惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

N
News and Events Feed by Topic
Malwarebytes
Malwarebytes
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
C
Cybersecurity and Infrastructure Security Agency CISA
F
Future of Privacy Forum
C
Cisco Blogs
T
The Exploit Database - CXSecurity.com
A
Arctic Wolf
S
Securelist
K
Kaspersky official blog
S
Schneier on Security
T
ThreatConnect
T
Tenable Blog
Spread Privacy
Spread Privacy
T
True Tiger Recordings
AWS News Blog
AWS News Blog
F
Fox-IT International blog
量子位
T
Threatpost
V
Vulnerabilities – Threatpost
C
CERT Recently Published Vulnerability Notes
Cisco Talos Blog
Cisco Talos Blog
GbyAI
GbyAI
宝玉的分享
宝玉的分享
腾讯CDC
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏
Cyberwarzone
Cyberwarzone
有赞技术团队
有赞技术团队
S
SegmentFault 最新的问题
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
V
Visual Studio Blog
U
Unit 42
雷峰网
雷峰网
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
Simon Willison's Weblog
Simon Willison's Weblog
O
OpenAI News
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
The GitHub Blog
The GitHub Blog
The Register - Security
The Register - Security
MyScale Blog
MyScale Blog
小众软件
小众软件
A
About on SuperTechFans
Last Week in AI
Last Week in AI
Y
Y Combinator Blog
博客园 - 三生石上(FineUI控件)
美团技术团队
Google Online Security Blog
Google Online Security Blog
P
Proofpoint News Feed
MongoDB | Blog
MongoDB | Blog

