Amir Mehrabi

The interesting distinction here is between generating cards and deciding what deserves reinforcement. Turning any webpage into cards removes capture friction, but the real value is synthesis: can The Sponge identify which ideas connect, conflict, or matter enough to revisit? That would make spaced repetition feel less like a bigger queue and more like knowledge compounding.

Filed. Tagged. Searchable. Inert.

Waiting for a version of you who has time to go back and look. That version isn't coming.

For thirty years the industry sold one fix: capture more, structure better, maintain harder. It produced 210,000 people in a single forum asking the same question I built an elaborate system and abandoned it, what am I doing wrong?

Nothing. Capture was never the problem. Synthesis was.

How much time do you waste every day updating your AI agents with company context?
I spend 40 minutes every morning re-explaining my company to Claude, then doing the same for ChatGPT. By the time AI actually understands my business, half my free quota is gone on background information. Not real work.
CLAUDE.md files go stale. Claude Projects doesn't know what happened on Slack last night. ChatGPT Memory only works inside ChatGPT. None of them talk to each other.
We're building FlowTask to fix this connect WhatsApp, Slack, Gmail, approval layer on top so personal stays personal, and any AI agent reads from the same brain via MCP simultaneously.
Launching on Product Hunt on July 28th. Anyone else feel this pain?