Context Layer Public Preview

Create a unified context layer that AI agents and assistants can use to answer questions about your business accurately.

Overview

AI agents need context to answer questions about your data. While table and column names describe the data's structure in your warehouse, agents also need to understand your business definitions, how metrics are calculated, and how information relates across your organization.

Fivetran Context Layer connects your organization's documentation sources, systems of record, and analytical sources to build a unified context layer in your Fivetran destination. It models source data, parses documents, builds search indexes, and extracts metadata. It uses this context to build a knowledge graph that maps the entities in your data and their relationships. Your AI agents and assistants can then use that context layer to answer questions based on your actual data, rather than guessing from the schema alone.

Instead of re-configuring context for each of your AI agents separately, Context Layer allows you to connect multiple agents to a single context layer. Once it's built, explore the Context Layer in the built-in playground to confirm it responds accurately before connecting it to your organization's AI agents.

How it works

To build a context layer, we perform the following steps:

1. Select your data: Choose the destination and datasets you want Context Layer to run queries over.
2. (Optional) Connect your sources: Add your organization's documentation sources (business definitions, policies, and operational records), systems of record (operational facts behind your data), and/or analytical sources (such as Power BI, Sigma Computing, or Hex). While Context Layer does not require connecting to a data source, we recommend connecting at least one of each source type for better answer quality.
3. Build the context layer: Review your inputs and start the build. During the build, Fivetran processes your selected data and metadata, then creates and populates the AGENTS schema in your destination with the resulting context. Building a context layer typically takes about a day to complete.
4. Review the organization fingerprint: After the build completes, review the organization fingerprint and the assets connected to your context layer.
5. Explore in the playground: Test the context layer with sample questions to confirm it responds accurately before rolling it out.
6. Install in your AI client: Connect the context layer to your organization's AI coding or chat tools. Learn more in the Connect your AI agents section.

For more information, see the Context Layer Setup FAQ.

Agents Schema

Agents Schema is an open-source standard for storing context about your data in your warehouse. Fivetran builds and populates the AGENTS schema in your warehouse, which acts as a map to help AI agents navigate, interpret, and act on your data. Learn more in the Agents Schema documentation.

Connect your AI agents

You can connect your AI agents to your Context Layer either through Agent Context MCP or directly to your warehouse. Agent Context MCP simplifies setup by allowing you to connect all your AI tools to a single interface. Connecting each tool to your warehouse gives you more control over access.

Agent Context MCP

You connect your AI agents to Agent Context MCP, a governed interface that uses the MCP to expose your context layer to all your AI agents at once. Learn more in the Agent Context MCP setup FAQ.

Connect directly to the warehouse

You connect each of your AI agents to your warehouse individually, then configure them to discover context through AGENTS.ROOT. Learn more in the Connect directly to the warehouse setup FAQ.

Included services

Context Layer includes the following services, which work together to build an open context layer in your destination:

• Metadata connectors: Ingest metadata and context from semantic layers and data sources.
• Context Catalog: Discover concepts and ontology from metadata sources, wikis, warehouse usage, and more, in a unified view.
• Context Layer-ready data connectors: Prepare your data for use by Context Layer through document parsing, which prepares unstructured data for AI retrieval, and search indexing, which provides search capabilities across applications.
• Agents Schema: A unified view of the context produced by the above services that helps AI navigate all entities in your destination accurately and efficiently.

Prerequisites

Your Fivetran account must meet the following requirements to see and use Context Layer in the Fivetran dashboard:

Once you start the setup flow, you must also connect a destination that meets the following requirements before you can build your context layer:

Context Layer is built on the datasets you select in your destination, so connecting data sources is optional. However, we recommend connecting at least one of each of the following source types for better answer quality. We support the following data sources:

Usage limits

During Public Preview, Context Layer enforces the following usage limits:

Additional support

If you have questions about Context Layer or need help building your context layer, contact Fivetran Support.