AI translations that follow your terminology
Translate structured content field-by-field with Agent Actions. Preserve references, slugs, and schema integrity with human review.
Noah Gentile and 2 others
agent context
Marketing Bot
[ click to chat ]
status:
agent contextCurrent Context:learn, docs
status:enabled
agent context
Pricing Bot
[ click to chat ]
status:
Make agents work reliably
Agent Context
Ship agents that query your content with structured retrieval, not just semantic search. One call. Real-time.
Innovate
Ship experiences your users deserve
Ship experiences your users deserve
Shopping agents
"Find hiking boots under $200 in my size." Real products, retrieved and validated against live inventory. Increase CVR, reduce abandoned carts.
Technical support
"How do I reset my password?" Real answers from your docs, instantly. Deflect tickets, cut support costs.
Content discovery
Surface related content, find gaps, explore connections. Speed up teams without adding headcount.
Internal agents
Encode how your team works. Classify, route, and process content with the logic that used to live in people's heads.
AI workflows you can build today
Your AI is only as good as the content it operates on. These guides show how to build real AI workflows on structured content: working code, honest trade-offs, and a starter kit for each.
Context means accuracy
Context means accuracy
1
Customer asks a question
"Do you have hiking boots under $200 in size 10?"
2
Agent generates a query
Understands the question, knows your schema, combines strict checks (price < $200) with semantic search (relevant to hiking).
3
Sanity returns precise results
Products that match, are in stock, and meet all business rules. Real-time.
Real-time. Reliable. Governed.
Real-time. Reliable. Governed.
Real-time sync
Update a product or policy and agents know immediately. No reindexing. No drift.
Constraints that work
Agents can't recommend what you don't sell. Business rules enforced in the query response, not the prompt.
Editorial control
Published content is agent-accessible. Drafts aren't. Internal stays internal.
GROQ + keyword match + semantic search = agents that obey real constraints.
What is Agent Context?
The building blocks
The building blocks
Semantic index
Turn it on, configure projections for which fields embed. No vector database to provision. No RAG pipeline to maintain. No reindexing schedule.
MCP endpoint
Any agent connects in one line. Claude, GPT, Gemini, or your own. They all see your structured content through a single endpoint.
GROQ + semantics
GROQ predicates narrow scope. Keyword match finds exact terms a specific SKU or API name. Embedding search handles conceptual queries.
Built for builders
Built for builders
Five minutes to a grounded agent.
npx skills add sanity-io/agent-context --all
The setup skill reads your schema, asks a few questions, and scaffolds a working agent against your live dataset. No infrastructure to provision. No pipeline to maintain.
The agent backend for structured content
Agent Context gives your agents the retrieval layer to use it, with the governance your team already built in.
