The model that decides instead of chatting. Tech & AI Weekly by Eli, October 02 2026
Jev and Strands Decider launch a new kind of decision model, three frontier labs ship in days, and prices fall across the board.
Tag: ai
-
-
AI Agent Audit Trails: Prove Why Your Agent Decided, Not Just What
Record why an agent decided, live, with zero tool changes. Store the traces in Neo4j with the official SDK and run the reverse audit a flat store can't express
-
Same model, 5x the bill, depending on the harness. Tech & AI Weekly by Eli, September 18 2026
Berkeley's harness-tax study found the same model costs up to 5x more depending on the harness. Plus: the best coding agent fails 60% on unseen code, and GitHub rewrites the Copilot runtime in Rust using Copilot.
-
Semantic Caching for AI Agents in Production
Semantic caching for AI agents fixes something that should embarrass all of us: an agent paying full...
-
How to Stop AI Agent Memory Poisoning
Memory poisoning is the attack a prompt injection leaves behind: one malicious message that your AI...
-
El Prompt Caching No Es Suficiente
El prompt caching solo descuenta tokens de entrada. Descubre dónde puede cachear un agente de IA y añade cachés semántico y de razonamiento que recortan el cost
-
Can AI build your agent? A benchmark says 23.9%. Tech & AI Weekly by Eli, September 11 2026
Sierra's benchmark asked coding agents to build a working AI agent. The best passed 23.9%, and one sentence about architecture took another from 31% to 67%.
-
Prompt Caching Isn't Enough
Prompt caching only discounts input tokens. Map where an AI agent can cache and add semantic and reasoning caches that cut agent costs up to 85%.
-
AI Agent Memory: What to Store and What to Throw Away
Everyone is racing to make agents remember more. Bigger context windows, longer histories, a vector...
-
The harness beat the reasoning dial. Tech & AI Weekly by Eli, September 4 2026
The harness added 36 points to GPT-6 Astra's benchmark. Also: what agent memory should throw away, DoorDash's 130K agent tasks, Kiro Crew goes open source, and pnpm 12 in Rust.
-
AI agents now control lab equipment. Tech & AI Weekly by Eli, August 29 2026
Anthropic released a spec for AI agents to control physical lab equipment. Also: self-improving AI, AWS AgentCore Evaluations, Meta's custom silicon, and a $40k hackathon.
-
Memoria de Grafo: Cuando la Búsqueda Vectorial Falla
📦 Clona y dale ⭐ a stop-ai-agents-losing-memory-sample-for-aws Los agentes de IA acumulan hechos...
-
Graph Memory: When Vector Search Fails
📦 Clone and ⭐ stop-ai-agents-losing-memory-sample-for-aws AI agents accumulate facts across...
-
Observability for AI Agents with OpenTelemetry
AI agent observability means capturing your agent's reasoning cycles, tool calls, and token usage as...
-
Amazon DynamoDB Vector Search. No Separate Vector Store
Amazon DynamoDB Vector Search GA: add a vector index to an existing table. Same accuracy as S3 Vectors, single-digit ms latency, data and embeddings collocated.
-
Amazon DynamoDB Vector Search. Sin Vector Store Separado
Amazon DynamoDB Vector Search GA: agrega un índice vectorial a una tabla existente. Misma precisión que S3 Vectors, latencia de un solo dígito en ms, vectores y
-
Memory Is Having a Moment. Tech & AI Weekly by Eli, August 14 2026
Two weeks of AI in one edition: context engineering from 35% to 98%, Meta's local 30B agent model, a shared plugin standard backed by five companies, and Anthropic's dream memory.
-
AI Agent Memory: Add Semantic Search Without a Vector Database
Keyword search misses intent questions. Semantic search finds them. Add vector search to AI agent memory with FAISS or S3 Vectors, benchmarked.
-
Memoria de Agentes de IA: Agrega Búsqueda Semántica Sin una Vector Database
La búsqueda por palabras clave pierde preguntas de intención. La búsqueda semántica las encuentra con FAISS o Amazon S3 Vectors, medido.
-
Detectar Alucinaciones en Agentes de IA: Métodos Zero-Shot
Detecta alucinaciones en agentes de IA sin datos etiquetados. Detección LSC zero-shot,...
-
Cómo Solucionar el Error de Retención de Datos de Claude Fable 5 en Amazon Bedrock
Claude Fable 5 falla en Amazon Bedrock con un error 400 antes de procesar un solo token: "data...
-
Stop Your AI Agent Forgetting User Preferences: Key-Value Memory
Here's a test most AI agents fail. A brand-new user searches flights, books one in business class, and asks what you recommend based on what you know about me?
-
Tipos de Memoria para Agentes de IA: Tu Agente lo Olvida Todo. Cómo Solucionarlo
Tu agente de IA funciona perfecto en el demo. Luego un usuario real regresa al día siguiente y el...
