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

Last Week in AI
Last Week in AI
GbyAI
GbyAI
Apple Machine Learning Research
Apple Machine Learning Research
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
N
Netflix TechBlog - Medium
量子位
aimingoo的专栏
aimingoo的专栏
D
Docker
F
Fortinet All Blogs
T
Tailwind CSS Blog
V
V2EX
D
DataBreaches.Net
Google DeepMind News
Google DeepMind News
MyScale Blog
MyScale Blog
G
Google Developers Blog
罗磊的独立博客
MongoDB | Blog
MongoDB | Blog
Microsoft Security Blog
Microsoft Security Blog
Microsoft Azure Blog
Microsoft Azure Blog
WordPress大学
WordPress大学
博客园 - 三生石上(FineUI控件)
小众软件
小众软件
A
About on SuperTechFans
IT之家
IT之家

Sanity.io

A Board Game agent built using Sanity Context and Vercel's AI SDK | Sanity Build a prototype with Claude Code that your whole team can edit | Sanity What’s New - May 2026 | Sanity I built a London pub guide with v0 and the Sanity MCP in six hours. Here's what I learned. | Sanity Build a conference concierge with Agent Context and Anthropic | Sanity Build a content-aware Telegram agent with Vercel AI SDK and Chat SDK | Sanity How I used Agent API to generate photos for my family’s recipes | Sanity What’s New April - 2026 | Sanity Better context, better matches: An AI love story (for dogs) | Sanity How to write for an agent | Sanity Content Agent, meet Slack: AI content operations in your workflow | Sanity Structure powers intelligence | Sanity Your agent needs better content. Here's how to give it. | Sanity How to serve content to agents (a field guide) | Sanity Sanity TypeGen GA: Automatic TypeScript types for content and GROQ | Sanity Sanity is now available on the Vercel Marketplace | Sanity The logo soup problem (and how to solve it) | Sanity Content Releases: From scattered updates to coordinated publishing | Sanity What's New - February 2026 | Sanity How we solved the agent memory problem | Sanity v0 Builder Challenge: The winners | Sanity Introducing: Sanity Agent Skills | Sanity Content Agent: Days of work in one conversation | Sanity Our Sanity Values | Sanity Open Source Pledge 2025: Stepping up when it matters | Sanity v0 builder challenge: $3000 in prizes | Sanity Why AI Breaks Without Structured Content Operations | Sanity What’s New January - 2026 | Sanity BFCM 2025: What teams built when infrastructure stopped being the problem | Sanity How AI shaped holiday shopping and what it means for content in 2026 | Sanity
Content Agent: AI that understands your structured conten...
Knut Melvær · 2025-10-22 · via Sanity.io

Content Agent is now generally available!

Picture this common Monday morning question:

Question from the CMO: How are competitors positioning their new AI features, and does our messaging still differentiate us?

Yesterday we had to: Research competitor sites. Screenshot relevant sections. Ping Sarah to query our marketing pages. Cross-reference manually. Write analysis. Schedule meeting to discuss findings. Get answers by Friday if you're lucky.

Today we can: Ask Content Agent. It researches the web, analyzes your content, identifies gaps and opportunities—all in one conversation in under a minute.

That's the difference between AI that needs your help and Content Agent, the AI that already knows your content.

Watch the 5 minute demo with Even and Evelina showing what you can do with the Content Agent.

Join the waitlist, or keep reading to see how it works.

An agent that already knows your content

Content Agent starts by reading how your content is organized:

  • The descriptions you wrote for each field
  • How documents connect to each other
  • What's required and what's optional
  • The structure that makes your content reusable
  • The semantic meaning of the content

Then it does what generic AI tools can't: it uses that understanding to answer questions, create documents, and validate content. Respecting your content model from the first prompt.

