Back
X (formerly Twitter) February 17, 2026

Garry Tan (@garrytan) on X

My Thoughts

I find it fascinating to see how others use modern AI tooling like Claude Code. The idea that you can configure your instructions well, almost like a well thought out onboarding, and then just get vastly better results and save tons of time is honestly not spoken about enough. I think the highest delta thing that can be done right now is optimising your Claude code or other agentic coding setup. Not just instructions, but also, custom commands, custom skills, off the shelf MCPs, custom MCPs where needed. This is a no brainer in terms of ROI.
Garry Tan (@garrytan) on X

Visit Link

https://x.com/i/status/2020072098635665909

I use a very specific prompt to push Claude to check its work and do a lot of testing and thinking about perf and refactoring. I find I can do big features (4K LOC+ with full testing) in about an hour.

You might also like

A Developer's AI Workflow: From Voice Dictation to Automated Reviews
blog

A Developer's AI Workflow: From Voice Dictation to Automated Reviews

The AI toolkit and workflow behind building three repositories, 347 commits, and a full-stack portfolio in under a month of part-time work — Claude Code, voice dictation, automated reviews, and more.

Building an efficient Content Pipeline with Claude Code: From PRs to Blog Drafts
blog

Building an efficient Content Pipeline with Claude Code: From PRs to Blog Drafts

I built a system that scans my GitHub PRs weekly, identifies content-worthy work, and generates blog drafts automatically. I call the pattern Quasi-Claw. I built a system to solve a problem most developers share: doing interesting work every week but never writing about it. The pattern — slash commands + LaunchAgents + CLI execution — turns Claude Code into a lightweight scheduled agent without any heavy framework or infrastructure. Here is how it works: 📅 The Trigger: Every Friday at 5pm, a macOS LaunchAgent triggers Claude Code. 🔍 The Scan: It scans my GitHub repos and scores PRs/commits for "content potential." 💬 The Summary: It sends me a Slack digest of the week's best stories. 🚀 The Execution: I run a single command to pick an idea, generate a full blog draft from the actual source code, and push it to my site’s API. The meta proof it works? This very post was identified and drafted by the system itself. #ClaudeCode #AI #BuildInPublic #Automation #SoftwareEngineering

Building an AI Portfolio Agent with Laravel, pgvector, and Gemini
blog

Building an AI Portfolio Agent with Laravel, pgvector, and Gemini

A chatbot that knows everything I've written — built with the Laravel AI SDK, pgvector embeddings, hybrid search, and Gemini's free tier.

All Shares
Next Visit Original