Bartosz Strickland

In the past few months, I have come to learn that building products isn't all about adding features.

Every single idea seems necessary.

Every single feature seems to be essential to improving the product.

However, each new feature brings along complexity, new use cases, delays its release and makes development harder.

Obviously, both are critical for survival. But which one actually moves the needle?

On one hand, you can prepare an incredible go-to-market strategy, but what good is it if your execution falls flat? If you don't have time to be consistent, your messaging is confusing, and your visuals are boring, nobody stays long enough to care about your plan.

Autonomous AI agents can already browse websites, call APIs, use external tools, and complete tasks with limited human involvement.

Payments are still a major interruption. When an agent encounters paid data, an API limit, or premium content, it usually has to stop and ask a person to complete the transaction.

I m curious how makers think this should work in practice.

Should an agent: