Context intelligence for your data and AI agents at scale

2026-06-17 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Cloud Computing & IT Infrastructure · Depth: Intermediate, medium

Summary

AWS announced a series of innovations at the AWS Summit New York City aimed at delivering context intelligence for data and AI agents at scale. Key among these is AWS Context, a new service that automatically maps data relationships into a knowledge graph, providing agentic search for AI agents to access governed data, business rules, and domain knowledge at runtime. This service extends Amazon Quick's knowledge graph technology, processing millions of requests daily, into an organizational context layer. AWS Context integrates with AWS Glue Data Catalog, Amazon SageMaker Unified Studio, and AWS Lake Formation, publishing key elements to Amazon S3 in Apache Iceberg format for open access. Additionally, AWS introduced a preview of business context and semantic search for AWS Glue Data Catalog, enabling enrichment of tables with business descriptions and skill assets. Finally, Amazon S3 Annotations are now generally available, allowing up to 1 GB of mutable, queryable business context to be attached directly to S3 objects, flowing into Iceberg tables for querying with Amazon Athena or Amazon Redshift.

Key takeaway

For AI Engineers and Data Architects building intelligent agents, these AWS innovations simplify providing trusted, governed context. You can now centralize scattered enterprise data into a learning knowledge graph with AWS Context, ensuring agents make informed decisions. Utilize AWS Glue Data Catalog's new business context and skill assets to enrich data understanding, and use Amazon S3 Annotations to attach rich, queryable metadata directly to your S3 objects. This streamlines agent development and enhances data discoverability and compliance.

Key insights

AWS innovations provide scalable, governed context intelligence for AI agents by unifying scattered data into knowledge graphs.

Principles

• AI agent intelligence depends on accessible, trusted context.
• Context layers should learn from agent usage patterns.
• Data governance and identity-awareness are critical for agent access.

Method

AWS Context automatically maps data relationships into a knowledge graph, which data stewards curate, and agents query via agentic search APIs, learning from usage.

In practice

• Use AWS Context to build an organizational knowledge graph.
• Enrich Glue Data Catalog with business context and skill assets.
• Attach up to 1 GB of mutable context directly to S3 objects.

Topics

• AI Agents
• Knowledge Graphs
• Data Governance
• AWS Context
• Apache Iceberg
• Metadata Management
• Amazon S3 Annotations

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, Data Engineer, AI Architect

Related on AIssential

• The Contextual Revolution: The Rise of the Metadata Engineer in the Intelligence Economy — Metadata engineering is crucial for building trusted, context-rich data foundations essential for advanced AI and mitigating hallucinations.
• AWS previews a cloud-agnostic registry for managing agentic fleets at scale — AWS Agent Registry centralizes AI agent discovery and governance to prevent "agentic sprawl" and enhance reuse.
• Twenty years in, Amazon S3 finds itself at the center of AWS’ push beyond storage — Amazon S3 has evolved into a foundational data substrate for AI and analytics, moving beyond basic object storage.
• AI Agent Trends Shaping Data-Driven Businesses — AI agents move business intelligence from passive reporting to active, automated decision-making and workflow optimization.
• AWS Quick's personal knowledge graph is making orchestration decisions most control planes can't see — AWS Quick evolves into a proactive, desktop-native AI agent with a persistent knowledge graph, raising enterprise governance concerns.
• Trace raises $3M to solve the AI agent adoption problem in enterprise — Providing AI agents with deep operational context is crucial for enterprise adoption and scalable deployment.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.