Ask "Show me blog posts about product launches" and it doesn't just keyword search. It:

  • Identifies posts with that has product launch-y content
  • Follows references to find which products launched
  • Reads your field descriptions to understand context
  • Returns results with the relationships intact

ChatGPT needs you to paste all this context. Content Agent already has it.

What you can do that you couldn't before

The magic isn't just prompting in natural language. It's what Content Agent can do that generic AI tools can't.

It understands how your content connect

Content Agent navigates your content like an experienced team member who knows exactly where everything lives. Ask for "blog posts about product launches," and it doesn't just search for keywords, it understands your content model and the meaning of your content.

It finds posts, identifies which ones reference products, follows those relationships to check launch dates, and even reads your field descriptions to understand the business context behind each piece.

This isn't pattern matching. It's comprehension of how your content connects, what each field means, and why those relationships matter to your organization.

It creates content ready to publish

Content Agent doesn't just read your content and it doesn't just generate text for you to copy and paste. It creates actual documents that match your content model perfectly, with proper references, correct field types, and valid structure throughout.

Generic AI tools give you unstructured text. Content Agent gives you production-ready drafts that fit seamlessly into your content workflow.

Ask it to "create a product launch announcement for our new feature," and the happy little helper generates a draft with all the right fields populated, references to related products linked correctly, and metadata structured exactly as your schema requires. Everything saves as a draft for your review, so you maintain full editorial control while eliminating the tedious structural work.

It works with image assets too

Content Agent understands that modern content isn't just text. It can transform images directly within your documents: adjust product photos to match variant colors, adapt visuals for different markets, or update imagery to match brand guidelines.

Our team's favorite proof? Asking it to add mullets to author photos:

Side-by-side comparison showing a profile photo update. On the left, a man with short, slicked-back hair and a trimmed beard against a blue background. On the right, the same man with a mullet hairstyle added, looking in the same direction, also against a blue background. The interface above shows document version history from August 28 to October 17 2025, indicating the avatar image was changed.
Proof that Content Agent understands 'business casual' is relative.

Beyond the fun, this shows AI that understands visual context and executes changes directly in your CMS. No export, edit, re-upload cycle.

It can research the web

Content Agent doesn't stop at your content boundaries. Ask "What's trending in our industry, and have we covered it?" and it researches the web, analyzes what it finds, then cross-references that intelligence with your existing content. All in one conversation.

This means you can identify content gaps, spot emerging topics before competitors, and understand how your coverage compares to industry conversations, without switching between research tools and your CMS. It's market intelligence that's immediately actionable within your content workflow.

These capabilities work together to transform how content teams operate. Research the web, analyze your content, create schema-valid drafts, transform images. All in natural language, all within your CMS. No context-switching, no copy-paste, no broken workflows.

It helps you work with developers

Content Agent bridges the gap between content teams and technical teams. Need to request a new field or suggest a schema change? It can analyze your current content model, explain how it's being used, and help you write clear, specific feature requests that developers can act on immediately.

And because Content Agent understands both Sanity's APIs and your specific setup, developers can use it too: to understand content patterns, validate changes, or explore how the content model is actually being used in practice. It becomes a shared language between teams.

Get early access and help us shape what's next

Content Agent works with your existing content immediately. No migration, no setup, no code required.

There are a few things that we haven’t rolled out in the Content Agent yet.

  • No delete operations. We're being careful.
  • No bulk operations yet. Coming soon.
  • Content Releases support is also being built. This will be a killer feature!

But it has plenty of utility already. Focused, intelligent help with the content work you do every day.

Why join now:

  • Shape the product before general availability
  • Get free access during private beta
  • Learn workflows that will become industry standard
  • Direct access to the team building it

What we need from you:

  • Real-world usage to understand patterns
  • Feedback on what works, what doesn't, what's missing
  • Ideas for the workflows you wish it could handle

Join the waitlist to get early access.

P.S. If you use Content Agent to add mullets or other fun hair styles, then share and tag us on LinkedIn. We might send you some swag from our new store.