The implications are profound. When AI agents can natively interact with any website through structured APIs instead of brittle DOM parsing, it fundamentally changes what's possible. Agent Experience Optimization isn't just a buzzword—it's the next competitive frontier.
Google and Microsoft just co-authored the spec that turns every website into an API for AI agents. The second-order effects here are massive.
Right now, browser agents work by taking screenshots, parsing the DOM, and guessing which buttons to click. It works about as well as you’d expect. Fragile, expensive, slow. WebMCP replaces all of that with a single browser API: navigator.modelContext. Websites register structured tools directly in client-side JavaScript. The agent reads a menu of available actions, calls them, gets structured data back. No scraping. No backend MCP server in Python or Node. The tools run inside the browser tab and share the user’s existing auth session.
Early benchmarks show ~67% reduction in computational overhead compared to visual agent-browser interactions. Task accuracy around 98%.
The second-order effect is where this gets wild. Today, when a browser agent visits two competing airline sites, it’s guessing at both interfaces equally. Once WebMCP adoption spreads, the site that exposes structured tools gives the agent a clean, reliable path to complete the task. The site that doesn’t forces the agent to fumble through the UI. Agents will prefer the cheaper path. Every time.
This means “Agent Experience Optimization” becomes a real discipline. Tool naming, schema design, description quality. Sound familiar? It’s the same shift that happened when meta descriptions and structured data became optimization surfaces for search engines. Except this time, the traffic source isn’t Google’s crawler. It’s every AI agent on the internet.
Bots already make up 51% of web traffic. Google just gave them a front door.
Getting AI policy right is essential. At @IQSourceAI, we help enterprises adopt AI safely—modernizing legacy systems, building intelligent solutions. Policy frameworks that promote safe AI integration will accelerate digital transformation across industries.
AI is being adopted faster than any technology in history. The window to get policy right is closing.
Today we’re contributing $20m to Public First Action, a new bipartisan org that will mobilize people and politicians who understand what’s at stake.
https://t.co/y9ZQNQ1Q8W
@AnthropicAI $30B at $380B valuation reflects AI safety's critical role in enterprise adoption. Investing in research depth while scaling infrastructure shows the right priorities for long-term trust and market leadership.
@AnthropicAI@codepath This is a significant move for AI accessibility in higher education. Bringing Claude to 20K+ students across community colleges, state schools, and HBCUs levels the playing field. Building AI literacy early will be essential for students navigating an AI-augmented workforce.
@EytanStarkman@RicardoIQSource We use @claudeai every day in our work for coding, financials, generating reports and documents. It's an incredible tool to help our customers and ourselves be more efficient
@tbpn@djpersia Such an important point: the hard part isn’t getting code to run once, it’s keeping it reliable over time. That’s where real engineering discipline (and good platforms) matter.
Gran recordatorio de @djpersia: el reto no es codear, es operar y mantener en producción. En https://t.co/8LYRSyiByb vemos a muchos equipos subestimar ese costo. Construye solo donde te diferencias y apóyate en buenas plataformas para el resto.
Databricks’ @djpersia says anyone claiming you can just vibe code any software you need isn’t actually in the business of using software in production.
“Build is easy - maintaining and sustaining it is hard.”
“If I can, I’d much rather buy than build.”
“For things like my CRM - that is not something that, if I can help it, I’m looking to build internally. I’m happy to use something externally, given that I imagine my needs are similar to many other ones, and there should be things that could meet those needs pretty quickly.”
@AnthropicAI lanzó Fast Mode para @claudeai Opus 4.6 — 2.5x más rápido. Estamos usándolo para acelerar entregas a clientes: transformación digital, desarrollo IA, modernización legacy y más.
Nos mantenemos al día para que nuestros clientes no tengan que hacerlo. 🚀