's latest developer protocols—including MCP, A2A, UCP, and AP2—and translate what these highly technical concepts mean for everyday business owners and marketers. If you are wondering how AI agents will discover, consume, and negotiate with your website in the future, and what actionable steps you can take right now to prepare your brand (like cleaning up your schema and structured data), this conversation is your roadmap.Google’s blog posts on the agentic protocols:https://developers.googleblog.com/developers-guide-to-ai-agent-protocols/Reach Liz Micik:https://lizmicik.com/Reach Marie:https://mariehaynes.com/contactThe Search Bar:https://mariehaynes/comBecome a member of Marie’s paid community:https://community.mariehaynes.com/collections/10503740:00 – Welcome to the Agentic Web: Moving beyond chat interfaces and GEO (Generative Engine Optimization) to prepare for AI agents.2:16 – The Evolution of the Web: Why the current shift mirrors the early days of e-commerce and how bots are consuming websites (discussing Cloudflare's markdown feature).11:00 – The 3 C's of AI Readiness: Why your website must be clear, complete, and consistent for AI agents to trust it.13:50 – What is MCP & WebMCP?: Exploring the Model Context Protocol and how AI applications connect to external systems and tools.25:20 – Agent to Agent Protocol (A2A): How agents discover and communicate with one another using JSON Agent Cards.27:50 – Universal Commerce Protocol (UCP): The future of AI shopping, building carts across multiple sites, and protecting your business's "moat."38:00 – Agent Payments (AP2) & MPP: How agents will handle transactions, negotiate payments, and the security hurdles of an agentic economy.46:15 – Actionable Advice for Businesses Today: Why Schema and Structured Data are the most important tools you can implement right now.52:00 – Agent to User Interface (A2UI): The potential for AI to generate unique web pages, UIs, and interactive tabs on the fly.56:50 – Summary & Rapid Fire Questions: A quick recap of all the protocols, plus Liz's advice on learning AI, financial planning with Claude, and the importance of reading analog books to kids.

More from Search News You Can Use - SEO Podcast with Marie Haynes

Jul 24, 2026

Google's latest earnings call reveals a massive shift in search and AI infrastructure. While Gemini 3.5 Pro is delayed, new Flash models are already changing how AI Overviews function and how agents interact with your data.

Jun 26, 2026

In my last video, I introduced the concept of Google's Open Knowledge Format (OKF). Today, I'm showing you exactly what I've built with it. I have created a personal brain that I use every day to automate complex SEO tasks, generate proposals, and analyze Google search updates. We walk through the structure of an OKF file, including the YAML frontmatter and how it differs from traditional RAG. If you want to make your data and processes agent-ready, my hope is that what I'm building will help you build your own OKF brain.Here's the first video on OKF: https://www.youtube.com/watch?v=MY9F9K7wWX4 To build something similar, give these links to your agent (Claude Code / Cowork, ChatGPT Codex or my favourite, Google's Antigravity) and try this prompt:"I want to build an OKF system similar to Marie's. Read these links and then give me some ideas of what this would look like. Then, ask me questions one at a time so that together, we can decide what we want to build:https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing/https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94fhttps://www.mariehaynes.com/okf/https://www.youtube.com/watch?v=MY9F9K7wWX4https://youtu.be/esYAIA6lU-s"

Jun 16, 2026

Google just announced the Open Knowledge Format (OKF), a new way to structure your knowledge for AI agents. This standard uses simple Markdown to make business and personal insights accessible to the agentic web. In this video, I break down why this changes SEO, how to build your first OKF bundle, and the potential for selling expert knowledge directly to AI systems.Google's blog post on okf:https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing/The Spec.md file for OKF on Github:https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.mdAndrej Karpathy's LLM-Wiki:https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94fJoin me in my community at the Search Bar:https://community.mariehaynes.comhttps://mariehaynes.com/join - for more on the paid areas.0:00 - Introduction to Google's Open Knowledge Format (OKF)1:03 - How OKF changes SEO and makes businesses accessible to AI agents1:43 - Selling proprietary knowledge and OKF bundles2:21 - How to use NotebookLM and Gemini to learn the new standard3:02 - What is OKF? (Markdown files and the LLM Wiki pattern)4:01 - Breaking down the OKF spec (Human and agent-friendly format)5:03 - Terminology: Creating "Knowledge Bundles" and directories5:51 - Structuring concepts as single Markdown files6:30 - Understanding YAML front matter (Type, title, descriptions, tags)7:18 - Formatting the body, citations, and cross-linking7:40 - Organizing files: Index files, log files, and using Git/Obsidian9:11 - Practical examples: BigQuery data vs. triggered Playbooks11:12 - Andre Karpathy’s LLM Wiki pattern explained13:48 - Letting the LLM write and maintain your knowledge wiki14:34 - Why OKF is the "new schema" and future revenue streams17:15 - How agents discover your OKF (llms.txt) and "Semantic Unbaking"

Jun 11, 2026

You can build an AI dashboard so easily - even if you don't know how to code! In this episode, Laura Tobin from the Search Bar community shares the incredible system of AI agents she built using Claude and Co-work. As a food blogger facing the shifts in AI changing Search, Laura decided to pivot from fighting the technology to using it to become a "one-person content machine."She walks us through her "Command Center," a custom dashboard that manages her entire workflow, from post pipelines to client shoots. We also discuss the "uncanny valley" of AI content and why her audience rejected AI avatars, teaching us a valuable lesson on where AI belongs in your business.The discussion following the webinar is so good. We share the different avenues we are exploring in building an AI brain. Where to connect with Laura Tobin:A free 30 minutes exploratory session:https://calendly.com/laura-tobinfooddigital/30minEmail:[email protected]'s Bloghttps://yourguardianchef.com/Laura's youtube channel:https://www.youtube.com/@yourguardianchefLaura's Instagram account:https://www.instagram.com/yourguardianchefJoin Marie's community, the Search Bar for real time Search and AI News:https://community.mariehaynes.com/Join the Search Bar Pro area so you can join our weekly meetings:https://www.mariehaynes.com/join/Timestamps: 0:01 - Introduction: Meet Laura and her Claude-powered content system.1:02 - Laura's Pivot: Becoming a one-person content machine after Google's update.3:03 - AI Video Testing: Why human authenticity still beats AI avatars.6:07 - System Setup: Centralizing goals and workflows into a "Second Brain."8:34 - The AI Team: Meet Laura's specific agents (Kiara, Francesca, Julia, Rosella).10:25 - Command Center: Walkthrough of her custom dashboard and time-tracking tool.13:48 - Social Batching: Automating schedules and building a reusable content bank.17:04 - Photography Days: Managing recipes, shoot schedules, and client quotes.19:30 - Results: How the system saves time and improves audience engagement.21:46 - Q&A: Moving assets to Google Drive and republishing YouTube Shorts.24:04 - Q&A: Using Claude Co-work and why Notion acts as the system's memory.28:20 - Global Instructions: Using .md files to run agents and saving token costs.32:46 - Getting Started: How Laura built it all without a coding background.36:13 - Choosing an App: Debating Notion, Craft, and Obsidian for data storage.41:06 - The Future: Discussing open-source agents and auto-building systems.46:37 - AI Goals: Using agents for task execution vs. life optimization.48:45 - Conclusion: Wrap-up and how to contact Laura for consulting.

Jun 3, 2026

Google has just released a major update to Search Console, providing website owners with dedicated performance reports for Generative AI features including AI Overviews, AI Mode, and Discover AI. In this video, I walk through where to find this new report, why impressions matter even without click data, and the new regulatory changes that forced Google's hand.

See all episodes →