-
Stateless MCP, 80% price cuts, and 37 agent projects in one day. Tech & AI Weekly by Eli, July 31 2026
Stateless MCP lands, GPT-5.6 drops 80% in price, Claude Opus 5 ships, and 151 builders built 37 agent projects in one day.
-
The model isn't the bottleneck anymore. Tech & AI Weekly by Eli, July 24 2026
Agent architecture over model choice: the context layer, converging agent platforms, Anthropic's $1.5B settlement, Kimi K3, and AI agent memory types.
-
AI Agent Memory Types: Your Agent Forgets Everything. Fix It
Your AI agent works beautifully in the demo. Then a real user comes back the next day, and the agent...
-
Every agent decision needs a receipt. Tech & AI Weekly by Eli, July 17 2026
Stripe benchmarked where agents fail, agents outspending humans, and the evidence-packet future of agent observability.
-
Agentes de IA auto-mejorables: Convierte razonamiento repetido en herramientas que el agente escribe solo
💻 Todo el código de esta serie está en un solo repo: resilient-agent-harness-sample-for-aws. Este...
-
Cómo Evitar que las Alucinaciones RAG Envenenen tu Vector Store
Un pipeline RAG fintech envenenó su propio vector store y el validador LLM-as-a-judge aprobó cada alucinación. La solución: validar las escrituras con código.
-
How to Stop RAG Hallucinations Poisoning Your Vector Store
A fintech RAG pipeline poisoned its own vector store and the LLM-as-a-judge validator approved every hallucination. The fix: gate writes with code.
-
I watched a RAG pipeline poison its own memory. Tech & AI Weekly by Eli, July 10 2026
This week: a RAG pipeline that poisoned its own vector store, GitHub's AI agent tricked into leaking private repos, GPT-5.6, and what I'm digging into next: graph-based memory for agents.
-
Por qué los agentes de IA fallan en tareas multi-paso, y cómo atrapar el fallo silencioso
💻 Todo el código de esta serie está en un solo repo: resilient-agent-harness-sample-for-aws. Este...
-
Cómo detener la inyección de prompts en agentes de IA que leen contenido no confiable
💻 Todo el código de esta serie está en un solo repo: resilient-agent-harness-sample-for-aws. Este...
-
Cómo probar agentes de IA contra fallos de producción antes que tus usuarios
💻 Este es el inicio de una serie. Todo el código está en un solo repo:...
-
Detener alucinaciones de agentes de IA: Validar antes de que el agente escriba en memoria
💻 Todo el código de esta serie está en un solo repo: resilient-agent-harness-sample-for-aws. Este...
-
Fable 5 returns, agent memory levels up. Tech & AI Weekly by Eli, July 3 2026
Claude Fable 5 returns to Bedrock, Sonnet 5 lands on AWS, and AgentCore memory gets metadata filtering. This week in tech and AI.
-
A fake bug report can hijack your coding agent. Tech & AI Weekly by Eli, June 26 2026
This week: AgentJacking hijacks Claude Code, Cursor, and Codex through a fake Sentry bug report, new research on why models confuse trusted and untrusted text, Strands chaos testing, AWS Blocks, and Lambda MicroVMs.
-
How to Stop Prompt Injection in AI Agents That Read Untrusted Content
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
-
How to Test AI Agents for Production Failures Before Your Users Do
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 c
-
Self-Improving AI Agents: Turn Repeated Reasoning Into Tools the Agent Writes Itself
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-improv
-
Stop AI Agent Hallucinations: Validate Before the Agent Writes to Memory
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, compound
-
Why AI Agents Fail at Multi-Step Tasks, and How to Catch the Silent Failure
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 don
-
Strands cut agent costs in half, and I published a book — Tech & AI Weekly, June 19 2026
This week: I published my book on AI agents that don't hallucinate or waste tokens, Strands cut agent costs in half, GLM-5.2 open weights, and the agent launches from AWS Summit New York.
-
Memoria de Agentes de IA: Conversación vs Contexto
Un agente de IA tiene dos tipos de memoria: conversación (semántica) y contexto (referencia exacta). Mantenlas separadas con Strands y AgentCore.
-
Stop wasting tokens with the wrong AI agent memory
An AI agent has two kinds of memory: conversation (semantic) and context (exact reference). Keep them separate with Strands and AgentCore.
-
A frontier model got pulled in 72 hours. Tech & AI Weekly by Eli, June 13 2026
Welcome to my very first newsletter!
-
AWS Agent Toolkit: Evita que tu Agente de IA Alucine APIs
Tu agente de programación con IA alucina APIs de AWS porque está adivinando con datos de...
-
AWS Agent Toolkit: Stop Your Coding Agent Hallucinating APIs
AI coding agent hallucinates AWS APIs because it's guessing from training data frozen in the...
