This isn’t just “explore a CSV” — you can build full, interactive workflows (with AI) by connecting nodes (joins, transforms, reconciliations, agings, etc.), and inspect/modify the DuckDB SQL at every step.
Still very early and intentionally constrained (CSV-only, no persistence), but I’m especially interested in:
- workflows people repeat monthly
- primitives that feel missing
- points where the node model breaks down
Really interesting! The chat-command approach feels faster than hunting through indicator menus. When do you plan to add real time data (i.e. from Polygon as an example) Is your thought process to essentially use this for folks to learn (i.e. add MACD, EMA etc. and then have it explain them on live let's say 1 minute charts)? Also, curious how will the Plaid integration will work out, let's say to add your holdings from robinhood (or Schwab, etc.) - will it monitor, and/or interact with your holdings via chat/chart(s), etc?
This isn’t just “explore a CSV” — you can build full, interactive workflows (with AI) by connecting nodes (joins, transforms, reconciliations, agings, etc.), and inspect/modify the DuckDB SQL at every step.
Still very early and intentionally constrained (CSV-only, no persistence), but I’m especially interested in: - workflows people repeat monthly - primitives that feel missing - points where the node model breaks down
Appreciate the thoughtful feedback so far.