Demand planning your CFO will actually trust
Perimattic Demand OS forecasts demand, optimizes inventory, and explains every number it gives you. Live in weeks, not years, with pricing you can see before you talk to sales.
$4.7–5.3B
Demand planning software market, growing ~10–11%/yr
Source: Mordor Intelligence & Grand View Research
$1.73T
Lost annually to stockouts & overstock industry-wide
Global retail inventory distortion. Source: IHL Group, 2025
20–50%
Forecast error reduction with AI-driven forecasting vs. traditional methods
AI vs. traditional forecasting. Source: McKinsey & Company
Your planners are still fighting spreadsheets
Manual forecasting hasn't fundamentally changed in 30 years. The cost of getting it wrong keeps rising.
Manual Excel-based planning
Version chaos, no audit trail, and endless "final_v3_FINAL.xlsx" files shared over email. One overwritten cell breaks the entire plan.
Stockouts & overstock
The $1.73T global inventory-distortion problem. Customers leave when you stock out. Capital ties up in the wrong SKUs when you over-order. Both happen simultaneously.
Siloed planning
Sales, Finance, and Ops each working off different numbers. The consensus meeting reconciles data instead of making decisions.
No early warning
No visibility into promotions, weather events, or competitor moves until it's too late. Reactive planning costs more than proactive planning every time.
One system that plans, explains, and adapts
Perimattic Demand OS is built for mid-market to lower-enterprise supply chain, demand planning, and operations teams who've outgrown spreadsheets but don't want a two-year rollout to find out if the AI actually works.
It replaces both spreadsheet-based planning and black-box AI tools, combining statistical and ML forecasting with a planner-first workbench, explainable outputs, and published pricing. You know what you're getting before you ever talk to sales.
Book a DemoBuilt around what actually breaks today
Every feature maps directly to a real failure mode in enterprise demand planning.
See the reasoning
Every forecast ships with its top contributing factors. Not a black box, a clear explanation your team can verify, override, and learn from.
Know the price first
Published price bands before any sales call. No NDA required to see a number. No "contact us for pricing" wall hiding what it actually costs.
Live in weeks
A defined SKU/location pilot goes live in weeks, not the 6–24 months typical of legacy planning suites. See results before committing to a full rollout.
Planners actually open it
Usability-tested with real demand planners. Designed for the people who run it every day, not just the executives who approved the budget.
Outcomes, not just accuracy
Tracks inventory dollars released and stockouts avoided, not just MAPE. Reports in the business metrics your CFO already recognizes.
How Demand OS works
A five-stage architecture that turns raw signals from your existing stack into executable plans, with full human oversight at every step.
Data Sources
ERP · POS · WMS · External signals
Connects to SAP, Oracle, Dynamics 365, NetSuite, Salesforce, Snowflake, and flat-file/SFTP feeds. Ingests structured demand history and external signals in one place.
AI/ML Forecast Engine
Ensemble statistical + ML models
Selects the best-fit model per SKU from ARIMA, exponential smoothing, gradient boosting, and neural approaches and explains which it chose and why.
Optimization Layer
Inventory · Safety stock · Supply
Translates forecast uncertainty into inventory targets, safety stock parameters, and prioritized replenishment recommendations across your network.
Planner Workbench
Collaboration · Overrides · Copilot
Where demand planners review, adjust, and collaborate. The AI Copilot surfaces plain-language explanations and anomaly alerts on demand.
Execution & Write-back
ERP write-back · PO generation
Approved plans push directly back to your ERP as purchase orders or production requirements. A full audit trail is maintained for every approved change.
Data Sources
ERP · POS · WMS · External signals
Connects to SAP, Oracle, Dynamics 365, NetSuite, Salesforce, Snowflake, and flat-file/SFTP feeds. Ingests structured demand history and external signals in one place.
AI/ML Forecast Engine
Ensemble statistical + ML models
Selects the best-fit model per SKU from ARIMA, exponential smoothing, gradient boosting, and neural approaches and explains which it chose and why.
Optimization Layer
Inventory · Safety stock · Supply
Translates forecast uncertainty into inventory targets, safety stock parameters, and prioritized replenishment recommendations across your network.
Planner Workbench
Collaboration · Overrides · Copilot
Where demand planners review, adjust, and collaborate. The AI Copilot surfaces plain-language explanations and anomaly alerts on demand.
Execution & Write-back
ERP write-back · PO generation
Approved plans push directly back to your ERP as purchase orders or production requirements. A full audit trail is maintained for every approved change.
Everything a demand planning team needs
Sixteen capabilities, four disciplines: from raw forecasting to governance and trust.
ML Forecasting
Ensemble of statistical and machine-learning models, auto-selected per SKU based on data patterns and forecast horizon.
Demand Sensing
Short-horizon signal detection using POS, order, and external data to sharpen the near-term forecast before the week closes.
New Product Forecasting
Cold-start forecasting for items with zero or sparse history, using analogous product matching and Bayesian priors.
