← Back to all announcements
★★☆☆☆ 01/05/2026

Amazon Bedrock AgentCore is now available in the South America (São Paulo) Region

Build and deploy AI agents in South America with full feature parity—no more waiting for regional availability.

View original announcement →

Visual Summary

graph TD A{{AgentCore - São Paulo Region}}:::announced B([Agent Runtime]):::feature C([Identity & Policy]):::feature D([Gateway]):::feature E([Observability]):::feature F([Code Interpreter]):::feature G([Browser Tools]):::feature H((End Users - South America)):::external I((Enterprise Systems)):::external H ==>|"low latency"| A A -->|"executes agents"| B A -->|"enforces security"| C A -->|"connects APIs"| D A -->|"monitors"| E A -.->|"runs code"| F A -.->|"web interaction"| G D -->|"integrates"| I classDef announced fill:#ff9900,stroke:#ec7211,color:#fff,font-weight:bold classDef compute fill:#e3f2fd,stroke:#1565c0,color:#1565c0 classDef storage fill:#e8f5e9,stroke:#2e7d32,color:#2e7d32 classDef feature fill:#fff3e0,stroke:#e65100,color:#e65100 classDef external fill:#f5f5f5,stroke:#616161,color:#616161

What's New

Amazon Bedrock AgentCore is now generally available in the AWS South America (São Paulo) Region as of May 1, 2026. AgentCore is AWS's unified platform for building, connecting, and optimizing AI agents, supporting any framework and any model. The full suite of AgentCore capabilities — including agent runtime, identity, gateway, policy, observability, code interpreter, and browser tools — is available in São Paulo at launch with no feature gaps relative to other supported regions.

How It Works

  • Amazon Bedrock AgentCore provides a managed infrastructure layer for deploying and operating AI agents at scale.
  • The agent runtime executes agent logic with lifecycle management, while identity handles authentication and authorization for agents interacting with enterprise systems.
  • The gateway enables agents to connect to external APIs and tools, and policy enforces guardrails and access controls at the infrastructure level — meaning security constraints cannot be circumvented by agent logic itself. Observability provides tracing, logging, and monitoring of agent behavior, while code interpreter and browser tools give agents the ability to execute code and interact with web-based interfaces.
  • All of these components operate within the São Paulo Region, meaning data processed by agents remains within the region's boundaries unless explicitly configured otherwise.

Why It's Important

  • The São Paulo expansion is significant for several reasons.
  • First, it enables South American customers — particularly those in Brazil operating under the Lei Geral de Proteção de Dados (LGPD) — to meet data residency and data sovereignty requirements by keeping agent workloads and associated data within Brazilian borders.
  • Second, deploying agents in-region reduces network latency for end users in South America, which is critical for real-time, interactive agent applications.
  • Third, it signals AWS's commitment to making its most advanced agentic AI infrastructure broadly accessible across global regions, not just in primary US and European markets.

How It's Different

  • Prior to this expansion, South American customers who wanted to use AgentCore had to route workloads through other AWS regions (such as US East or EU regions), introducing latency, potential compliance complications, and data egress costs.
  • Compared to building custom agent orchestration infrastructure using raw AWS services (Lambda, API Gateway, IAM, CloudWatch), AgentCore provides a purpose-built, integrated platform that eliminates significant undifferentiated engineering work.
  • Unlike open-source agent frameworks (e.g., LangChain, AutoGen) deployed on self-managed infrastructure, AgentCore enforces security at the infrastructure layer, meaning developers cannot accidentally or intentionally bypass policy controls through application-level code.

When to Prefer It

  • Choose AgentCore in São Paulo when your use case involves Brazilian or broader South American end users who require low-latency agent interactions, or when your organization must comply with LGPD or other regional data residency mandates.
  • It is particularly well-suited for enterprise deployments where security, auditability, and policy enforcement are non-negotiable — since AgentCore's infrastructure-layer security model provides stronger guarantees than application-level guardrails.
  • Teams that want to iterate quickly across multiple agent frameworks and foundation models without rebuilding connectivity, observability, or identity plumbing for each project will also benefit most from AgentCore's unified platform approach.