DEV Community

From Zero and Confused, This Is How I Started Learning to Code I Built a Local AI Gateway That Talks to Claude, ChatGPT, DeepSeek and Gemini — Without a Single API Key Bootstrapping with AI: Why Gemma 4 is the Micro-SaaS Founder’s Best Friend Google I/O 2026 Is One Uncanny F.R.I.E.N.D.S Group Upgrade The "MTTR Is All You Need" Trap The Quiet Revolution: How Firebase Became the First Agent-Native Backend at Google I/O 2026 I Built ResuMate! A 100% Private, Local AI Resume Optimizer with Google Gemma 4 Learning DirectX 12 - Part 2 Initialization Theory NeuralHats: I Put Edward de Bono’s Six Thinking Hats on Local LLMs Using Gemma 4 📝 Instant Auto Save Notes Engineering the "App-Like" Experience: A Deep Dive into PWA Architecture I built a local first AI CCTV assistant using Gemma 4 + Frigate CrowdShield AI — Smart Stadium Operating System & Crowd Intelligence Platform I built a free AI observability tool, prove your AI is useful, not just running Beyond Autocomplete: Why Google Antigravity 2.0 Changes the Rules for Indie Builders 터미널 AI 에이전트 구축 (v12) Building Instagram-Powered Apps with HikerAPI (Without Fighting Scrapers) Checkpoints, Not Transcripts: Rethinking AI Coding Agent Memory From Side Project to Student Savior: My AI PPT & Resume Tool Crossed 1.5K+ Users Why Story Points Don’t Work in the AI Era, And What Should Take Their Place Instead. Self-Hosted Document AI: How to Run Document Intelligence On Your Own Infrastructure (2026) How to Extract Tables from PDFs with AI: 4 Methods That Actually Work (2026) IDP vs OCR: What's the Difference — and Which Does Your Business Actually Need? Automated PII Detection and Redaction in Business Documents: A Practical Guide Human-in-the-Loop Document Review: When to Use It and How to Set It Up (2026) Document Processing Without RPA: A Modern Approach for Small Teams Reducto Alternative: When You Need More Than a Document Parser (2026) Hermes Agent vs LangChain vs CrewAI: When to Reach for Each SparshAI: I Built an Offline AI Tutor for Students Using Gemma 4 — Here's What Happened Building NeuroSense AI: A Human-Centered Stress Insight Assistant Powered by Gemma Why I Built a Privacy-First Dev Toolkit GAS Input Tags: Ability Activation Without Hardcoded Bindings AI Legal Document Advisor Supported By Gemm 4 Model Building Convertify in Public Week 10: PDF Cluster + Blog Launch CureNet AI: Decentralized Health Intelligence for India, Powered by Gemma 4 and ABHA Standardization When Open-Weights AI Meets a Broken Healthcare System: Deploying Gemma 4 in Rural India V.A.L.I.D. Google I/O 2026: The Year Google Stopped Building AI Assistants and Started Shipping AI Engineers Bondmap: AI-Powered Relationship Network That Maps How You're Connected to Everyone Using Gemma 4 Gemma 4 challenge inspired me to build my first app! 96. LoRA: Fine-Tune a Billion-Parameter Model on a Laptop From a Student Who Used CircuitVerse to a GSoC Contributor — My Community Bonding Story How Bf-Tree Keeps Mini-Pages Small, Hot, and Cheap to Evict I asked Claude to explain the chip war and ended up understanding modern geopolitics differently Stop Manually Checking for Server Updates: Automate With Email Notifications Nostalgia Meets Cybersecurity: Spotting Modern Scams in a Retro OS Simulator - Forward or Fraud CRACKING CODING INTERVIEW From Python to Production Pipeline :A Practical guide to Apache Airflow Antigravity 2.0: Google Just Changed What It Means to Be an Engineer I Built a Free Sticker Maker Because Every Other One Hid the Export How I bypassed Blazor WebAssembly's Virtual DOM using raw WASM pointers Distributed Tracing for LLM Agents: When MCP Makes Tool Calls Observable The Zero-Budget Memory Setup Behind My AI Agent Workflow No database. No framework. Just files, startup order, correction logs, and discipline. I Built an AI Second Brain with Gemma 4 The Most Exciting Google I/O 2026 Announcement for Me: HTML-in-Canvas CrisisLens: Compressing Disaster Scenes into 200-Byte Emergency Payloads with Gemma 4 I'm 15 and I built a todo app with Telegram Stars payments — only legal way for me to monetize before turning 18 Crypto Branding After the Token Launch Building an on-chain alerts bot in Python without any blockchain library FinePrint — An AI Pocket Lawyer That Decodes Predatory Contracts Using Gemma 4 How to Connect OpenAI with Supabase in 10 Minutes for a Lightning-Fast AI MVP One AI Gateway for AWS Bedrock, Google Vertex AI, Gemini, and Anthropic Reading Log #9 — Aoashi The Tacit Dimension Thinking, Fast and Slow Web3 Onboarding Is Not a Wallet Problem. It Is a Trust Problem. FHE Prompt Privacy: The Metadata Leak Your Demo Still Has Software Might Be Becoming Agent-Aware: What if software starts coordinating itself? The Silent Killers of Go Concurrency: Mutexes, Semaphores, and Goroutine Leaks Lynx framework first look Building Aries AI: A Solo-Built AI Abacus Tutor on OpenAI + Supabase + Render + Razorpay I built a paid Telegram bot. Here's what Telegram Stars actually pay. Transfer Fees, Metadata, and Soulbound Tokens: A Tour of Solana Token Extensions Improving AI resume matching with prompt iteration — 7.37 to 8.37/10 7 things you can do with Rogue Studio that no other AI IDE will let you do Why I Think WordPress Still Matters Reading Log #7 — Aoashi Guns, Germs, and Steel Distinction Open Models and the Sub-Saharan Region What 12 Months of AI-Generated Pull Requests Taught My Engineering Team Feature Flags in .NET 8: ASP.NET Core, Minimal APIs, Blazor The Quiet Architecture of Systems That Refuse to Die From OOP to SOLID: Everything You Need to Know in One Article I Scanned 5 Common LangChain Agent Patterns. Every Single One Was Over-Permissioned. Production-Ready MCP Servers in 60 Seconds (Auth, Rate Limits, Audit Logs Included) Dari OOP ke SOLID: Semua yang Perlu Kamu Tahu dalam Satu Artikel The Most Important Part of Google I/O 2026 Wasn’t a Model — It Was the Infrastructure When SafetyCo Goes to War: Anthropic, the DOD, and the Limits of Ideals-Based Frameworks Why AI Memory Resolves Too Much — And What to Preserve Instead What Gemma 4 Means for the Future of Local AI (And Why It Matters More Than GPT-5) The Classroom Gap: Why Applied AI Has Yet to Transform How the World Learns Cell-to-Sentence (C2S): LLM-Powered scRNA-seq Annotation with Gemma 4 GitHub rust-2026-template — my Rust starter in 2026 Stop Editing JSON by Hand How I Turned an Old Movie Recommendation Project Into a Cinematic AI Platform Linux Command Line: The 25 Commands I Use Every Day (2026) The Multilingual SEO Trap: When Your Meta Description Speaks the Wrong Language young-colleague-job-worries What I Learned About Token Design on Solana as a Web2 Developer 19/30 Days System Design Questions! My first Android App - NightLock Tabula vs Camelot vs pdfplumber in 2026: Which Python Library Actually Wins? AI Agent Failure Loops: When Persistence Becomes a Quality Bug
How Does an AI Agent Actually Buy Something? Google Just Published the Spec.
Lewis Sawe · 2026-05-25 · via DEV Community

