Field notes from the edge.
What our engineers learned this week. Hands-on technical deep-dives, postmortems, and strategy frameworks.
AIRuntime instances: persistent compute for production AI agents on Amazon Bedrock AgentCore
Amazon Bedrock AgentCore introduces runtime instances, a new managed compute option that provides persistent EC2 infrastructure for production AI agents requiring extended execution times, GPU acceleration, and multi-agent coordination. Unlike the existing microVM option limited to 8-hour invocations, runtime instances support sessions up to 14 days with features like stop/restart capabilities, sh
AITop announcements of the AWS Summit in New York, 2026
AWS Summit New York 2026 focused heavily on agentic AI capabilities, with major announcements centered on Amazon Bedrock AgentCore enhancements for enterprise AI agent development. Key launches include managed knowledge bases, web search integration, AI traffic monetization through AWS WAF, and security automation tools like AWS Continuum that operate at machine speed to identify and remediate vul
AIAWS Weekly Roundup: AWS FinOps Agent in preview, Gemma 4 on Bedrock, Kiro Pro Max, and more (June 15, 2026)
AWS announced multiple significant updates at its New York Summit, including the preview of AWS FinOps Agent for automated cost optimization and anomaly detection, and general availability of M9g/M9gd EC2 instances powered by Graviton5 processors. The week also featured new AI model releases on Amazon Bedrock, including Gemma 4 and Claude Fable 5 (though Claude models were temporarily revoked due
AIAnthropic Claude Fable 5 on AWS: Mythos-class capabilities with built-in safeguards now available
Anthropic has launched Claude Fable 5 on Amazon Bedrock and AWS, offering Mythos-level AI capabilities with built-in safeguards for broader enterprise use. The model features long-running task execution, advanced vision capabilities for document processing, and proactive self-verification, while automatically routing high-risk prompts to the less capable Opus 4.8 model. Enterprise customers can ac
AITry the new console experience in Amazon Bedrock, optimized for Anthropic- and OpenAI-compatible APIs
Amazon Bedrock has launched a new console experience optimized for the bedrock-mantle endpoint, supporting the latest GPT, Claude, and open-weight models through OpenAI and Anthropic-compatible APIs. The refreshed interface introduces project-based workflows, enhanced model comparison capabilities, and live documentation with auto-populated code snippets to accelerate development from evaluation t
AIGet started with OpenAI GPT-5.5, GPT-5.4 models, and Codex on Amazon Bedrock
AWS announces general availability of OpenAI's GPT-5.5, GPT-5.4 models, and Codex coding agent on Amazon Bedrock, providing enterprises with frontier AI models through a next-generation inference engine. GPT-5.5 targets demanding workloads while GPT-5.4 offers optimal price-performance, both accessible via the Responses API with pay-per-token pricing and no per-developer seat licenses. Codex integ