Creating a context layer between enterprise data stores and AI agents is a custom job, with no standard service to automate or maintain graphs over time. Amazon is making a direct play to change that.
Amazon entered the space on Wednesday, announcing a series of three products that it is positioning as a contextual intelligence stack for AI agents. The centerpiece is AWS Context, a new knowledge graph service that gets smarter by using agents over time. AWS also announced the general availability of Amazon S3 Annotations and a preview of skills assets in AWS Glue Data Catalog.
The context layer is now a controversial architectural category with no shortage of options from different vendors. AWS is entering that market with a different architectural premise: that the graph should learn from how agents use it automatically, without the need for human retrieval.
"Your agents now become smarter without you having to rebuild anything from scratch." said Swami Sivasubramanian, vice president of Agentic AI at AWS, during his keynote speech at AWS Summit NYC.
"This service automatically creates a knowledge graph from all your existing data." said. "This service infers relationships between your data sets, business rules, and domain knowledge, and makes it all available to your agents and organization at runtime."
AWS Context creates a self-learning knowledge graph from existing data
It’s an issue AWS says it has seen repeatedly in customer deployments.
AWS Context automatically maps relationships between existing data: what tables exist, what the columns mean, how sources are related, and which sources are authoritative. It combines semantic search with graph-level reasoning and infers relationships between data sets, business rules, and domain knowledge, making it all available to agents at runtime.
"The knowledge graph improves over time as it learns which sources produce correct results and which parts are used." said Sivasubramanian.
Data stewards manage the graph through the AWS Management Console, review inferred relationships, promote them to production, and attach business definitions and usage rules. Each query inherits the IAM and Lake Formation permissions of the calling user, making access to agent data auditable by identity through controls that businesses already rely on.
All metadata is published in Apache Iceberg format to Amazon S3 tables and can be queried through Athena, Redshift, Spark, or any Iceberg-compatible engine, without proprietary APIs. Third-party catalog connections are supported, so context from systems outside of AWS can be extracted into the same graph. Agents perform queries through Agent Search APIs and MCP tools in Bedrock AgentCore, EKS, or any MCP-compatible framework.
Context is more than just a service
Context is a complicated space and AWS is layering multiple services to help businesses create context across the data stack.
Amazon S3 Annotations. This service allows users to attach rich business context at the storage layer, directly to individual S3 objects.
AWS Glue Data Catalog Skill Assets. Glue skill assets attach domain knowledge at the catalog layer, linking runbooks, query patterns, and usage rules to data assets across the estate.
AWS Context then synthesizes both into the knowledge graph that agents query at runtime, combining semantic search with graph-level reasoning across structured and unstructured sources. Each layer feeds the next.
AWS is entering a highly competitive context space
Snowflake announced its context approach earlier this month with its Horizon Context and Cortex Sense services. Microsoft provides context through its Fabric IQ Platform which provides a semantic ontology for the data. Redis has developed a context platform that optimizes data for recovery. The vector database provider Pinecone has its Nexus Context Offer that compiles business data into task-specific artifacts before agents query them.
AWS’s structural argument is simple: for enterprises already running S3, Glue, and Lake Formation, AWS Context extends an existing identity model without requiring data movement. The argument is zero integration friction, not just cost consolidation.
"Context makes agents more powerful, and since everyone is building agents, every agent platform provider needs a context capability," Holger Mueller, vice president and principal analyst at Constellation Research, told VentureBeat.
Mueller noted that AWS is no exception. "The concern, as with all context offerings, will be performance, especially for transactional data, as we will see." said.