Availability

  • Amazon Bedrock AgentCore is generally available (GA) in the AWS South America (São Paulo) Region (sa-east-1) as of May 1, 2026.
  • All core capabilities — agent runtime, identity, gateway, policy, observability, code interpreter, and browser tools — are available at launch with full feature parity.
  • Pricing follows the AgentCore pricing model (see the AgentCore pricing page for region-specific rates).
  • For a complete and up-to-date list of all supported AWS regions, refer to the official AWS Supported Regions documentation.
  • No preview or limited-access restrictions are noted for this region at launch.

Tags

Servicesbedrock-agentcore
Typeregion-expansion
Conceptsagentic-ai
Use Casesenterprisemulti-region
GeographyAMERICAS

AI Radar AWS

AWS AI/ML news — curated, researched, explained

An automated intelligence platform that curates, researches, and analyzes AWS AI/ML/GenAI announcements daily. Every report is backed by real research — the system reads linked blog posts and documentation to provide accurate, in-depth analysis.

How Each Report Is Generated

  1. Collection — Daily monitoring of the AWS "What's New" RSS feed
  2. Filtering — AI-powered relevance detection for AI/ML/GenAI topics
  3. Taxonomy Tagging — LLM-based classification across 6 dimensions
  4. Importance Scoring — Point-based system with tag bonuses (1-5 stars)
  5. Research Phase — Follows links to blog posts and documentation
  6. Report Generation — Claude Sonnet produces structured 6-section analysis
  7. Visual Summary — Claude Opus generates Mermaid diagrams for key items
  8. Publishing — Static website rebuilt and deployed via CloudFront

Features

  • Faceted filtering by service, type, concept, and more
  • Multi-dimensional taxonomy with 80+ tags across 6 dimensions
  • Geographic availability badges (Global, APJ, EMEA, AMER) with filtering
  • Timeline visualization of announcement volume
  • PDF export for offline reading
  • Mermaid visual summaries for key announcements
  • Daily automated updates — no manual curation
What makes this different: Each report involves a dedicated research phase where the system reads linked blog posts and AWS documentation pages. This produces analysis that goes beyond the original announcement text.

Technology

Built with Python, AWS Lambda, Amazon Bedrock (Claude Sonnet 4.6, Opus 4.6, Haiku 4.5), S3, CloudFront, WAF, EventBridge, and CDK.

Open Source

This project is open source. Fork it, customize it for your needs, and deploy your own instance.
📦 github.com/bbonik/ai-radar-aws

How Importance Scoring Works

Each announcement receives a point score based on multiple factors. The total score maps to a 1-5 star rating:

1★ < 2 pts 2★ ≥ 2 pts 3★ ≥ 3.5 pts 4★ ≥ 5 pts 5★ ≥ 6.5 pts

Point Breakdown

FactorPointsWhen
Core AI service (Bedrock, AgentCore, SageMaker AI)+4Service named in title
Key AI service (SageMaker, Kiro, QuickSight)+2Service named in title
Other AI-related service+1Default
Blog post link+3Link to aws.amazon.com/blogs/
GitHub samples link+2Link to github.com/aws*
Documentation link+1Link to docs.aws.amazon.com/
New model+1.5Tagged as "new-model"
New service+1Tagged as "new-service"
New feature+0.5Tagged as "new-feature"
Anthropic / OpenAI provider+2Provider explicitly mentioned
Instance / notebook announcement-2Hardware/capacity, not feature
Performance / pricing / security-0.5Incremental updates
Region expansion to APJ+1Expands to Asia Pacific
Region expansion (non-APJ only)-1.5Only expands to other regions

Geographic Relevance Badges

Each announcement card shows a small badge indicating whether the feature is available in your region:

🌐 Global Available in all regions
🌏 APJ Asia Pacific
🌍 EMEA Europe / Middle East / Africa
🌎 AMER Americas (US, Canada, South America)
No badge Geography unknown
How geography is detected: The system detects ALL geographies mentioned in each announcement. If the text mentions specific regions (Tokyo, Frankfurt, Oregon, etc.), the corresponding geography badges are shown. If it says "all regions" or is a new feature with no region specified, it gets the Global badge. Geography is also filterable — click a geo chip to see only announcements available in that region.