ABC-XYZ Segmentation
Automatic segmentation by value and demand variability, so model selection, safety stock, and review cadence all match the SKU's profile.
Scenario Planning
Model optimistic, pessimistic, and most-likely demand scenarios side-by-side. Commit to a plan only when you've seen the range.
What-If Analysis
Adjust any driver (promotional uplift, price change, channel mix) and see the downstream inventory and supply impact instantly.
Consensus Forecasting
Sales, Finance, and Ops submit inputs into a single structured workflow. One number, full traceability, no more spreadsheet reconciliation.
Promotion Planning
Model promotional uplift, cannibalization across SKUs, and halo effects so your promotional forecast is built on data, not gut feel.
Inventory Optimization
Service-level–driven safety stock recommendations that balance working capital against stockout risk, by SKU, location, and season.
Supply Planning
Converts optimized demand plans into constrained supply requirements, accounting for lead times, MOQs, and supplier capacity.
Automated Replenishment
Rules-based and ML-driven replenishment triggers that reduce manual PO creation while maintaining your agreed service levels.
Demand Shaping
Recommend pricing, promotion, or channel actions to shift demand toward available supply, turning a constraint into a commercial lever.
Explainable AI
Every forecast includes a ranked list of contributing factors (seasonality, trend, promotions, external signals) in plain language, not just a number.
Forecast Accuracy Dashboard
Track MAPE, WMAPE, bias, and Forecast Value Add at every level (SKU, category, channel, region) with drill-down to the root cause.
Bias Detection
Automatically surfaces systematic over- or under-forecasting by planner, product group, or channel so teams can correct it before it compounds.
Audit Logs & Versioning
Every override, approval, and plan change is logged with a timestamp and reason. Full version history for compliance, review, and learning.
AI you can actually explain
The "black box" criticism is valid, and Demand OS is built to answer it directly.
Ensemble, not a single model
Demand OS runs a library of statistical models (ARIMA, Holt-Winters, Croston for intermittent demand) alongside ML approaches (gradient boosting, neural networks). For every SKU and horizon, it evaluates each model against held-out data and selects the best performer, automatically re-selecting as patterns shift. No single model is trusted blindly; the ensemble picks the winner and logs the reason.
SKU-4021 · Model selected this cycle
Every forecast shows its work
Every forecast ships with a ranked feature-attribution breakdown. Instead of a single unexplained number, planners see the top contributing factors: seasonality, recent sales trend, active promotions, weather anomaly, or a leading indicator, ordered by impact. Override confidence comes from understanding, not guessing.
SKU-4021 · Forecast drivers this week
Forecast value add vs. statistical baseline: +8.3%
Ask it anything, in plain language
The built-in GenAI Copilot lets planners ask questions directly in the workbench without opening a report or writing a query. It draws on the forecast model, override history, and supply data to give grounded, traceable answers.
"Why did the forecast for SKU-4021 increase 28% this week?"
The uplift is primarily driven by the active July promotional event (+48%) and a strengthening summer seasonality signal (+72%). The model last changed on Tuesday when the promotion was confirmed in Salesforce.
"Which SKUs are most at risk of stockout next week?"
3 SKUs are below safety stock threshold: SKU-1182, SKU-2047, SKU-3391. Replenishment orders are pending approval in your queue.
Plays well with the stack you already have
Native connectors for the ERPs that run mid-market and enterprise supply chains, plus REST API and SFTP for everything else.
CSV / SFTP supported for legacy systems. Ask about a custom connector →
Built for how your industry plans
Pre-configured templates for five verticals, because retail demand patterns are nothing like spare-parts forecasting.
Retail
Promotional uplift, seasonal spikes, store-level replenishment
Manufacturing
Long-tail spare-parts forecasting, production scheduling, MRP integration
CPG
Trade promotion management, category management, retailer collaboration
Distribution & Wholesale
Multi-echelon inventory, customer demand volatility, lead-time variance
Ecommerce
Daily demand signals, rapid SKU proliferation, returns-adjusted forecasting
From day-one problems to day-one wins
The scenarios demand planning teams face in the first 90 days, and how Demand OS handles them.
Launching a product with zero sales history
Demand OS uses analogous product matching (finding historically similar SKUs by attribute, category, and channel) combined with Bayesian priors to generate a defensible launch forecast without any prior demand data. Planners can see which analogues were used and why.
Reacting to a demand spike within a week
Demand Sensing ingests daily POS and order signals to sharpen the near-term baseline before the weekly planning cycle. When a spike appears, the system flags it, explains the likely driver, and recommends a replenishment adjustment within days, not quarters.
Running a promotional forecast without guessing at cannibalization
Promotion Planning models uplift, cross-SKU cannibalization, and post-promotion dips together. Instead of applying a flat percentage uplift, planners see a bottom-up estimate with confidence intervals and can override any assumption with a logged reason.
