All articles on the site that touch AI agents
The AI agent is the through-line of Google I/O 2026 — broader than any single macro-area because it cuts across shopping, development, work, infrastructure, web, and personal assistance. Under this tag you find every article on the site that directly engages the agentic dimension, from platforms to build them to ready-to-use vertical instances.
What Google showed last year as Workspace Flows in alpha is becoming Workspace Studio, generally available across all Business and Enterprise plans. Describe a workflow in plain words, Gemini 3 writes, edits and monitors it from inside Gmail, Chat and Drive.
Google Maps Platform brings into Experimental a toolkit that gives AI agents what they have been missing: a visual voice. When the user's question has a spatial component, the agent no longer answers in text but generates a grounded, interactive map in real time.
Google repositions Cloud Run as a runtime platform for AI agents. Managed MCP servers GA, NVIDIA RTX PRO 6000 Blackwell support for 70B+ parameter models, integrated ephemeral sandboxes: the message is that production-grade infrastructure for agents has to scale to zero, not inflate the bill.
At I/O 2026 DeepMind updates the status of CodeMender, the Gemini Deep Think-based security agent that doesn't just find vulnerabilities but rewrites code to eliminate them. In six months it has already upstreamed 72 fixes to open source projects.
Behind Universal Cart there is a more ambitious piece of infrastructure. At I/O 2026 Google published the Universal Commerce Protocol (UCP), an open-source standard co-developed with Shopify, Etsy, Wayfair, Target, Amazon, Walmart and Meta. Its job is to give AI agents a common language to read catalogs, manage carts and complete checkouts. Consumers see it as Universal Cart; for merchants, the adoption work starts now.
At I/O 2026 Google brings Gemini 3 inside Chrome with a new side panel and an agentic feature called Auto Browse. It compares products across two tabs in parallel, fills forms reading data from a PDF, runs multi-step research, and always pauses before checkout or sign-in. Available now to US AI Pro and Ultra subscribers. Chrome for Android joins in late June, with Gemini Spark integration coming in the fall.
Spark won't be an island: Google confirmed at I/O 2026 that the 24/7 personal agent will use Anthropic's Model Context Protocol to talk to 30-plus external services. The first live integrations are Canva, Instacart and OpenTable. Adobe, Asana, Dropbox, Lyft, Uber, Zillow, Zocdoc and Shopify follow in the coming weeks.
Google Labs expands Pomelli with an agent that defines your brand DNA and auto-generates brand books and full websites. Aimed at SMBs, available now on labs.google.
At I/O 2026 Stitch — the Google Labs tool launched last year as a text-to-UI generator — turns into an agentic platform. You describe by voice or text, the Stitch Agent builds and re-flows the interface in streaming, and export goes straight into Antigravity or Netlify.
At I/O 2026 Google showed the next generation of Jules, its async development agent, under the internal name Project Jitro. The paradigm shifts: you don't tell it what to do step by step, you tell it where you want to land — test coverage, latency, accessibility — and the agent finds the path.
Fifteen updates from the developer keynote. The two most concrete for practitioners: Chrome DevTools exposes console and network to AI agents, and the Soft Navigations API in Chrome 150 finally closes the long-standing gap in performance metrics for single-page applications.
Hypothesis Generation, Computational Discovery and Literature Insights. DeepMind, Research, Cloud and Labs assemble a research toolkit, wired into 30+ life-science databases through Antigravity.
Google's Agent Development Kit jumps to 2.0 with a unified graph-based engine that gives developers a slider between dynamic model reasoning and deterministic workflows. Multi-Agent Collaboration, human-in-the-loop, retries and nested workflows become runtime primitives.
Google is bringing inside the Gemini API what used to be reserved for Antigravity: an agent that reasons, uses tools and runs code in an isolated Linux sandbox, configurable through markdown files like AGENTS.md and SKILL.md. No more hand-rolled orchestration.
With an origin trial in Chrome 149 and native support coming to Gemini in Chrome, WebMCP aims to bridge AI agents and websites through structured JavaScript functions and HTML forms. Booking.com, Expedia, Instacart, Intuit, Shopify and Redfin are among the first to try it.
A single cart across Search, Gemini, YouTube, and Gmail. Add a product and Gemini starts hunting for deals, tracking price history, and alerting you when it's back in stock. US rollout this summer.
The most-seen search box in the world gets a redesign. It expands as you type, accepts text, images, files, and video, and anticipates intent with suggestions that go beyond autocomplete. Search agents are coming too.
Google turns Antigravity into an agentic development suite: desktop app, parallel agent orchestration, persistent sandboxed Linux environments in the APIs. And announces the transition of Gemini CLI to Antigravity CLI.
Google makes two coordinated moves: Gemini Spark, a 24/7 personal agent, and Android Halo, the indicator that shows at the top of the screen what it's doing. An explicit response to the agent transparency problem.