13h ago · 11 min read · Last week, I watched a junior developer turn a simple ChatGPT wrapper into a fully autonomous agent that could research competitors, analyze their pricing strategies, and generate detailed market reports — all while she grabbed coffee. The transforma...
Join discussion1d ago · 8 min read · Last week, I was helping a junior developer implement their first chatbot for customer support. We were debating between building everything from scratch versus using a framework. "I just want something that can search our docs and give helpful answe...
Join discussion2d ago · 5 min read · AI Agent Orchestration Patterns: How to Build Production-Grade Multi-Agent Systems A month into running AI agents in production, I've learned something counterintuitive: the hard part isn't getting a single agent to work. It's getting multiple agents...
Join discussion3d ago · 8 min read · Between 2024 and 2025 I co-founded DocHelp, a RAG-powered medical AI assistant for Brazilian doctors. We shipped it. The technical RAG layer worked. The product did not stick. This post is the honest
Join discussion
4d ago · 6 min read · Your LangChain agent is wrong about 10% of the time. Not occasionally — consistently, confidently, and silently. The problem isn't the model. It's that your agent has no way to know when it's wrong. I
Join discussion
6d ago · 4 min read · What you'll learn: How to instrument LangChain agents with custom logging hooks that capture execution metrics Why monitoring agent behavior differs fundamentally from traditional application monitoring Techniques to track decision-making patterns, ...
Join discussionApr 17 · 12 min read · The "Shallow Agent" Problem Nobody Talks About If you've been following my previous articles on Prompt Engineering and Context Engineering, you know I've been going deeper and deeper into how LLMs act
Join discussion
