General
p/generalShare and discuss tech, products, business, startups, or product recommendations
trending
•

1yr ago

What’s the most unconventional way you’ve ever come up with a business idea?

Hey Product Hunt community!

We all know the classic ways to brainstorm startup ideas scratching your own itch, spotting market gaps, or improving on an existing product. But sometimes, the best ideas come from unexpected places.

•

3mo ago

Why isn't there one place where founders consistently ask and answer startup questions?

I've been thinking about this lately.

Every founder has questions, whether it's about hiring, fundraising, getting the first 100 customers, pricing, AI, operations, or simply making difficult decisions.

How do you evaluate AI agents before trusting them with real users?

Building an AI agent is one thing, but deciding when it's actually ready for real users is much harder.

Unlike traditional software, an AI agent can perform perfectly in testing and still behave unexpectedly when it encounters new situations in production.

I'm curious how other teams approach evaluation before deployment.

Do you rely on benchmark tasks, automated evaluations, human reviewers, simulated user interactions, or something else?

•

2mo ago

Have you been a victim of AI Flop Loop?

How does it go? You are looking for something, so you ask an AI assistant to find more info, but you are unconvinced by the findings.
Then you find a credible source, but it quotes the findings you weren't convinced by in the first place as its primary source.

How do you monitor AI agents once they're in production?

Shipping an AI agent is only the beginning. Once it's being used by real users, monitoring becomes just as important as development.

Traditional software monitoring focuses on uptime, latency, and errors, but AI agents introduce additional questions. Are they making good decisions? Are tool calls succeeding? Are they completing tasks efficiently? Are they getting stuck or behaving inconsistently?

•

4mo ago

The missing primitive in agent memory is not retrieval. It is expiry.

Almost every agent memory system I see is built to remember more and find it faster. Nothing in any of them knows how to stop believing something. A note that says "we tried X, it did not work" is written once and then never expires. Nothing in the system changes on the day it stops being true. It just sits there, gets retrieved, and reads as more authoritative every time it survives another run. A system that only accumulates gets more confident and less correct at the same time, which is a genuinely nasty combination because the confidence is the part people can see. There is a smaller version of this that shows up constantly. When an agent runs out of context mid task, everyone reaches for a handoff note, and handoff notes work strangely well. Worth asking why, because the agent had far more information available than the note contains. They work because they are lossy in the right direction. A note keeps the decision and throws away the reasoning that produced it. The raw context does the opposite: it keeps everything, including the three wrong turns that got corrected later, and restoring it restores the confusion along with the conclusion. So decisions and context are two different objects and most memory work treats them as one. A decision is "we went with X over Z because Y". Context is the forty thousand tokens of finding that out. Only one of those is worth carrying forward, and it is not the big one. What I actually want is a memory entry that carries the conditions under which it was true, so it can be invalidated by the world changing rather than by someone remembering to go and delete it. Nobody is asking a knowledge base to forget. Curious whether anyone here has shipped expiry properly, and what triggered it. Time, contradiction, or someone noticing by hand?

•

2mo ago

5 things nobody tells you about running a solo SaaS

1/ Your payment env vars can silently break because of a type mismatch you'll never see in the UI mine sent every "Upgrade" click to a landing page instead of checkout for who knows how long

2/ You will not notice a broken checkout button. Nobody reports it. They just... leave

3/ Your service worker will cache the broken version even after you fix it. You'll think you shipped a fix, but you didn't

Where do your notes from sales calls actually end up?

Mine used to go into three places at once. The CRM, a Notion page and a random Google Doc.

A week later I couldn't find the one thing I needed before the next call.

Now I think the problem was never taking notes. It was that nothing connected them to the next step.

•

4mo ago

5 house rules for letting AI agents commit code

Hey Makers!

Handing over repo access to autonomous coding agents is awesome, but honestly, it's also a great way to break things if you aren't careful.

My team recently set up a strict "Zero Trust" baseline to keep things under control. Here are the 5 rules we actually enforce right now:

  1. Bound the blast radius before the first run

  2. Assume it reads everything it can reach

  3. Treat everything the agent reads as a potential instruction

  4. Verify like it's a stranger's pull request

  5. Be ready to do forensics

•

2mo ago

How do you handle churn caused by silent disengagement rather than active dissatisfaction?

The most dangerous type of churn isn't the angry customer leaving detailed feedback it's the silent user who just quietly slips away.

When users cancel with a complaint, at least they tell you why. But most of our churned accounts simply stopped opening the app three weeks before they actually hit the cancel button.


For founders tracking retention data: what early warning metrics or behavioral triggers do you use to step in before an account goes completely cold?

First
Previous
•••
423424425
•••
Next