This is a submission for the Google I/O Writing Challenge

Google I/O 2026 said the word "agent" more than any other noun across both keynotes. Agents that code. Agents that research. Agents that plan your day. The dev community wrote about Antigravity, Gemini Spark, managed agents, agentic search.

But here's what nobody asked: how does an AI agent actually buy something?

Not "recommend a product." Not "show a link." Actually complete a purchase. Add to cart, select shipping, pay, confirm. On behalf of a human, talking to a merchant's backend, without ever loading a webpage.

Google shipped the answer at I/O. It's called the Universal Commerce Protocol. Almost nobody in the developer community noticed.

The problem UCP solves

Today, when you ask an AI assistant to buy you running shoes, it shows you a link. You click it. You land on a website. You add to cart, enter your address, fumble with Google Pay, and check out yourself. The "agent" was just a search engine with better grammar.

That's not agentic commerce. That's a recommendation engine.

Real agentic commerce means the agent talks directly to the merchant's system, builds a cart, applies shipping, and completes the transaction. No browser. No webpage. No human clicking through a checkout flow.

The blocker was always: there's no standard way for an AI agent to interact with a store programmatically. Every store has a different checkout API (if they have one at all). Most stores don't have one. They have HTML forms.

UCP fixes this. It's a REST API specification that turns any online store into a service an AI agent can call.

What UCP actually is

Universal Commerce Protocol is an open standard, open-source on GitHub, co-designed by Google and Shopify. It defines how AI agents discover products, build carts, handle shipping, and complete checkout.

It's already live. If you use AI Mode in Google Search (which crossed 1 billion monthly users at I/O), you've seen UCP-powered "Buy on Google" buttons. Those aren't just links. They're agent-initiated checkout sessions running over this protocol.

The three-sentence version: A merchant implements three REST endpoints. Google's agent (or any agent) calls them to create, update, and complete checkout sessions. The merchant stays in control of pricing, inventory, and fulfillment. The agent never touches payment credentials.

The checkout flow, step by step

Here's how a purchase works when Gemini Spark (Google's personal agent) buys shoes for you:

1. Agent builds the session.
The agent calls POST /checkout-sessions with the product IDs and a partial shipping address (city, state, zip). The merchant responds with prices, tax estimates, and shipping options.

{
  "line_items": [
    { "item": { "id": "product_12345" }, "quantity": 1 }
  ],
  "fulfillment": {
    "methods": [{
      "type": "shipping",
      "destinations": [{
        "address_locality": "Sunnyvale",
        "address_region": "CA",
        "postal_code": "94089",
        "address_country": "US"
      }]
    }]
  }
}

Enter fullscreen mode Exit fullscreen mode

2. User reviews in a Google UI.
The agent hands control to a Google-rendered checkout page. The user sees the items, total, and shipping options. They select a payment method (Google Pay). The agent is not involved in this step. It never sees the credit card.

