2d ago · 14 min read · Introduction AI agents are no longer experimental curiosities, they’re core components of production systems, orchestrating workflows, making autonomous decisions, and interacting with users in real t
Join discussion5d ago · 3 min read · Disclosure: I am a frontend developer transitioning into AI engineering, sharing real experiments and learnings from building production-style RAG systems. Your RAG pipeline works perfectly on Friday
Join discussionMay 10 · 11 min read · The agent returned a 200. The customer lost $4,200. The monitoring dashboard showed green. This is the failure mode that keeps me up at night — not the one where your AI agent crashes with a stack trace, but the one where it succeeds at the wrong thi...
Join discussionMay 9 · 11 min read · The agent returned a 200. The customer lost $4,200. The monitoring dashboard showed green. This is the failure mode that keeps me up at night — not the one where your AI agent crashes with a stack trace, but the one where it succeeds at the wrong thi...
Join discussionMay 6 · 6 min read · When building production AI systems with CrewAI, the choice between specialist agents and orchestrator-worker patterns isn't just architectural—it's a decision that impacts cost, reliability, and scalability. Let me walk you through the concrete trad...
Join discussionMay 5 · 6 min read · The names have been changed to protect the innocent. :) A Fortune 500 retailer spent $5 million on GPUs and hired a team of Stanford PhDs to build their AI future. Six months later, they quietly disbanded the team. Not because the AI didn't work. The...
Join discussionMay 2 · 7 min read · In Part 1, we covered why traditional agents fail at scale and how the Skills architecture solves the Context Ceiling problem. In Part 2, we go further: what happens when a single agent — even a well-architected one with a mature skills library — is ...
Join discussionMay 2 · 6 min read · There is a dirty secret in the AI agent space that vendors do not advertise: their systems degrade badly as the number of available tools grows. If you have ever deployed an agent in production and watched it confidently select the wrong tool, or wor...
Join discussion
