e1108b6112
Adds corporate memory v1 (verification flywheel + contradiction detection + confidence scoring) and v1.5 (audience-based distribution + per-item privacy + admin curation). Server: GET /api/memory/bundle returns mandatory + ranked-approved items within a token budget; POST /api/memory/admin/mandate accepts an audience field gated against user_group_members; /api/memory/stats uses SQL aggregation. CLI: da sync writes received items to .claude/rules/km_*.md. Verification detector extracts knowledge candidates from session JSONL files. Auto-tagging via Haiku when ai: is configured. Adapted from the v9-era branch onto v13/v14 RBAC: _is_privileged_viewer + _effective_groups now query user_group_members JOIN user_groups; require_role(Role.KM_ADMIN) replaced with require_admin (km_admin collapsed into admin). Schema v15: knowledge_items context-engineering columns + knowledge_contradictions + session_extraction_state. Schema v16: verification_evidence. Cuts release v0.15.0 (also bundles #116 /me/debug page).
7 lines
786 B
JSON
7 lines
786 B
JSON
{"role": "user", "content": "Show me the NPS scores."}
|
|
{"role": "assistant", "content": "The NPS score for last quarter was 45."}
|
|
{"role": "user", "content": "Not quite. We use a rolling 90-day NPS, not quarterly. The current score should be around 52."}
|
|
{"role": "assistant", "content": "I see, let me recalculate using a rolling 90-day window."}
|
|
{"role": "user", "content": "Also, FYI, our retention metric is defined as the percentage of users who are active in month N who were also active in month N-1. We call it MAU retention."}
|
|
{"role": "assistant", "content": "Thank you. I'll use rolling 90-day NPS and MAU retention = active_month_N intersect active_month_N-1 / active_month_N-1."}
|
|
{"role": "user", "content": "Perfect. Now compare NPS to retention over the last 6 months."}
|