Simulating a supplier disruption before it happens
Scenario Planning lets supply chain teams model a "what if Supplier A lead time doubles?" event before it occurs, surfacing which SKUs would breach safety stock, which customers would be impacted, and what demand shaping levers are available. Decisions made before the crisis, not during it.
What makes Demand OS different
Five differentiators, each answering a category-wide gap that enterprise teams tell us they hit with every other tool.
Explainable-by-default
Gap: Black-box AI that planners don't trust and can't override confidently
Every forecast explains its reasoning. Planners override with confidence, not guesswork.
Transparent pricing
Gap: Mandatory sales call just to see a number
Published price bands before any conversation. No surprises after you've invested months in evaluation.
Fast phased go-live
Gap: 6–24 month implementations that burn budget before a single forecast runs
A scoped pilot goes live in weeks. You see results from a defined SKU/location set before committing to a full rollout.
Modern planner-first UI
Gap: Legacy UX designed for ERP consultants, not the planners who use it daily
Usability-tested with real demand planners. Work surfaces are shaped around how planners actually think, not how the database is structured.
Outcome-based reporting
Gap: Accuracy dashboards that show MAPE but not what it cost the business
Reports in inventory dollars released and stockouts avoided, metrics a CFO can read without translation.
See the difference for yourself
Five dimensions that separate modern demand planning from legacy enterprise software.
Pricing transparency
Contact sales, NDA often required
Pricing transparency
Published bands before any call
Implementation time
6–24 months typical
Implementation time
Pilot live in weeks
AI explainability
Black-box outputs, no factor attribution
AI explainability
Per-SKU factor attribution by default
UI / UX
Built for consultants; planners adapt to the system
UI / UX
Built for planners; usability-tested
Reporting focus
MAPE / accuracy metrics
Reporting focus
Inventory dollars & stockouts avoided
See how we compare to Blue Yonder, o9, ToolsGroup & SAP IBP: full comparison →
Enterprise trust, built in
Security and compliance are not add-ons. They ship with every tier of Demand OS.
SOC 2 Type II
Independent third-party audit of our security controls, availability, and confidentiality practices.
ISO 27001 Certified
International standard for information security management systems, independently certified.
GDPR-ready data handling
Data processing agreements, data residency options, and configurable retention policies for EU compliance.
Role-Based Access Control
Granular permissions per user, team, product group, and location. No one sees what they shouldn't.
Full audit logging
Every login, data access, forecast change, and approval is logged with timestamp and user, immutable and exportable.
Encryption at rest & in transit
AES-256 at rest, TLS 1.2+ in transit. Keys managed via HSM. Annual penetration testing by an independent firm.
See what Demand OS could save you
Enter three numbers. Get a conservative estimate based on published research, every multiplier cited, every assumption labeled.
Demand planning, answered
Straight answers to the questions enterprise supply chain teams ask before buying.
What is Perimattic Demand OS?
Perimattic Demand OS is AI-powered demand planning and forecasting software that predicts demand, optimizes inventory, and turns those predictions into executable plans, with every forecast explained in plain language, not a black box. It's built for supply chain, demand planning, and operations teams who need forecasting accuracy without a multi-year enterprise rollout.
What's the difference between demand planning and demand forecasting?
Demand forecasting predicts what customers will want and how much. Demand planning turns that prediction into an operational plan: inventory targets, replenishment orders, and production commitments, blended with human judgment and cross-functional consensus. Demand OS handles both.
How much does Perimattic Demand OS cost?
Perimattic Demand OS is scoped and priced based on your team size, SKU count, and integration requirements. Contact us for a tailored quote. We give you a clear number before you commit to anything.
How long does implementation take?
A scoped pilot can go live in 4–8 weeks, not the 6–24 months typical of legacy enterprise planning suites. We deploy in phases, starting with a defined SKU/location scope, so you see results before a full rollout.
Does Demand OS integrate with our ERP?
Yes. Demand OS connects natively to SAP, Oracle, Microsoft Dynamics 365, and NetSuite, plus Salesforce, Snowflake, Power BI, Tableau, Slack, and Microsoft Teams via REST API, and supports CSV/SFTP for legacy systems.
Can planners override the AI's forecast?
Yes. Every forecast is editable, every override is logged with a reason and timestamp, and the system tracks override accuracy over time (Forecast Value Add) so you can see whether human adjustments are actually improving the number.
How does Demand OS explain its forecasts?
Every forecast ships with a plain-language breakdown of its top contributing factors: seasonality, recent trend, promotions, or external signals like weather, instead of a single unexplained number. Planners can ask the built-in copilot "why did this change?" and get a direct answer.
Which industries does Perimattic Demand OS support?
Demand OS is built for retail, manufacturing, CPG, wholesale distribution, and ecommerce, each with pre-configured templates for that industry's demand patterns, from promotional cannibalization in retail to long-tail spare-parts forecasting in manufacturing.
Ready to plan with confidence?
Talk to a demand planning specialist, see a live demo on your own data, and get a pricing proposalall in one conversation.