Technical insights, engineering perspectives, and lessons learned from building software systems.
Content Strategy
This blog covers AI topics (often building on AI Lab experiments), general software engineering, career reflections, and tool evaluations. Content may move between the blog and AI Lab Developer Resources, or appear in multiple places when relevant—AI Lab is living documentation, blog posts are polished insights, and Resources are curated references.
Every LLM agent starts the same way: a model calling tools in a loop. Build a weather bot? Easy. Create a code reviewer? Works fine. But try to build an agent that writes a feature across multiple files, runs tests, debugs failures, and iterates—suddenly your simple loop falls apart.
A comprehensive, step-by-step guide to installing, configuring, and mastering the Jupyter AI chat to supercharge your productivity.
Google's new File Search Tool for Gemini API delivers production-ready RAG with zero infrastructure—upload PDFs, query with natural language, and get grounded answers with source citations in minutes.
Kimi K2 Thinking is Moonshot AI's flagship open-source thinking model, delivering competitive performance on complex reasoning, coding, and agentic tasks with a 256K context window and impressive autonomous capabilities.
OpenAI Agent Kit packages opinionated utilities for building production-ready AI agents—wrapping model calls, tool routing, and evaluation in a way that scales from quick prototypes to real apps.
This blog post tracks some of the AI code assistance CLI's that I'm trying out so I can remember what clicked, what still feels rough, and how to reinstall them on a fresh machine.
The GitHub CLI (gh) brings GitHub's pull requests, issues, releases, and workflows straight into your terminal so you can stay in flow without leaving the command line.
After years of building software, I've created this site to consolidate my professional work and share technical insights. It's part portfolio, part lab notebook.