Omniscio documentation
Browse all documentation
  1. Getting Started13
  2. Sessions & Agents115
  3. Inbox & Notifications59
  4. Projects & Tasks95
  5. Automation & Scheduling75
  6. Knowledge & Memory26
  7. AI Features60
  8. Integrations100
  9. Plugins & Marketplace33
  10. Cloud & Teams56
  11. Settings & Customization58
  12. Account & Billing28
  13. Troubleshooting84
  14. CLI & API Reference22
  15. Legal & Policies4
  16. Uncategorised22

PM Predictive Analytics (G9 -- velocity, forecasts, risk)

An in-development predictive analytics layer for PM boards: velocity tracking over a configurable window, Monte Carlo completion forecasts, what-if scenarios with resource, priority and deadline levers, and risk heatmaps with cascading cross-board impact.

What it is

In-development predictive analytics layer: velocity tracking, Monte Carlo completion forecasts, what-if scenarios, and risk heatmaps.

Watches how fast work moves through PM boards and produces four kinds of predictions:

  • Velocity tracking -- counts completed items over a configurable window (default 14 days). Trend uses 7-day buckets with linear regression to classify direction as increasing, decreasing, or stable.
  • Monte Carlo simulation -- runs 1000 simulations per board. Each simulation samples a per-item velocity from empirical data (>= 10 observations) or a triangular distribution from best/typical/worst estimates (< 10 observations). Extracts p50/p85/p95 completion dates and deadline-hit probability.
  • What-if scenarios -- three lever types: resource (velocity multiplier), priority (item reorder), deadline (day shift). Cascades impacts to related boards via parent-item relationships and blocking lead-time configs.
  • Risk heatmap -- four dimensions per board, each clamped to [0, 1]: overdue risk (0.3 weight), velocity risk (0.25), bottleneck risk (0.25), dependency risk (0.2). Overall = weighted sum.

Where to find it

In-development, gated behind the pm-predictive-analytics unreleased feature (pmPredictiveAnalyticsEnabled). Background computation is gated; IPC handlers respond unconditionally but the renderer widgets are not yet mounted.

How it behaves

Results are cached in the G2 snapshot store and refreshed on a three-tier scheduler: hot (on board sync), warm (15 minutes), cold (24 hours with 90-day velocity data retention).

For agents

Frontend widgets

Three widgets in src/renderer/src/features/pm-ops/:

  • PredictiveDeadlineWidget -- p50/p85/p95 dates, confidence source badge.
  • VelocityTrendWidget -- current velocity, trend arrow, sparkline.
  • RiskHeatmapWidget -- boards sorted by overall risk, expandable breakdown.

Technical details

  • Service layer in src/main/services/pm/predictive-analytics/ (velocity engine, Monte Carlo engine, what-if engine, risk heatmap, observation wiring, prediction scheduler).
  • 7 IPC channels under pm:predictive:* namespace.
  • 4 CLI routes under /pm/predictive/* (velocity, velocity/trend, monte-carlo, risk-heatmap) — gated on missionControlEnabled.
  • Data in pm_velocity_history table + pm_intelligence_snapshots (shared with G2).
  • Observation wiring bridges R65 time-in-stage with G9 via dispatchPostSyncSideEffects.
  • Contract: pm-predictive-analytics-contract.md.

Related

The widgets this layer produces are mounted in the Ops Engine panel, documented in pm-operations-engine.md, and the PM Advisor surfaces the same completion forecasts as plain-language narratives — see pm-intelligence-advisor.md. Its cross-board view of the data is described in pm-cross-board-intelligence.md. The full list of library pages is in INDEX.md.

Last verified 2026-09-23