What is AWS Context?
AWS Context is a service announced by AWS that automatically maps the relationships across an organisation’s existing data into a knowledge graph. Through agentic search, AI agents access governed data relationships, business rules, and domain knowledge at runtime.
AWS announced the service on 17 June 2026 at the AWS Summit in New York and lists it as coming soon. This page reflects the announced scope; for binding information on availability, Regions, and pricing, consult the official documentation.
Core Features
- Automatically built knowledge graph: Relationships across existing data sources are mapped without you modelling the graph by hand
- Agentic search: Agents query the graph through APIs and MCP tools without building custom retrieval pipelines
- Learning from usage: According to AWS the service observes which sources produce correct results, which join paths agents rely on, and which curated rules get applied
- Inherited permissions: Every call is designed to inherit the calling user’s IAM and Lake Formation permissions
- Open format: Key metadata from structured and unstructured sources is published into Apache Iceberg format in Amazon S3 Tables
- Integrations: AWS Glue Data Catalog, Amazon SageMaker Unified Studio, AWS Lake Formation, Amazon Bedrock AgentCore, and Amazon Quick
Typical Use Cases
Agents with enterprise context: AI agents gain access to data relationships and business rules instead of individual tables or documents alone.
Governance for agentic systems: Because calls inherit the calling user’s permissions, an agent’s access stays limited to the authorised subset.
Consolidating scattered data landscapes: Data lakes, data warehouses, lakehouses, databases, and streams are opened up through a shared context layer.
Connectivity without custom pipelines: Access through APIs and MCP tools replaces self-built retrieval paths.
Benefits
- Context for AI agents drawn from existing data sources rather than manually curated knowledge bases
- Permission checks based on IAM and AWS Lake Formation
- Metadata stored in an open format (Apache Iceberg in Amazon S3 Tables)
- Connects to existing AWS data and AI services
- Access through MCP tools, as used by other agent frameworks
Integration with innFactory
As an AWS Reseller, innFactory helps you prepare for AWS Context: taking stock of your data sources, building catalogue and governance structures in AWS Glue Data Catalog and AWS Lake Formation, and planning the architecture for agentic applications that will use the service once it is released.
Typical Use Cases
Frequently Asked Questions
What is AWS Context?
AWS Context is a service announced by AWS that automatically maps the relationships across your existing data into a knowledge graph and provides agentic search. AI agents in the organisation can use it to access governed data relationships, business rules, and domain knowledge at runtime.
Which problem does AWS Context address?
AWS describes the problem as context being scattered across data lakes, data warehouses, lakehouses, databases, and streams, and residing in institutional knowledge that has never been written down. AWS Context is intended to turn this into a unified foundation for agent decision-making.
How are permissions handled?
According to AWS, every call is designed to inherit the calling user's IAM and AWS Lake Formation permissions, so an agent can only see and traverse the relationships its identity is authorised to access.
In which format is the metadata stored?
Per the announcement, AWS Context publishes all key metadata from structured and unstructured sources into Apache Iceberg format in Amazon S3 Tables.
Which AWS services does AWS Context work with?
The announcement names the AWS Glue Data Catalog, Amazon SageMaker Unified Studio, AWS Lake Formation, Amazon Bedrock AgentCore, and Amazon Quick.
Is AWS Context available already?
No. AWS announced AWS Context on 17 June 2026 at the AWS Summit in New York and lists it as coming soon. No official information on availability, Regions, or pricing has been published yet; the official documentation is authoritative.
Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of AWS (official documentation). This page does not represent an offer by AWS.