Earlier this month, I was laid off from my job as senior editor at The New Stack. While I figure out what’s next, I resolved to dive into a technology stack I’ve been deeply interested in for a while: Web AI. Only this time not just writing about these technologies, but building apps with them too.
In my next article, I’ll explain how I built my first Web AI experiment: an AI chatbot for my personal website called “Ask Ricmac” (which you can test by clicking that link — I’m still pecking away at it). Ask Ricmac was developed using the WordPress MCP Adapter and Claude Desktop during development, and deployed as a Cloudflare Workers app using Vectorize, D1, and Workers AI.
Before I publish that post, I’d like to set the context for what Web AI is and why I’m so excited about it. Frankly, I have no idea if I can earn a living from practicing Web AI, but I know for sure that I can build some really cool things with it. So I’ll start there.
What is Web AI and why does it matter?
I was the first writer at The New Stack to regularly report on what’s now called AI engineering. I reported from an AI conference in London in 2022, before ChatGPT was even launched. Then I attended the first AI Engineer Summit in San Francisco in 2023, in the first flush of the AI hype wave initiated by ChatGPT. But that’s just what I do: explore what’s next in technology before it truly takes off (if it ever does — cough, metaverse!).
So I enjoyed writing about AI engineering, but it wasn’t until 2025 — not coincidentally, the year that agents became a huge trend — that I began to see a really interesting web angle to the AI development trend. I realized that AI models could, and should, be symbiotic with websites and web applications. Yes, there are fundamental issues with AI — the fact that it takes content from people like me for free, without any compensation, and the environmental concerns about AI data centers. But it’s also undeniably a technology that can augment websites and web applications; and so I think web publishers and operators should lean into that.
This realization spurred me to research and do interviews with the people who were creating new products, protocols and standards at the intersection of AI and the Web; including from leading tech companies like Google, Microsoft, Vercel and Shopify. Incidentally, the term “Web AI” derives from Google — see my recent interview with Google’s Jason Mayes, who runs the Google Web AI Summit, for that background.
I quickly became fascinated with all the latest “Web AI” technologies, such as WebMCP, MCP Apps, MCP-UI, OpenAI’s Apps SDK, Google’s A2UI, and more. You’ll notice that MCP — the Model Context Protocol — is part of the name for some of these new technologies. That’s because MCP is a key connective protocol between AI agents and the Web. It allows agents to access web content, tools and services in a structured way.
I’ve also become extremely interested in on-device AI, using web browser technologies like LiteRT.js (a JavaScript runtime for running AI models in the browser using WebGPU) and Chrome’s built-in AI APIs, which provide access to on-device models like Gemini Nano.
Over the coming months, I’ll be testing and developing with all these different Web AI technologies. That will allow me to ascertain the strengths and weaknesses of each Web AI component, and their use cases.
The Web AI stack
For now, I’ve taken a stab at a high-level overview of the Web AI stack. But this is a work-in-progress, so leave a comment on this post or tag me on Mastodon, Bluesky or LinkedIn if you have ideas to improve it. (Note: I did ask ChatGPT to help me refine this.)
APPLICATION LAYER
- User interfaces
- Web browsers
- Browser extensions
- Chatbots
- AI-powered web apps
- Application frameworks
- OpenAI Apps SDK
- Google A2UI
- MCP-UI
- MCP Apps
AGENT LAYER
- Agent frameworks
- OpenAI AgentKit and Agents SDK
- Anthropic Claude Agent SDK
- Google Agent Development Kit (ADK)
- LangChain
- Agent builders / platforms
- Google Vertex AI Agent Builder
- Custom agents
- Cloudflare Workers agents
- Node.js / Python agents
TOOL & PROTOCOL LAYER
- Core protocols
- Model Context Protocol (MCP)
- WebMCP
- NLWeb
- Agent2Agent (A2A)
- Tool access mechanisms
- MCP adapters (e.g. WordPress MCP adapter)
AI RUNTIME LAYER
- Cloud inference (e.g. Cloudflare Workers AI)
- On-device inference runtimes (e.g. LiteRT.js)
- Browser AI runtimes (e.g. Chrome built-in AI APIs)
KNOWLEDGE LAYER
- CMS (WordPress, Drupal)
- Vector DB (e.g. Vectorize)
- Databases (e.g. D1, PostgreSQL)
MODEL LAYER
- GPT
- Claude
- Gemini
- Gemini Nano
- Llama
Web relevance for each layer
The application layer is where a lot of the innovation has happened over the past year in Web AI. It was MCP-UI that first caught my attention last year, because it brought web technology into chatbots — in the form of sandboxed iframes. MCP-UI eventually turned into MCP Apps, which is carrying that work forward. OpenAI, Google, Anthropic and others are all working hard to define this layer.
The agent layer is, of course, the most hyped layer currently. Since it’s not inherently tied to the Web, I won’t focus on it as much as some of the other layers. At least initially.
The tools and protocol layer is where a lot of the most interesting action is happening in Web AI right now. Underpinning a lot of it is the Model Context Protocol (MCP), which I noted above is a critical protocol. But for the Web specifically, I think WebMCP holds the most promise — it basically allows websites to expose their capabilities and content in a structured form that agents can discover and use. So it gives a lot of power back to web publishers and operators, which is a welcome development.
The AI runtime layer is where a lot of deep technical work is happening to make the web platform a first-class citizen of AI inference.
The knowledge layer is mature from a web perspective, but AI-native integrations into CMS platforms are still emerging. However, I have been closely tracking the progress of the two most prominent open source CMSs: WordPress and Drupal.
My final post for TNS ended up being about Drupal CMS 2.0, which I described as “a return to the simpler Drupal CMS product of yore and a response to the current trend of vibe coding.” It’s basically a less complex Drupal that includes AI functionality, such as Drupal Canvas to help build user interfaces.
WordPress has also jumped on the AI bandwagon with the release earlier this month of WordPress MCP Adapter, which “implements the Model Context Protocol in the scope of a WordPress site and lets AI tools (like Claude Desktop, Claude Code, Cursor, and VS Code) discover and call WordPress Abilities directly.” I’ll go into this in detail in my next post, as I used the MCP Adapter to integrate Ask Ricmac into this website (ricmac.org is a WordPress site).
In the meantime, let me know in the comments or on social media if you have any feedback on this post about the Web AI stack!