Manan Shah's activity on Indie Hackers

Recent activity

Testing confirmation screens for clarity was the wrong test

Wrong test: "is this clear?" Right test: "did you catch the mistake?"

Where should the approval gate sit in an AI course workflow?

A few weeks ago, I shared Tweak on Indie Hackers when we launched the first version.

Did anyone actually pay you before you built the full product?

I built a guard for AI agents that act on stale information

I built this for myself. It worked, so I'm testing it inside PlanMoon.

"Never says it worked" gets harder to hold onto the longer nothing happens

"Never says it worked" gets harder to hold onto the longer nothing happens

A reply about email lists got me thinking about what I could actually offer!

Launching AgentRender — agent-native screenshot/PDF/extract API (MCP + REST), waitlist open

Free tests get generous answers. Paid tests get honest ones.

"Never says it worked" gets harder to hold onto the longer nothing happens

A reply about email lists got me thinking about what I could actually offer!

I built this for myself. It worked, so I'm testing it inside PlanMoon.

What I learned making my SaaS usable from the ChatGPT and Claude chat windows

I built a guard for AI agents that act on stale information

"It never says it worked" is a better test than I thought

My app can't be its own witness

"It never says it worked" is a better test than I thought