Notes from the build
The Blog
Build logs, prompt breakdowns and hard-won lessons from shipping production AI software with Claude.
video editing with ClaudeVideo Editing With Claude: 6 Effects Without After Effects
Video editing with Claude now covers the grade, the counter and the motion. Here are six effects and the one prompt line that makes them land.
Read article→
Reverse Engineer AnythingReverse Engineer Anything: Claude Can Now Rebuild Any App
Reverse Engineer Anything lets Claude look inside apps it has no code for. Here's how it works, who should skip it, and the software moat a copy can't take.
Read article→
AI agent skillsAI Agent Skills: 9 Free Ones and the Step Most Skip
AI agent skills install from one pasted link — that part is easy. The step that makes them genuinely useful is the one almost nobody runs.
Read article→
Jev decision modelJev Decision Model: The AI That Can't Write, Only Decides
The Jev decision model can't write a word. Vercel and LangChain added it anyway. Why a "System One" classifier is 200x faster than the LLM in your agent.
Read article→
open source SaaS alternativesOpen Source SaaS Alternatives: 5 Repos Worth Selling
Semrush charges $250. This costs ten.
Read article→
Claude AI side hustlesClaude AI Side Hustles: 5 That Fit Around a Full-Time Job
Claude AI side hustles work because your job already gave you the niche. Five that fit around full-time work, and the one thing that decides all five.
Read article→
agentic AI system designAgentic AI System Design: 9 Layers That Break in Production
Agentic AI system design is backend engineering, not prompting. The nine layers that decide whether your agent survives production.
Read article→
Model Context ProtocolModel Context Protocol: What It Is and Why It Matters
Model Context Protocol exists because your AI agent still cannot call an API. Here is the exact division of labor between the model, the client, and the server.
Read article→
agent harnessingAgent Harnessing: Why AI Agents Fail on Long Tasks
Agent harnessing is why long AI tasks finally finish. The fix isn't a bigger context window — it's a loop that never needs to remember.
Read article→
