LLM
3 articles
Agentic AI in Production: What I Learned Building Tool-Calling Workflows
Production lessons from building agentic AI with OpenAI tool-calling and structured outputs. Architecture, failure modes, guardrails, cost controls, and everything the tutorials leave out.
Building a RAG Pipeline That Actually Works
A production-focused guide to building Retrieval-Augmented Generation pipelines with Python and FastAPI. Covers chunking strategies, embedding models, vector search, prompt construction, and the stuff that breaks when you move past the tutorial stage.
How Local LLMs Replaced $300/Month in OpenAI Costs
A practical breakdown of when to move AI workloads from OpenAI APIs to local models. Real cost math, production code, and an honest look at when it's not worth the trouble.
