LLM
3 articles
Agentic AI in Production: What I Learned Building Tool-Calling Workflows
Practical lessons from deploying AI agents with tool-calling. Hallucinated arguments, infinite loops, runaway costs, and the guardrails that actually prevent them.
Building a RAG Pipeline That Actually Works
Production-focused guide to building RAG pipelines with Python. Chunking strategies, vector search with pgvector, re-ranking, prompt construction, and the stuff that breaks 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.
