amazon-bedrock

Harness GA Jun 17, 2026 plus Strands 1.0 primitives — and why AWS Context is still Coming soon. Reuse the ~180→95 ms Gateway canary; ship Managed KB today.

On Aug 6, 2026 AgentCore Runtime Instances went GA — EC2-backed agents with sessions up to 14 days vs 8-hour microVM Runtime. Field guide: capacity providers, GPU fit, and when idle EC2 burns more than serverless.

On August 5, 2026 DynamoDB GA’d native vector search — single-digit ms at 99%+ recall, up to 4096 dims, SearchVectors topK ≤ 100. Decision guide vs S3 Vectors, OpenSearch, and Bedrock Knowledge Bases.

Hand this to your technical lead. The store decision: one lookup this week, a person signs money, skip when a rule already works. Sample uses 8 Gateway tools — not a client case study.

On June 15, 2026 Grok 4.3 GA on Bedrock Mantle at $1.25/$2.50 per 1M. On August 19, 2026 Grok 4.6 added Converse + US Geo/Global CRIS at $2.00–$2.20 / $6.00–$6.60 — do not jump on name alone.

On July 30, 2026 AWS cut Bedrock on-demand prices 80% for GPT-5.6 Luna and 20% for Terra — Luna is now $0.22/$1.32 per 1M tokens. Here is the routing math and what not to re-price overnight.

On July 24, 2026 AWS shipped Claude Opus 5 on Bedrock — 1M-token context, 128K max output, ZDR by default. Here is the Bedrock vs Claude Platform routing call and a lane-by-lane rollout plan.

February 2026 server-side tool execution via AgentCore Gateway + Responses API cut median tool-round-trip latency ~180 ms → ~95 ms on a 12-tool SaaS CRM assistant by removing the client orchestration hop.

For a multi-district LMS (~52k concurrent exam submissions in 30 min), SQS decouple + Aurora Serverless v2 held p95 submit at 410 ms — off-peak monthly compute −71% vs always-on EC2.

First-party TCO benchmark (July 2026): 500-employee Quick Suite ~$3,580/mo vs AgentCore support agent ~$791/mo at 50K sessions. CTO framework for choosing managed assistants vs custom agent infrastructure on AWS.

Q2 2026 ranked: AgentCore Harness GA (Jun 17), FinOps Agent preview (Jun 9), Graviton5 GA (Jun 10), OpenAI on Bedrock (Apr 28). Adoption matrix + verified TCO signals for CTOs.

AWS announced Claude Sonnet 5 on June 30, 2026. This guide explains the two AWS access paths, where Sonnet 5 fits in agentic workloads, and how to evaluate adoption without model-churn.