Knowledge & retrieval

Your knowledge. In the conversation.

Ingest documents and URLs, then retrieve relevant content for an agent or application.

Your knowledge. Right on hand.

Make your product information, policies and reference material available as searchable sources. The Knowledge API turns content into a retrieval layer for your application.

Interactive example No live actions

Knowledge example

Example source / A product care guide

Step 1 of 3 / Source

Inside Knowledge & retrieval

Open a capability to read how it works.

Add useful sources

Ingest supported text, URLs and PDFs into the vector Knowledge API. Associate each source with the bot it belongs to.

Search by meaning

Retrieve relevant chunks with semantic search rather than requiring an exact keyword match.

Keep context scoped

Use workspace-scoped retrieval and a bot filter when looking up sources for a specific agent.

Manage the source material

Review ingestion state and manage sources as information changes. Use retrieved passages as context rather than treating an upload as proof of a correct answer.

Open Knowledge & retrieval

Make your
first connection.

Read the documentation

1
Choose the bot and gather the documents or URLs it should reference.
2
Ingest the sources through the Knowledge API and check their processing state.
3
Test representative searches and configure the agent to use the relevant knowledge.

Browse all products

AI agent builder

Give your agent instructions, knowledge and tools, then configure it for its channel.

Tools & automations

Connect agents to your business tools, calendars, custom APIs and MCP servers.

Web search

Retrieve web results through the API and make current information available to supported agents.