Nabeel mohi ud din

We ve been heavily testing autonomous AI coding agents in our workflow. Last week, I asked our agent to implement a new authentication flow. It touched validation, authorization, and our database schema.

Within 4 minutes, it generated a 300 line diff. It also wrote new tests, and the CI pipeline came back perfectly green. On paper, it looked like a massive win.

But when my senior dev went to review it, we had to throw the whole thing out.

The problem wasn't the code itself it was the handoff. The agent gave us a massive wall of code with zero context. We couldn't tell why it chose a specific middleware approach, or why it structured the database write in a way that could eventually cause race conditions. We spent an hour trying to reverse-engineer its thought process before giving up and writing it ourselves.

Hey Product Hunt!

I have a confession: I have a love-hate relationship with voice dictation.

I love how fast it is. I hate that I spend just as much time deleting the "ums," "likes," and "uhhs" as I would have spent just typing the message. The built-in dictation on our phones just doesn't understand how humans actually speak.