Journal Backlog Processing Directions¶
How to run Running Notes backlog pipeline — cluster review, routing proposals, rewrite presentation
When to use¶
user wants to process or clean up their Running Notes backlog
Slash command: /wb-journal-backlog
Linked workflow: daily-journal/process-backlog
Related capabilities¶
journal/running_notesjournal/vault_write_at_location
Directions¶
Start via mcp__work-buddy__wb_run("process-backlog"), then advance with wb_advance.
Default to today's journal unless a different date is specified.
Cluster review rules¶
- High confidence (cohesion >= 0.7): Accept unless obviously wrong
- Medium confidence (0.5-0.7): Check thread summaries -- do they belong together?
- Low confidence (< 0.5): Likely need splitting
- Uncertain edges with strength > 0.55: Seriously consider moving that thread
- Singletons: Should any join an existing cluster?
Present: "I found N clusters. M look correct, K need your input."
Routing proposals¶
For each unit: use semantic_search to find relevant vault location, use context for type guesses, flag cryptic items as low confidence, note staleness for completed work.
Rewrite presentation¶
Before rewriting Running Notes, present before/after summary. Thread ID tags are removed (processing artifacts). This is a filesystem write -- consent required.
Don'ts¶
- Don't run in the background -- requires active participation
- Don't skip cluster review -- bad grouping cascades into bad routing
- Don't auto-route without user confirmation
- Don't pressure to process everything -- partial processing is fine
- Don't restore carried-over banners
- Don't create new organizational systems during this workflow
Related blindspots¶
- Insight hoarding: this workflow directly addresses it. Start with easy items to build momentum
- Infrastructure displacement: if user redesigns task system mid-triage, name it and redirect
- Branch explosion: routing may reveal many live threads. Don't solve that here -- make it visible