3. Google completes the session.
Once the user taps "Pay with GPay," Google calls POST /checkout-sessions/{id}/complete with the tokenized payment credential. The merchant processes the charge and returns an order confirmation.

That's it. Three endpoints: create, update, complete. A merchant who already has a checkout backend can implement this in a few days.

Why this matters more than another model announcement

Every I/O post I read this week talks about agents in the abstract. "Agents will change everything." "The agentic era is here." Cool. But an agent that can research and plan yet can't transact is just a chatbot with a longer context window.

Commerce is where agents become economically real. The moment an agent can spend money on your behalf (with your permission, within your budget), the business model for AI shifts from "subscription to a chat interface" to "commission on transactions completed." That's a different industry.

UCP is the plumbing that makes that shift possible. And the design choices are interesting:

The agent never handles payment. This is deliberate. The moment you hand sensitive data to an autonomous agent, you inherit liability nightmares. UCP sidesteps this by routing payment through a Google-controlled UI. The agent builds the cart. Humans authorize the money.

The merchant stays Merchant of Record. Google doesn't intermediate the transaction the way Amazon does. The merchant keeps their customer data, their relationship, their fulfillment. UCP is a protocol, not a marketplace.

It's compatible with MCP, A2A, and AP2. You can expose your checkout endpoints as MCP tools, use A2A for agent-to-agent negotiation, or plug into the Agent Payments Protocol. UCP doesn't lock you into Google's ecosystem. It defines the commerce primitives. The transport layer is your choice.

What this means if you build e-commerce

If you run a Shopify store, this is coming to you automatically. Shopify co-designed the protocol.

If you run a custom e-commerce backend, here's the integration surface:

  • POST /checkout-sessions (create a session from line items)
  • PUT /checkout-sessions/{id} (update shipping, recalculate tax)
  • POST /checkout-sessions/{id}/complete (process payment, return order)
  • POST /checkout-sessions/{id}/cancel (cancel)

Google provides Python and JavaScript SDKs, plus a conformance test suite to validate your implementation. The SLO expectations are reasonable: 95% availability, p50 latency under 1 second for session creation.

The payoff: your products become purchasable directly inside Google Search AI Mode, the Gemini app, and (soon) anywhere an agent speaks UCP. No affiliate links. No "visit our website." Direct checkout inside the AI conversation.

The part nobody is talking about

UCP is expanding to lodging and food. Google has waitlists open for both verticals. That means hotel booking and restaurant ordering get the same treatment: an agent calls your API, the user confirms in a Google UI, the transaction completes without a website visit.

Think about what this does to SEO-driven e-commerce. If an agent can buy directly from a merchant's API during a Search conversation, the website becomes optional for the transaction. Discovery still happens (through product feeds in Merchant Center), but the conversion doesn't require a click-through anymore.

That's a structural change to online commerce. Not "AI will change shopping someday." It's live, it has SDKs, and merchants are integrating right now.

The skeptic's questions

"Is this just Google capturing more of the transaction?"
They'd argue no, because the merchant stays Merchant of Record. But Google does control the surface (Search, Gemini) and the payment layer (Google Pay). Draw your own conclusions on where the power concentrates over time.

"Will other platforms adopt UCP?"
It's open-source and Shopify co-designed it. That's meaningful. Whether Amazon, Meta, or Apple adopt it or build their own competing protocol is the billion-dollar question. Interoperability with MCP and A2A suggests Google wants this to be a lingua franca, not a walled garden. Time will tell.

"Do consumers actually want agents buying things for them?"
Probably not yet for expensive purchases. But for replenishment (toothpaste, dog food, contacts), routine bookings (same hotel, same rental car), and low-stakes impulse buys? The friction reduction is real. Google's Gemini Spark starts with a "check with you before taking major actions" guardrail for a reason.

Try it yourself

  1. Read the UCP documentation
  2. Browse the open-source spec on GitHub
  3. Grab the Python SDK or JS SDK
  4. Run the conformance tests against your endpoints
  5. Join the waitlist if you're a merchant

The protocol that lets AI agents spend money exists, is open, and is already processing transactions in Google Search. That's not a keynote prediction. It's infrastructure you can build on today.