PM Cross-Board Intelligence (G2 -- cross-board reasoning infrastructure)
Shipped backend infrastructure that aggregates every Mission Control board into materialized snapshots across hot, warm, and cold computation tiers, so higher-level features read pre-computed numbers instead of querying live. It backs template-based natural-language answers, per-board seasonal urgency, lead-time tracking, and three tiers of detected patterns.
What it is
Shipped backend infrastructure for cross-board reasoning, natural-language querying, seasonal urgency, lead-time tracking, and pattern detection. It has no screen of its own: it is the shared reasoning layer that higher-level features read from.
Where to find it
Nothing here is Lab-gated -- it ships, but as backend infrastructure, so you meet it through the
features that consume it rather than by opening it directly. It is feature-gated as
pm-cross-board-intelligence (pmCrossboardIntelligenceEnabled), and all computation and IPC
handlers are no-ops when disabled.
How it behaves
It aggregates data across all PM boards into materialized snapshots that higher-level features (narrative queries, dashboards, AI recommendations) read from.
It runs three computation tiers:
- Hot -- event-driven (on board sync), sub-second recompute for the synced board plus cross-board snapshots.
- Warm -- every 10 minutes, refreshes all board snapshots and runs pattern detection.
- Cold -- daily with chunked processing (50 boards/batch), full cleanup of expired snapshots and patterns.
Key subsystems
- Narrative queries -- natural-language answers built from templates (deterministic, no model call for the answer itself). One step can use a model: classifying a question the templates do not recognise as a known intent. That fallback is capped at 50 classifications and $1 of model spend per day (resetting at local midnight), and when either is reached — or when no API key is configured — the question simply gets the ordinary "I don't recognise that — try rephrasing" answer. The cap is never reported, so a question that would have been understood earlier in the day reads exactly like one that was never understood at all.
- Seasonal calendar -- per-board quarterly urgency multipliers.
- Lead-time tracker -- SOP-derived lead-time configs and status-transition observation tracking.
- Pattern detector -- three tiers of patterns (operational, strategic, predictive) with TTL expiry.
- Feature gate -- all IPC handlers check
requirePmEnabled()(no multi-tier permission model is implemented).
For agents
- Module in
src/main/services/pm/intelligence/. - 14 IPC channels in
pm-intelligence-handlers.ts. - 5 database tables (
pm_intelligence_snapshots,pm_seasonal_calendar,pm_lead_time_configs,pm_lead_time_observations,pm_detected_patterns). - All reads come from pre-computed snapshots, never live queries at read time.
- 141 tests (87 unit + 54 integration).
- Contract:
pm-cross-board-intelligence-contract.md.
Related
The boards whose data is aggregated here are described in mission-control.md. The gate that decides whether a board has accumulated enough usage to be reasoned about at all is pm-data-density.md, and the suggestions that turn those patterns into inbox cards come from pm-discovery-callouts.md. The forecasts and risk views built on this snapshot layer are in pm-predictive-analytics.md.
Last verified 2026-09-28