All activity
Most mentors get flooded with coffee chat requests. Most people hesitate to reach out because they feel they have nothing to offer in return.
ImpactChat solves both: every 1:1 session comes with a direct donation to an NGO of the mentor's choice — UNICEF, GiveDirectly, WWF, and more. Minimum $10.
Real conversations. Real impact. The Pay-It-Forward culture, finally systematized.
ImpactChatCoffee chats that fund NGOs — min $10 per session
Janggeun Leeleft a comment
I've done hundreds of coffee chats over the years. When people tried to send me gift cards as thanks, I always said: "Pass it on to someone who needs it." ImpactChat is that idea, turned into a platform. Book a mentor, pay it forward to an NGO. Simple as that. Happy to answer any questions — and yes, I'm the first mentor on the platform 😄
ImpactChatCoffee chats that fund NGOs — min $10 per session
Janggeun Leeleft a comment
alive-analysisTraceable AI analysis for Claude Code & Cursor. Open source.
Janggeun Leestarted a discussion
Just launched alive-analysis — traceable AI analysis workflows (Claude Code & Cursor, open source)
Hey everyone, I just launched alive-analysis — an open-source workflow kit that runs inside Claude Code and Cursor. Problem: you ask AI to analyze something, get a good answer, then a month later nobody can explain why we concluded what we did. Chat is gone and the logic isn’t reproducible. alive-analysis fixes that by turning the agent into a structured analysis partner. Instead of one-shot...
When you ask AI to analyze data, you get an answer—but a month later nobody can explain why. alive-analysis is an open-source workflow kit for Claude Code and Cursor. 5-step loop (Ask, Look, Investigate, Voice, Evolve), Git-tracked Markdown, checklists for confounders and Simpson's paradox. Quick and Full modes. Free. Install: clone repo, run install.sh, then /analysis-init and /analysis-new in the agent chat.
alive-analysisTraceable AI analysis for Claude Code & Cursor. Open source.
Janggeun Leeleft a comment
I kept running into the same problem: ask Claude or an AI to analyze something, get a good answer, then a month later nobody (including me) could explain why we concluded what we did. Chat was gone and the logic wasn’t reproducible. So I built alive-analysis to structure the process instead of replacing it — a 5-step loop (ALIVE), Git-tracked Markdown outputs, and checklists so we don’t skip...
alive-analysisTraceable AI analysis for Claude Code & Cursor. Open source.