-rw-r--r--1.4KApr 20
›Building an AI Agent with Tool Calling: Lessons from Production
Function calling sounds simple in the docs and breaks in fascinating ways once real users hit it. Here's what I learned shipping an LLM agent to production.
grep -l '#AI' ./blog/*.md
blog
total 4 entries
-rwxr-xr-x1KApr 08
›RAG vs Fine-Tuning: When to Use Which (and When to Use Both)
Every AI project hits this fork. The honest answer is more nuanced than the Twitter takes suggest.
-rw-rw-r--1.1KMar 22
›Running LLMs Locally with Ollama: A Practical Workflow
Local LLMs went from "toy" to "genuinely useful" in 2024. Here's the setup I use daily for prototyping without burning OpenAI credits.
drwxr-xr-x1KMar 05
›Evals Are the Most Underrated AI Engineering Skill
Anyone can build an LLM demo. Shipping an LLM product means knowing if it actually works. Evals are how you know.