Story

Hi HN — I’m exploring an idea and would love your feedback.

I’m a builder and user of Obsidian, validating a concept called Concerns. Today it’s only a landing page + short survey (no product yet) to test whether this pain is real.

The core idea (2–3 bullets):

- Many of us capture tons of useful info (notes/links/docs), but it rarely becomes shipped work.

- Instead of better “organization” (tags/folders), I’m exploring an “action engine” that:

  1.detects what you’re actively targetting/working on (“active projects”)

  2.surfaces relevant saved material at the right moment

  3.proposes a concrete next action (ideally pushed into your existing task tool)

Before writing code, I’m trying to pin down two things:

- Project context signals (repo/PRs? issues? tasks? calendar? a “project doc”?)

- How to close the loop: ingest knowledge → rank against active projects → emit a small set of next-actions into an existing todo tool → learn from outcomes (done/ignored/edited) and optionally write back the minimal state. The open question: what’s the cleanest feedback signal without creating noise or privacy risk? (explicit ratings vs completion events vs doc-based write-back)

What I’m asking from you:

1.Where does your “second brain” break down the most?

capture / organization / retrieval / execution (If you can, share a concrete recent example.)

2.What best represents “active project context” for you today?

  task project (Todoist/Things/Reminders)

  issues/boards (GitHub/Linear/Jira)

  a doc/wiki page (Notion/Docs)

  calendar

  "in my head"

3.What’s your hard “no” for an AI that suggests actions from your notes/links? (pick 1–2)

  privacy/data retention

  noisy suggestions / interruption

  hallucinations / wrong suggestions

  workflow change / migration cost

  pricing

  others