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

小众软件
小众软件
V
Visual Studio Blog
博客园 - 三生石上(FineUI控件)
Last Week in AI
Last Week in AI
Blog — PlanetScale
Blog — PlanetScale
爱范儿
爱范儿
J
Java Code Geeks
A
About on SuperTechFans
F
Fortinet All Blogs
B
Blog
aimingoo的专栏
aimingoo的专栏
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Engineering at Meta
Engineering at Meta
Y
Y Combinator Blog
有赞技术团队
有赞技术团队
G
Google Developers Blog
Apple Machine Learning Research
Apple Machine Learning Research
V
V2EX
博客园_首页
博客园 - 叶小钗
罗磊的独立博客
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
D
Docker
云风的 BLOG
云风的 BLOG

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
Agentic eCommerce with Shopify and Sanity
Jono · 2026-06-18 · via DEV Community

Turbo Start Aisle is our agentic e-commerce starter on Shopify and Sanity. Instead of filters and category pages, you chat with an agent that builds the shopping UI as you go, narrowing by brand, size, and colour, and answering questions like the return policy in plain language. In the video I shop for tea and let the agent do the filtering.


FAQs

What is agentic e-commerce?

It's a way for customers to interact with your store by talking to an AI agent instead of clicking through filters and category menus. You ask for what you want in plain language, whether that's a product, a size, a colour, a brand, or a policy question, and the agent answers in real time.

How do agents generate UI in e-commerce?

The agent reads your request and renders the matching products and options on the spot, rather than sending you to a pre-built category page. You see only what fits what you asked for.

Can I ask agents about product specifics like size and color?

Yes, that's most of what the demo does. Ask whether a product comes in a given size, colour, or brand and the agent checks inventory and shows what's in stock. It narrows things down through conversation instead of stacked filters.

What else can agentic e-commerce agents help with besides finding products?

More than product search. You can ask about returns, shipping, or warranties and get a plain-language answer, or ask anything else about how the store works.

How does this compare to traditional e-commerce filtering?

Traditional e-commerce makes you navigate categories and set the filters yourself. With an agent you describe what you need and it does the searching and filtering for you in the chat.

Is agentic e-commerce only for small websites?

We demoed it on a small store, but it suits large catalogues just as well. The more products and categories you have, the more an agent saves customers from hunting through menus.

How do I try agentic e-commerce?

We built Turbo Start Aisle on Shopify and Sanity as a working example. Open the chat, describe what you want, and the agent helps you narrow it down.


Transcript

Hey, how's it going? Today I'm going to talk about Agentic e-commerce, what it means, and how it's going to completely shape the way users interact with your e-commerce website. In today's example, I will show you how the agents will work to generate UI on the fly and it would be completely the opposite of the traditional way of using filters and categories in your e-commerce website. So let's have a look.

Okay, so I'm going to try to find a tea for myself. And I'm at Turbo at Isle, which is Robboto's e-commerce website built with Shopify and Sanity. So let's go to the chat. And I'm going to first of all find out what brands they have. Oh, great. So they have Robboto. Perfect. That's the top end of my budget. 50 quid tea is still quite expensive. Oh, thank God they have three options. Great. Do you have any in small? Oh, amazing. Do you have in small and pink? Pink, not whatever I typed. Oh, great. So let's have a look. Okay, so they have Tazmin in pink and in my size. So this is a great example of just showing how you would interact with agents in an e-commerce website.

You can also probably find out what the policy is like, return policy. So, um, explain written policy to me like I am a two-year-old. Okay, so that's pretty straightforward. So this is one example of how you would interact with agents in your e-commerce website. Obviously you can do it in many different ways and Turbo at Isle is a very, you know, small website with some products and categories. But if it's a large e-commerce, the world is your oyster. Go crazy with it. Hope you enjoyed today's video. Thank you so much for watching.