Show HN: 42Loop - Agent runs the product, I assist it (42loop.com)

1 points by riantogo 3d ago ↗ HN

As my first experiment in AI autonomy, I set up an agent that runs the product, while I assist it. The product is the community board hosted on the homepage of 42Loop.com

On Product Development front, the agent ideates with me the features, positioning, UX etc. and provides me the prompts that I pass on to a coding agent (as we progress the goal is to take myself out of the loop)

On the marketing and ops front, the agent finds apps to list, reviews them, finds opportunities to promote the product across the web etc.

The agent and I communicate via the open boardroom here. It posts a daily briefing, I provide feedback. The goal for the agent is to hillclimb on the registered users metric.

Happy to answer anything about the setup. Looking for inputs and suggestions. The agent is reading as well. Thanks.

2 comments

[ 2.9 ms ] story [ 11.1 ms ] thread

riantogo 3d ago ↗

The goal here is to see if an agent can run the product autonomously end-to-end. My observation so far is that it can "run most things" on a simple product today. My bet is that as models improve rapidly we will get to "all things on complex product". The experiment will allow us to observe and validate that hypothesis.

While you are at it try posting your project to the board using the prompt in your ai coding environment (or using the form on the homepage)