Using the workflow

This section describes how to use the research workflow day to day, assuming everything has been installed (see the Installation and Extensions sections).

The workflow has three phases. Phase 3 is handled by tooling; phases 1 and 2 involve you.

PhaseWhat happensYour role
1 — Cast wideItems flow into Zotero _inbox from three sourcesForward items from the feedreader or share directly from iOS
2 — FilterClaude Code presents each _inbox item with a relevance score and summary; you decideGo / No-go per item
3 — ProcessClaude Code writes a structured literature note to the Obsidian vaultReview the generated note

Three sources into Zotero _inbox (Phase 1)

All items that enter the workflow pass through Zotero _inbox first. They arrive from three distinct sources:

SourceWhat it isFiltering before _inboxPhase 2 treatment
1. FeedreaderAggregated RSS/YouTube/podcast feeds scored daily by feedreader-score.py; you browse the HTML reader or NetNewsWire and forward interesting itemsPartly autonomous (scoring algorithm), partly manual (your click)Standard Go/No-go
2. iOS share sheetItems you share directly from YouTube, Overcast, Safari, or NetNewsWireDone by you — you consumed or deliberately selected the itemLighter: you already pre-filtered
3. Desktop / email / notesManual additions from any other sourceNone — comparable to source 1Standard Go/No-go

Key distinction: items from source 2 arrive after you have already read, watched, or listened to them (or deliberately chosen them in NetNewsWire). The Phase 2 Go/No-go step is therefore lighter for these items. Items from sources 1 and 3 still need a full Phase 2 review.

One nuance for source 2: if you click an item in the feedreader HTML reader and then share it to Zotero via iOS — without having read it fully — it still needs proper reading before a Go in Phase 2. The share action is not always a signal that the content has been consumed.


Current state: calibration mode

The feedreader is in calibration mode until its scoring threshold is stable. During this phase:

  • The feedreader runs automatically but does not yet route items to Zotero _inbox on its own.
  • You browse the HTML reader daily and give feedback signals: click on interesting items (and add them to Zotero) for positive signals, press 👎 on irrelevant items for explicit negative signals.
  • feedreader-learn.py processes these signals every morning at 06:15.
  • Once ≥30 positive signals have accumulated, feedreader-learn.py will recommend an initial threshold.

Future state: autonomous mode

Once the threshold is set, the feedreader will route items above the threshold automatically to Zotero _inbox without any action from you. The HTML reader stays available as a transparency window and as an ongoing calibration channel — occasional browsing in NetNewsWire and sharing items to Zotero continues to refine the threshold over time.

See Roadmap for the remaining steps.