Amazon Web Services has unveiled a new suite of products designed to bridge the gap between enterprise data stores and AI agents. At the center is AWS Context, a knowledge graph service that improves itself by observing how agents use it, eliminating the need for constant manual reconfiguration. The announcement came during the AWS Summit NYC, where Swami Sivasubramanian, vice president of Agentic AI at AWS, presented the solution as a major step forward in context management for enterprise AI.
The problem AWS aims to solve is well known. Today, building a context layer between enterprise data stores and AI agents is bespoke work, with no standard service to automate or maintain the knowledge graphs over time. AWS Context changes the game: the graph is automatically generated from existing data, inferring relationships across datasets, business rules, and domain knowledge. It is all available to agents at runtime, without requiring data movement.
Sponsored Protocol
An ecosystem of three services
The announcement goes beyond a single product. AWS introduced three components that together form a true context intelligence stack. The first is Amazon S3 Annotations, which allows users to attach rich business context at the storage layer directly to individual S3 objects. The second is AWS Glue Data Catalog skill assets, now in preview, which attaches domain knowledge at the catalog layer, linking runbooks, query patterns, and usage rules to data assets across the estate. Finally, AWS Context synthesizes both into a knowledge graph that agents query at runtime, combining semantic search with graph-level reasoning across structured and unstructured sources.
The self-learning graph
The uniqueness of AWS Context lies in its automatic learning capability. As Sivasubramanian explained, the knowledge graph improves itself over time as it learns which sources produce correct results and which parts get used. Data stewards can still manage the graph through the AWS Management Console, reviewing inferred relationships, promoting them to production, and attaching business definitions and usage rules. Every query inherits the calling user's IAM and Lake Formation permissions, making agent data access auditable by identity through controls enterprises already rely on.
Sponsored Protocol
A key aspect is the adherence to open standards: all metadata is published in Apache Iceberg format to Amazon S3 Tables, queryable via Athena, Redshift, Spark, or any Iceberg-compatible engine, with no proprietary APIs. Third-party catalog connections are supported, allowing context from systems outside AWS to be pulled into the same graph. Agents query through agentic search APIs and MCP tools across Bedrock AgentCore, EKS, or any MCP-compatible framework.
Sponsored Protocol
An increasingly crowded context race
AWS enters a highly competitive space. Snowflake recently launched Horizon Context and Cortex Sense services. Microsoft provides context via Fabric IQ with a semantic ontology. Redis has a context platform that optimizes data for retrieval. Vector database vendor Pinecone offers Nexus Context, which compiles enterprise data into task-specific artifacts before agents ever query them. AWS's structural argument is straightforward: for enterprises already running S3, Glue, and Lake Formation, AWS Context extends the existing identity model with no data movement required. The pitch is zero-integration friction, not just cost consolidation.
Challenges ahead
Holger Mueller, vice president and principal analyst at Constellation Research, told VentureBeat that context makes agents more powerful and that every agentic platform vendor will need a context capability. However, Mueller raised a critical point: performance, especially for transactional data, is the main concern. It remains to be seen how AWS will handle this.
Sponsored Protocol
For more on context in AI, check our article on Solar Geoengineering: The Engineering Challenge to Cool the Planet, which shows how complex technologies require integrated solutions. Another relevant piece is Facial Recognition for Refugees: Flawed Tech Is No Excuse, highlighting the importance of data quality. Also, see Entrepreneurs in Nairobi: Off-Grid Solar as a Driver of Development for context on renewable energy.
For an authoritative external source, refer to the Wikipedia page on knowledge graphs.
