About

My work sits at the intersection of AI, product, and execution, turning ideas into practical, high-impact solutions. I'm on the founding team at KaDeep AI, building AI agents for Engineering Release Confidence: agents that use your product like a real customer, on every surface and in every language, and deliver a release decision backed by evidence.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Maker History

  • KaDeep AI
    KaDeep AIAI QA, localization and accessibility to know when to ship
    Nov 2026
  • 🎉
    Joined Product HuntSeptember 16th, 2026

Forums

Who makes the final go/no-go call on your releases, and what do they look at?

A question for anyone who ships software.

On every team I've worked with, the final "ship it" was a judgment call in a meeting. QA said green. Translations were "done". Nobody had looked at accessibility since the last audit. Each report was fine on its own, and the bugs that hurt us were sitting in the gaps between them.

AI made the building part much faster. The deciding part is still the same meeting.

So how does it work on your team?

•

3h ago

How do you make your AI-generated websites stand out from the rest of the internet?

  • I'm seeing website developers having less and less work to do.

  • At the same time, more and more websites are starting to look identical (the typical purple colour palette and standardised AI-generated templates).

  • When it comes to AI website development, Lovable, Bolt, Replit, and Vercel have grabbed a significant share of the market.

Are there still people building websites the old-school way, or has everyone switched to AI?

But more importantly:

AI more than tripled the code. Releases rose 30%. Usage didn't move. Where's your bottleneck now?

A new study puts numbers on something a lot of us feel: writing code got cheap, and almost nothing after it got any faster. I'd like to hear where the slowdown sits for your team.

I've been reading "Writing Code vs. Shipping Code," an NBER working paper by Mert Demirer (MIT Sloan), Leon Musolff (University of Pennsylvania) and Liyuan Yang. It follows GitHub developers before and after they adopted three generations of AI coding tools: autocomplete, interactive agents that edit alongside you, and autonomous agents that work on their own.

The headline from the revised version on NBER's site (September 2026): cumulative increases in commits of about 30%, 180% and 240% across those three generations. Then the gains shrink at every step down the line. The 240% in commits becomes about 80% more projects and about 30% more actual releases. An earlier May draft had different commit numbers, but the same shape and the same roughly 30% on releases.

The part that stuck with me is the app stores. The authors looked at four marketplaces (Apple's App Store, Google Play, the Chrome Web Store and SourceForge) and found a sharp rise in new apps, but no increase in total usage. More things shipped. People didn't use more things.

View more