Eason Zhou

Building feedback handoffs for AI work

About

I use Codex and Claude Code to make reports, decks and interactive HTML. I'm building PreApp so someone outside the Agent session can review that work, and the feedback comes back with the right version and location.

Links

GitHub

PreApp

Badges

Tastemaker

Gone streaking 10

Gone streaking

Gone streaking 5

Maker History

PreAppReview agent-made work. Return feedback to Agents.

🎉

Joined Product HuntFebruary 4th, 2024

Forums

p/htmldrag

•

1mo ago

Edit complex HTML visually without losing the structure

Existing HTML can look complete in a browser and still be difficult to edit. The challenge becomes clearer when one file combines standard HTML with SVG, Canvas, IFrame content, positioned elements, and nested tables.

p/ai-hive

•

1mo ago

For folks running AI in regulated industries, what's the audit trail level you actually need?

Audit trail is one of those features that sounds binary but isn't.

Levels I've seen requested:

- Basic: timestamp + user + action

p/openmarkdown

•

2mo ago

Do we need an phone app?

An phone app with sync'ed notes could be convenient, but we then lose the co-edit feature on the phone. It's more a quick notes. Eventually we can setup co-edit with the agent on the cloud. So phone can also enjoy the co-edit. Currently leave a todo for the agent on phone is definitely do-able.

Any thoughts?