-
Detect AI Agent Hallucinations: Zero-Shot Methods
Detect AI agent hallucinations without labeled data. Zero-shot LSC detection, claim decomposition, and real-time guardrails. Python code included.
-
Cómo Prevenir Loops de Razonamiento en Agentes de IA y No Desperdiciar Tokens
Los loops de razonamiento en agentes de IA ocurren cuando un agente llama a la misma herramienta...
-
Cómo Evaluar Agentes IA: Tutorial de LLM-as-Judge
Evalúa la calidad de agentes IA con LLM-as-Judge y análisis de trayectorias. Detecta fallos silenciosos, tokens desperdiciados y alucinaciones antes de producci
-
How to Evaluate AI Agents: LLM-as-Judge Tutorial
Evaluate AI agent quality with LLM-as-Judge and trajectory analysis. Catch silent failures, wasted tokens, and hallucinations before production. Python tutorial
-
Solucionar Timeouts de MCP: Patrón HandleId Asíncrono
Las herramientas MCP congelan a los agentes de IA cuando las APIs externas son lentas, causando...
-
Cómo Evaluar AI Agents: Comparación de 3 Frameworks
Al evaluar AI agents, la elección del framework determina tus puntajes. Ejecuta pruebas idénticas en...
-
How to Evaluate AI Agents: 3 Framework Comparison
How to Evaluate AI Agents, Compare Strands, PydanticAI, and DeepEval for AI agent evaluation. Same test cases, same rubrics, different frameworks. Code examples
-
Desbordamiento de Ventana de Contexto de IA: Solución con Puntero de Memoria
El desbordamiento de ventana de contexto** ocurre cuando las salidas de herramientas de un agente de...
-
Built-in Token Counting: Telemetry for Production AI Agents
Strands Agents provides native telemetry and cost tracking out of the box. Stop writing custom token...
-
Cómo Monitorear Costos de Agentes IA sin Configuración
Strands Agents proporciona telemetría nativa y seguimiento de costos desde el primer momento. Deja...
-
Cómo Guiar Asistentes de IA para Construir Agentes Listos para Producción: 8 Patrones Esenciales
Cuando le pides a un asistente de IA como Kiro (el asistente de IA de AWS), Claude Code o ChatGPT...
-
Prompt AI Coding Assistants to Build Production-Ready Agents: 8 Essential Patterns
When you ask an AI assistant like Kiro (AWS's AI coding assistant), Claude Code, or ChatGPT to...
-
Por Qué Fallan los Agentes de IA: 3 Modos de Fallo Que Cuestan Tokens y Tiempo
Los agentes de IA no fallan como el software tradicional: no se bloquean con un stack trace. Fallan...
-
How to Prevent AI Agent Reasoning Loops from Wasting Tokens
AI agents get stuck in reasoning loops, calling the same tool repeatedly. DebounceHook and clear SUCCESS states break the loop. Runnable demo included.
-
Fix MCP Timeouts: Async HandleId Pattern
MCP tools freeze AI agents when external APIs are slow, causing 424 errors. The async handleId pattern returns immediately with a job ID and polls for results w
-
AI Context Window Overflow: Memory Pointer Fix
AI agents fail silently when tool outputs exceed the context window. The Memory Pointer Pattern stores data externally and passes references.
-
Guardrails para Agentes de IA que se Autocorrigen en Lugar de Bloquear
La mayoría de los guardrails para agentes hacen una sola cosa: bloquear. El agent choca con una...
-
Multichannel AI Agent: Shared Memory Across Messaging Platforms
Build an AI chatbot that remembers users across WhatsApp and Instagram using Amazon Bedrock...
-
Guardrails para Agentes de IA: Reglas Que los LLM No Pueden Evadir
Los agentes de IA pueden alucinar el éxito de una operación incluso cuando violan reglas de negocio....
-
5 Techniques to Stop AI Agent Hallucinations in Production
Deploy 5 production-ready techniques to stop AI agent hallucinations using Amazon Bedrock AgentCore, DynamoDB steering rules, Lambda tools, and Graph-RAG with N
-
Why AI Agents Fail: 3 Failure Modes That Cost You Tokens and Time
AI agents don't fail like traditional software — they don't crash with a stack trace. They fail...
-
Reduce errores y costos de tokens en agentes con seleccion semantica de herramientas
Cuando los agentes de IA tienen muchas herramientas similares, a menudo seleccionan la incorrecta y...
-
Deten las Hallucinations en Agentes de IA: 4 Tecnicas Esenciales
4 tecnicas para detener las hallucinations en AI agents: Graph-RAG para recuperacion precisa de datos, seleccion semantica de tools para elegir la herramienta correcta, guardrails neurosimbolicos para aplicar reglas de negocio, y validacion multi-agent para deteccion de errores.
