Elizabeth Fuentes L

💻 Todo el código de esta serie está en un solo repo: resilient-agent-harness-sample-for-aws. Este...

💻 Todo el código de esta serie está en un solo repo: resilient-agent-harness-sample-for-aws. Este...

💻 Este es el inicio de una serie. Todo el código está en un solo repo:...

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.

De cero a la nube: cómo dockericé mi feed de AWS y lo desplegué en ECS ...

Un agente de IA tiene dos tipos de memoria: conversación (semántica) y contexto (referencia exacta). Mantenlas separadas con Strands y AgentCore.

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

Tu agente de programación con IA alucina APIs de AWS porque está adivinando con datos de...

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

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

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

Los loops de razonamiento en agentes de IA ocurren cuando un agente llama a la misma herramienta...

Evalúa la calidad de agentes IA con LLM-as-Judge y análisis de trayectorias. Detecta fallos silenciosos, tokens desperdiciados y alucinaciones antes de producción. Tutorial en Python con código.

Evaluate AI agent quality with LLM-as-Judge and trajectory analysis. Catch silent failures, wasted tokens, and hallucinations before production. Python tutorial with code.

Pushing Kiro's Free Tier to Its Limits ...

Las herramientas MCP congelan a los agentes de IA cuando las APIs externas son lentas, causando...

How to Evaluate AI Agents, Compare Strands, PydanticAI, and DeepEval for AI agent evaluation. Same test cases, same rubrics, different frameworks. Code examples and results.

Al evaluar AI agents, la elección del framework determina tus puntajes. Ejecuta pruebas idénticas en...

How to Prevent AI Agent Reasoning Loops from Wasting Tokens ...

El desbordamiento de ventana de contexto** ocurre cuando las salidas de herramientas de un agente de...

Strands Agents provides native telemetry and cost tracking out of the box. Stop writing custom token...

Strands Agents proporciona telemetría nativa y seguimiento de costos desde el primer momento. Deja...

Cuando le pides a un asistente de IA como Kiro (el asistente de IA de AWS), Claude Code o ChatGPT...

When you ask an AI assistant like Kiro (AWS's AI coding assistant), Claude Code, or ChatGPT to...

How to Prevent AI Agent Reasoning Loops from Wasting Tokens ...

Los agentes de IA no fallan como el software tradicional: no se bloquean con un stack trace. Fallan...