About

I've spent the last few years building products across SaaS, AI and business systems, including a SaaS product that reached ~$145K ARR and independent builds that brought in ~$50K–60K in project revenue. Now I'm building Reehers, where beginners learn to create content by practising it privately before they post publicly. Most people quit creating because their first attempts are in front of everyone. Reehers fixes that. I like products that solve a visible pain and become hard to replace once adopted. Always happy to swap notes with other builders.

Badges

Tastemaker
Tastemaker
Veteran
Veteran
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
View all badges

Maker History

  • Ryft
    RyftA workout tracker built for friends who train together
    Oct 2026
  • Skitre
    SkitreAI-Powered Talent Development
    Nov 2023
  • 🎉
    Joined Product HuntSeptember 22nd, 2018

Forums

•

19d ago

agents score 80% on isolated tasks but 38% maintaining a codebase. does that match what you see

reading the end of software engineering paper (arxiv 2606.05608). its own benchmark has agents above 80% on one-off tasks and at most 38% when they maintain a codebase over time, because early mistakes carry forward. writing code got cheap, keeping a system correct didnt. feels like the real job is now writing intent down clearly and checking agent output with a different method than the one that wrote it. are you spending more time writing code or reviewing what agents wrote?

•

19d ago

whats one action you never let an ai agent take without a human check

whenever i give an agent write access i keep the riskiest action behind a separate check it cant talk its way past, because a prompt injected request looks exactly like a normal one. routing is plain code, the llm only writes the message. where do you draw the line, payments, sending emails, db writes?

•

23d ago

running parallel coding agents on one repo, how do you stop them stepping on each other

been running a few coding agents at once and the dumb failure is one nuking anothers uncommitted changes. worktree per agent fixed most of it for me but merging back is still manual. how are you doing it, separate worktrees, separate branches, or just one agent at a time

View more