-
Detén las Hallucinations en Agentes de IA: 4 Técnicas Esenciales
4 técnicas para detener las hallucinations en AI agents: Graph-RAG para recuperación precisa de...
-
RAG vs GraphRAG: Cuando los Agentes Alucinan Respuestas
Un agent que alucina durante la ejecucion es catastrofico: podria fabricar parametros de API,...
-
How to Stop AI Agents from Hallucinating Silently with Multi-Agent Validation
AI agents fail silently. They confirm operations that never completed, return success when tools...
-
Runtime Guardrails for AI Agents - Steer, Don't Block
Most agent guardrails do one thing: block. The agent hits a rule, the workflow stops, and the user...
-
AI Agent Guardrails: Rules That LLMs Cannot Bypass
AI agents can hallucinate operation success even when they violate business rules. They confirm...
-
Reduce Agent Errors and Token Costs with Semantic Tool Selection
When AI agents have many similar tools, they often select the wrong one and consume excessive tokens...
-
RAG vs GraphRAG: When Agents Hallucinate Answers
Traditional RAG makes AI agents hallucinate statistics and aggregations. This demo builds a travel...
-
Stop AI Agent Hallucinations: 4 Essential Techniques
4 techniques to stop AI agent hallucinations: Graph-RAG for precise data retrieval, semantic tool...
-
Build Agentic Video Analysis with TwelveLabs Pegasus in minutes
Learn to build intelligent video analysis agents in minutes using TwelveLabs Pegasus 1.2 and Strands...
-
Multi-Modal Travel Planning Agent in Minutes
🇻🇪🇨🇱 Dev.to | LinkedIn | GitHub | Twitter GitHub Repository: Strands Agent Samples Build a...
-
Monitorea Agentes de IA en Producción sin Código
Aprende a monitorear agentes de IA en producción con Amazon Bedrock AgentCore Observability....
-
Monitor AI Agents in Production with Zero Code
Learn to monitor AI agents in production with Amazon Bedrock AgentCore Observability. Zero-code...
-
Bring AI agents into production in minutes
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Build Agentic Video RAG with Strands Agents and Containerized Infrastructure
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Ask Your Video: Build a Containerized RAG Application for Visual and Audio Analysis
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Build Agentic Video RAG with Strands Agents and Amazon Aurora PostgreSQL - Local Infrastructure
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Construyendo Agentes Strands con pocas líneas de código: Comunicación Agente a Agente (A2A)
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Building Scalable Multi-Modal AI Agents with Strands Agents and Amazon S3 Vectors
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Building Strands Agents with a few lines of code: Evaluating Performance with RAGAs
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Building Strands Agents with a few lines of code: Implementing Observability with LangFuse
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Building Strands Agents with a few lines of code: Custom Tools and MCP Integration
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Procesamiento de Contenido Multimodal con Strands Agent: Capacidad de Recordar usando Strands y FAISS
🇻🇪🇨🇱 Dev.to LinkedIn GitHub Twitter Instagram YouTube Linktr ...
-
Multi-Modal Content Processing with strands agents and FAISS Memory
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Procesamiento de Contenido Multimodal con Strands Agent y solo unas pocas líneas de código
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Multi-Modal Content Processing with Strands Agents and just a few lines of code
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Building a RAG System for Video Content Search and Analysis
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ...
-
Add Generative AI to a JavaScript Web App 2.0
This article was written in colaboration Enrique Rodriguez ...
-
Incorpora IA generativa con Claude 3 a una aplicación web de JavaScript
Este artículo fue escrito en colaboración con Enrique Rodriguez ...
-
Construyendo un asistente genAI de WhatsApp con Amazon Bedrock y Claude 3
El blog enseña a desplegar una aplicación de WhatsApp en Amazon Bedrock para chatear en...
-
Construyendo un asistente genAI de WhatsApp con Amazon Bedrock
Versión en inglés Chatea en cualquier idioma con un LLM en Bedrock. Envía notas de voz y...
-
Cómo elegir un LLM
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ✅ Original Blog: Working With Your...
-
How To Choose Your LLM
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ✅ Original Blog: Working With Your...
-
Working With Your Live Data Using LangChain
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ✅ Original Blog: Working With Your...
-
Build A Translator App in 30 Min or Less
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ✅ Blog original: Build A Translator...
-
Inteligencia Artificial Como API en tu aplicación
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ✅ Blog original: All the things that...
-
Todas las cosas que Comprehend, Rekognition, Textract, Polly, Transcribe y otros pueden hacer.
🇻🇪🇨🇱 Dev.to Linkedin GitHub Twitter Instagram Youtube Linktr ✅ Blog original: All the things that...
-
All the things that Comprehend, Rekognition, Textract, Polly, Transcribe, and Others Do
Original:...