Use AI where it’s strongest: predicting, detecting, explaining, and recommending. Keep the schedule engine deterministic so every plan stays feasible.
Practical AI features you can implement without risking feasibility
AI suggests options; the optimizer enforces capacity, materials, skills, and due dates.
Deterministic estimation of processing and setup times, with uncertainty (P50 / P90) and a confidence signal based on your own history.
Deterministic what-if analysis: simulate uncertainty with a fixed seed and get KPI ranges (P50 / P90) — not just a single number.
Pre-solve quality gates catch broken inputs early (blocking issues vs warnings) so you don't waste solver time or ship misleading schedules.
Infer sequence-dependent setup times from your history (A→B differs from B→A) and generate a solver-ready changeover matrix with P50 / P90 and confidence.
Turn “raw inputs” into solver-ready inputs deterministically: apply improved times, merge inferred changeovers, and return clean deltas — with opt-in rollout before optimize.
Every suggestion comes with clear reasons and traceable artifacts so planners can trust what changes — and why.
Keep control: capture overrides, compare before/after, and improve future assists without autonomous takeovers.
Run assists in parallel, compare KPIs, then enable changes with opt-in controls and easy rollback.
See what AI would recommend — safely, transparently, and without changing your schedule.
Every AI output is recorded as a traceable event: what it suggested, when, and why.
Built to run in real factories: predictable performance, sensible limits, and safe data handling.
You stay in control. AI assists generate recommendations and explanations — planners decide what to apply.
Production-safe helpers with predictable behavior, clear failure modes, and exportable artifacts.
Same input = same output. Explainable artifacts. Solver-first integration that stays production-safe.
Validate inbound specs before optimizing (horizon sanity, resources/capacity, unique op IDs, precedence cycles). Fail fast with actionable errors.
Optional repair=true applies deterministic, safe fixes (clamps nonpositive times/capacity, fills missing setup_family, rewrites unknown pools). Cycles get a break-edge suggestion.
Deterministically enrich processing times and merge changeover matrix entries from observations. Supports tenant-scoped DB-backed sampling when enabled.
Ingest overrides as immutable events (idempotent), store before/after + metadata, and fetch recent edits ordered by occurred_at.
Infer deterministic tie-break weights from aggregated planner edit deltas (e.g., tardiness vs setups) and persist a latest profile per tenant/plant.
Export a deterministic “why scheduled this way” trace per operation (stable keys + reason codes). Store artifacts and return a presigned download URL.
Use an optional LLM to generate a concise report and analysis from KPIs, solver traces, and plan deltas — including risks, likely root causes, and recommended next steps.
Run deterministic multi-scenario what-if sweeps, rank scenarios with stable ordering, and persist results + artifacts for later review.
Estimate deterministic due-date hit probabilities per order (stable outputs for the same inputs). No ML dependency.
Concrete endpoints, predictable status codes, and copy/paste payloads — designed for production integration.
AI assists learn from your plan-vs-actual signals. PlanQuill connects to your ERP/MES and keeps schedules synchronized.
Native integration with SAP ECC and S/4HANA
Oracle ERP Cloud and E-Business Suite
Dynamics 365 Business Central
REST API for custom integrations
We start with one line or one planning area and prove measurable impact in weeks.
Trusted by industry leaders worldwide