AWS published a reference implementation that wires Amazon Bedrock AgentCore Evaluations, generally available since March 2026, into GitHub Actions so pull requests touching agent code, system prompts…
AWS launched CloudWatch Omni, a unified observability service that integrates metrics, logs, and traces across AI agent behavior and application performance in production, according to CIO.com. AWS sa…
Fintech company Ramp deployed an autonomous AI on-call agent called OCA that assisted with 575 merged fixes across 1,220 incident pull requests over four weeks, cutting human investigation time by rou…
A security researcher disclosed a HackerOne report (No. 3022516) finding that an AWS account's threat-detection layer was silently disabled: CloudTrail logging, CloudWatch metric filters, and SNS alar…
A self-hosted LiteLLM gateway for OpenAI's Codex on AWS ECS with Bedrock provides per-team virtual keys, spend caps, and CloudWatch logging, with a reference CDK stack in the guidance-codex repo under…
A developer detailed the architecture of production AI systems on AWS, emphasizing that the core challenge is building reliable systems around LLM API calls rather than making the calls themselves. Th…
An engineer building Porch Light, an AI agent that monitors city public meeting agendas, found that AI coding agents Kiro and Claude over-engineered a throwaway spike, adding a byte-identity test to a…
AWS announced agentic observability with Amazon OpenSearch Service MCP Apps on 25 August 2026, an extension to the Model Context Protocol that renders interactive dashboards inside AI chat windows, re…
A developer explains how to use CloudWatch Embedded Metrics Format (EMF) to emit custom metrics from an AI Node.js service without extra overhead. The approach embeds metric data in JSON log lines, av…
An AWS ECS payment-api service suffered a terminal failure loop at 3 a.m., causing 7,279 failed tasks since mid-August with no alerts, but an LLM agent workflow using Kiro Crew and the Model Context P…
A developer built an AWS DevOps AI agent using Kiro Crew and MCP, which autonomously detected and resolved a critical ECS service failure within minutes, reducing mean time to repair from hours to und…
Amazon Bedrock Model Evaluation enables teams to compare foundation models with data instead of guesswork, offering automatic metrics and LLM-as-a-Judge modes. A hands-on guide demonstrates building a…
Bluebox, a monitoring platform, warns that homegrown monitoring stacks for coding agents are a trap because they silo metrics, logs, and traces, leaving engineers to manually correlate data and losing…
A developer has published a guide explaining how to deploy a Retrieval-Augmented Generation (RAG) API on AWS App Runner, using Node.js 22, DynamoDB vector search, and Claude for answer generation. The…
Amazon Web Services (AWS) has launched AgentCore Payments, now generally available, enabling AI agents on its infrastructure to autonomously pay for APIs, web content, and other services in USDC on Co…
An engineer at ZopNight ran a week-long experiment giving an AI agent read-only access to AWS and GCP accounts with a single prompt: 'Cut our cloud bill by 20% without breaking anything.' The agent id…
A developer solved a log correlation problem in AWS Step Functions by using the execution name as the correlation ID. Instead of generating a separate UUID, the engineer used the business case ID as t…
AWS Lambda MicroVMs, which reached general availability on June 22, 2026, gives each AI agent or user session its own dedicated Firecracker virtual machine with no shared kernel, launching in seconds …
A developer built Horcrux Hunt, a multi-agent Harry Potter game where two AI agents compete live, and racked up a $1,847 bill in one weekend. By pruning invalid actions with a constraint solver before…
A developer compared nine cloud monitoring tools across infrastructure metrics, APM, log management, external endpoint checks, and multi-cloud coverage. The comparison found that tools like DevHelm ex…