Fetching from the wire…
Agents2026-06-24 · source-backed
AWS made the managed AgentCore harness generally available on June 18. You define model, tools, skills, and memory with CreateHarness, then run it with InvokeHarness. It ships multi-model support (Bedrock, OpenAI, Gemini, LiteLLM), mid-session context preservation, built-in browser/code-interpreter/shell tools, automatic memory, CloudWatch tracing, immutable versioning with instant rollback, and code export so you can graduate from config to real code. This collapses the infrastructure-wiring step that's kept most agents stuck in prototype. The export path is the smart part, you're not locked into the config abstraction forever.
Each link below shares sources, entities, or timing with this story.
Each tenant gets a dedicated Bedrock AgentCore runtime, every user session runs in its own microVM that's terminated and memory-sanitized on completion, paired with Knowledge Bases metadata filtering, Guardrails on responses, VPC Lattice for private connectivity and per-tenant...
AWS announced August 6 that agents can now run on your own EC2 instances while AgentCore handles provisioning, patching, scaling, and lifecycle. Complements the existing microVM runtime, targeting sustained or specialized-hardware workloads that need the full EC2 instance-type...
Plus fine-grained access control and customer-managed key encryption scoped per agent. Unglamorous and load-bearing: you can't systematically measure agent quality when the evidence is scattered across destinations. (AWS)
AWS shipped per-user, per-target rate limiting August 6 covering MCP targets, inference targets and HTTP passthrough across three metrics: requests (RPS/RPM), tokens (TPM, inference only), connections (CPS). Limits scope by JWT claims ($.context.jwt.sub, .role, .azp) or IAM id...
AWS shipped Policy in Amazon Bedrock AgentCore to general availability across 13 regions. The breakthrough: security teams can write agent-to-tool access rules in plain English, which auto-convert to Cedar policies with automated reasoning that catches overly permissive or uns...
The walkthrough covers implementing MCP tools, wiring authentication, and deploying with AWS CDK against Bedrock AgentCore and Mistral AI Studio. Steal the two-layer JWT pattern: agent identity and end-user identity as separate token layers. Most MCP server tutorials hand-wave...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.