Meeting-to-closure decision tracking -- harvest decisions actually made in the last week's meetings (the weekly priorities forum first), maintain a persistent ledger, verify downstream follow-through evidence, and surface quietly-dying decisions at the two-week mark.
Monthly red-team pass over the user's active big bets -- build the strongest evidence-backed case AGAINST each position they're invested in (steelman opposition, not strawman compliance), ending each bet with an honest KILL / HEDGE / PROCEED-EYES-OPEN verdict.
Weekly knowledge-graph curation loop -- freshness sweep against the week's reality, stale-edge invalidation, pending-merge queue drain, and org-chart temporal completeness against your authority model.
PM Weekly Triage
Decision radar + dossier generator -- detect decisions approaching the user in the next few days and build evidence-backed dossiers (prior positions, stakeholder map, constraining commitments, what it gates) before the moment arrives.
Draft-first email posture -- high-priority emails and key-contact unreplied threads arrive each morning WITH a reply already drafted in the user's voice. The user edits-and-sends or discards instead of starting cold. Drafts only, never sends.
Weekly self-retrospective -- grade Edwin's own performance against a fixed rubric, re-score past lessons for behavioral gain, and land corrections as mechanical checks or harness diffs (prose memory as fallback)
Corpus distillation -- pick one high-value stable corpus, generate a synthesis study file (narrative, current state, key decisions, anticipated Q&A with citations) into memory/distilled/ so retrieval can answer multi-hop questions that chunk retrieval misses.