When Codex uses Bedrock's OpenAI-compatible API, switching models can break requests: the selected model changes, but the provider still points to the same AWS Region. The failure appears both when using Codex directly and when operating it through the ChatGPT app. In both cases, Codex makes the model API request. A …

1. The Three-Phase Transcription Pipeline A production podcast transcript is not produced by one model call. The pipeline behind these measurements has three stages: Phase 1: VAD, speech recognition, punctuation, timestamps, and speaker diarization. Phase 2: speaker identity verification and label correction. Phase 3: …

If you run claude against Amazon Bedrock across a dozen repos, your bill arrives as one opaque number. Until recently, the workaround was clunky — create an application inference profile per project, swap them by hand, hope you remembered which one was active. In April 2026, AWS shipped native per-principal cost …

In a previous post, I introduced an AWS CDK project for deploying OpenHands on EC2, featuring Cognito authentication and Aurora PostgreSQL. While this architecture successfully facilitated initial deployment, operating a shared AI coding platform for a team revealed three fundamental limitations: Shared Resources: All …

TL;DR (30-Second Read) With Amazon Bedrock AgentCore now generally available — including AgentCore Identity for agent authentication and AgentCore Policy, which enforces Cedar rules by intercepting every tool call before execution — the security design for multi-tenant SaaS on Bedrock Agents has reached an inflection …

Choosing a vector store on AWS for generative AI (GenAI) workloads used to be a one-line decision: pick Amazon OpenSearch Service or its serverless variant (AOSS) and move on. That changed when Amazon S3 Vectors went GA in 2025. By storing vector data directly in S3 and pricing it on a fully consumption-based model, S3 …

Autonomous AI dev teams move the bottleneck. When a dispatcher fans out work to dev and review agents every 5 minutes, the constraint is no longer human attention — it is the CI/CD pipeline that gates every PR. Each agent push triggers builds, tests, E2E verification, and bot reviews. With even a small team of agents …

OpenHands is an open-source AI-driven development platform that enables AI agents to write code, fix bugs, and execute complex development tasks autonomously. The default setup works well for local development, but what if you want to run it for a team or make it accessible from anywhere? This post introduces an AWS …

The Xiaozhi hardware is an impressive ESP32-based AI voice assistant capable of offline wake-up, multi-language support, and cloud connectivity. But what if you want your Xiaozhi device to access multiple AI tools, APIs, and services without managing complex integrations on the hardware side? This is where Amazon …

You can stop hoping your Large Language Model (LLM) follows complex instructions. Context Engineering is the strategic practice of curating what enters the model's limited attention budget. To build reliable AI agents, you must master these four deterministic context patterns. This post explores the key insights from …