Leanne Thuong
Software Engineer & AI Tools Specialist
San Francisco, CA
About Me
I'm a software engineer who became obsessed with AI productivity tools. After spending thousands of hours testing tools for my own projects, I started documenting my findings to help other developers make informed decisions. My reviews are based on real-world testing, not press releases.
Areas of Expertise
Certifications & Credentials
Featured In
Recent Articles
View all articlesClaude Code Guide 2026: Terminal Agents, CLAUDE.md, Skills, and Hooks
Claude Code is Anthropic's agentic coding tool for the terminal, IDE, and CI. Here is a practical setup guide covering CLAUDE.md, skills, hooks, subagents, MCP, and when to use it versus an editor-first agent.
Context Engineering for Coding Agents: AGENTS.md, Rules, Skills, and Hooks
Prompt engineering is not enough once agents edit real repos. Context engineering decides what loads every turn, what loads on demand, and what is enforced by the harness. Here is a practical layer model for Cursor and Claude Code.
Claude Code vs Codex vs Cursor: Which Coding Agent Fits Your Workflow?
Three serious coding-agent platforms, three different centers of gravity. Compare Claude Code, OpenAI Codex, and Cursor by surface, customization, cloud work, and team fit -- without treating mixed benchmarks as gospel.
LLM Evals in CI: Promptfoo and DeepEval Without the Cargo Cult
Shipping an LLM feature without eval gates is like deploying without tests. Here is a practical guide to Promptfoo and DeepEval -- what each is good for, how to wire a CI gate, and how to avoid burning money on judge calls.
Prompt Caching for Developers: Cut LLM API Costs Without Gutting Quality
Prompt caching reuses stable prefixes so you pay less and wait less on repeated context. Here is how OpenAI and Anthropic caching work, how to structure prompts for hits, and which metrics prove you are actually saving money.
Skills and Hooks for AI Coding Agents: Stop Pasting the Same Playbook
If your team pastes the same release checklist into every agent chat, you are doing it wrong. Use skills for procedures and hooks for guarantees -- a practical playbook for Claude Code and Cursor-style agents.
Want to Work Together?
I'm available for tool reviews, sponsored content, and consulting on AI tools and developer productivity.
Get in Touch