AWS

AWS just announced free Sandbox environments which lets any AWS Builder Center user to provision...

On June 22, 2026, AWS released Lambda MicroVMs and I also covered how it works and how your agents...

AWS Blocks handles authentication, databases, file storage, AI agents and more out of the box. But...

This is an intro to "Multi-Agent Systems in Production: What They Don't Tell You" — a four-part...

An AI agent that's flawless in the demo can still fall apart the first time a tool fails in production: a timeout, a network error, a response that comes back corrupted. The fix isn't a smarter model. It's testing the agent against those failures on purpose, before your users do, and hardening it one failure type at a time.

A static AI agent re-reasons the same kind of task from scratch every time, burning tokens and sometimes getting it wrong differently on each run. A self-improving agent solves it once, writes a small verified tool, and reuses that tool exactly from then on. The catch worth knowing up front: writing the tool costs more tokens than one-off reasoning. The payoff is correctness and reuse, not a smaller bill.

On a multi-step task, an AI agent will trust a tool that reports success even when the work silently never saved, and then confidently report the whole task done while part of it quietly failed. The fix isn't a better prompt. It's checking each step against the real backend and re-doing the one that didn't take.

When an AI agent reads untrusted content (a web page, a document, an email), a hidden instruction can ride in, get stored in the agent's own memory, and fire in a later session to exfiltrate data. This persistent form of prompt injection is called memory poisoning, and a better prompt won't stop it. The reliable defense is a deterministic gate on the dangerous action, at the tool boundary.

When an AI agent hallucinates a fact, the real damage starts when it writes that fact to memory and re-reads it as trusted context every session after, compounding the error and the token cost. Stopping it isn't a prompting problem. It's a deterministic check that validates what the agent is about to write, so a bad fact never becomes a permanent memory.

The FIFA World Cup 2026 kicked off on June 11th. And I had a problem. Most of the matches are played...

When I started working with agents, tools were the concept that made the rest of the architecture...

Skills in AWS DevOps Agent allow you to define and reuse your team’s investigation procedures so the...

IFTTT shipped MCP support but only for Claude and ChatGPT. Here's how I built a 500-line Node.js proxy to connect it to any stdio-based MCP client.

AWS just launched AWS Blocks, an open-source TypeScript framework that gives you backend capabilities...

An AI agent has two kinds of memory: conversation (semantic) and context (exact reference). Keep them separate with Strands and AgentCore.

Last Friday, the U.S. Commerce Department sent a letter to Anthropic. By that evening, Fable 5 and...

Introduction It's crazy to me that some GitHub repos, that were just created in the last...

AI coding agent hallucinates AWS APIs because it's guessing from training data frozen in the...

A hands-on look at the official Agent Toolkit for AWS: what it is, why I switched from the old MCP server, and how to set it up.

So developers like CI... for everything! We do this because we like things to be automated....

Claude Fable 5 fails on Amazon Bedrock with a 400 error before processing a single token: "data...

In the previous post, we talked about context windows. The model has a fixed-size desk and everything...

Context engineering matters for two reasons: reliability and cost. If your agent's context window is...

El modelo de tu agente de IA tiene mucha información y puede inferir muy bien, pero hay un tema y es...

Detect AI agent hallucinations without labeled data. Zero-shot LSC detection, claim decomposition, and real-time guardrails. Python code included.

A 30-second decision on your very first screen that saves a lot of confusion later. You sign up for...

The scale wall A computer vision pipeline that works on one image at one resolution isn't...

Deploy a standard FastAPI app to AWS Lambda serverlessly in two commands. No Docker. No handler...

Cuando escribes localStorage.getItem("token"), el navegador busca por clave de forma directa, sin...

For over a decade, there's been a tiny ASCII duck hiding in plain sight. Open the page source for...