Manufacturing
Planr
Demand intelligence for multi-plant manufacturers.
The field report
The planner’s shortest decision is still taking hours.
Import-dependent plants run on a 45–65 day replenishment clock. Inventory, transport, and demand live in separate files. Planr stitches them and answers “can we keep the line running?” in minutes.
- Deployment
- Live · 8 plants
- ERP
- Any · field-mapped
- Engine
- Operations research
- Decision cycle
- Days → minutes
The crisis
The decision that keeps breaking.
Tuesday morning, filter plant outside Nasik. Media 007 is down to 8 kg against a 46 kg daily burn. Coverage: two and a half days. Supplier lead time: 45–65 days. Shortage: 912 kg across a nineteen-day window.
The fix already exists in the network. The same part sits at two sister plants. A compatible substitute sits at a third. A master roll in the building can be cut to width. Planr surfaced all three within seconds of the data loading.
“From lag report to actionable shortage resolution options, in one session.”
Walkthrough · Part 1 of 4
How Planr starts where spreadsheets end.
The operational reports a planner already exports — stitched into one decision-ready view before the day begins.
The gap
Why planning stays manual.
The problem is cohesion, not data. The operational reports a planner needs already exist — stock and buffers, open POs and ETAs, plant-level inventory value, inter-plant transport. They arrive separately, at different cadences, owned by different teams.
Stitching them into one view eats the day. Deciding gets what’s left. Every at-risk part becomes a coordination project; the knowledge of who substituted what lives in whoever is in the room.
Walkthrough · Part 2 of 4
Coverage across every plant, in one view.
Every plant, every part — coverage in one view. Risk surfaces the moment the data loads; one drill-down lands on the stock projection.
What Planr is
Introducing Planr.
Planr ingests the operational reports, normalises them, and runs an operations-research engine across the network. Output: a ranked, costed menu of resolution options the planner can act on.
Three layers — data, analytics, decision — with an AI layer on top. Not an LLM doing the math; OR doing it, auditably.
The four layers
- Accepts the operational exports your ERP already produces. Field-mapping aligns any column naming to a stable internal vocabulary. No code.
Dashboard & drill-down
Shortage intelligence.
Planr runs a shortage computation across every plant and every raw material at once — the thing a spreadsheet can’t. The dashboard shows coverage in kilograms and days. Click any at-risk part: RLT window, on-hand, material-in-transit against confirmed ETAs, exact stockout window, replenishment to restore the buffer.
The same engine runs in two planning modes. Pick whichever your data supports today. Both feed the options engine downstream.
Resolution pathways
The Options Engine.
For every at-risk part, four families of resolution. Same part at a sister plant. Compatible substitute at another plant. Substitute already at home. Master-roll cuts, LP-optimised inside the 3–12% machine-constraint window.
Each option lands in one row: source plant, source part, width and grade match, transferable quantity, cutting waste, transit days, total delivered cost. Every number visible. Every number auditable.
Same part · different plant
Sister plants with surplus above their own green level. Transferable quantity, transport cost, transit days.
Substitute · different plant
Compatible substitute at another plant. Width-mismatch wastage plus transfer cost and transit.
Substitute · same plant
Parts already in-house that can be converted or reallocated. Zero transport. Cutting waste traded for it.
Master roller cutting
Cutting combinations from available master rolls. LP-optimised inside the 3–12% waste window.
Walkthrough · Part 3 of 4
Every shortage, every feasible path.
Transfer, substitute, reallocate, or cut from a master roll. Each row arrives with rolls needed, wastage percentage, and transit already solved — through OR, not heuristics.
AI decisioning
From options to plans.
The options engine handles feasibility — every pathway the network allows. The AI layer handles optimisation — picking the right subset across every plant and every part in a single pass.
Three plans, three goals. Lowest cost leans on transfers. Fastest leans on shortest transit. Balanced trades cost, speed, and waste. Cross-plant dependencies are honoured: surplus committed to Plant 3 isn’t available to Plant 5. Drill into any action and the underlying combination opens with the same tables and tooltips from the options view.
“Hundreds of unranked options to three plans with reasoning, in a minute instead of a morning.”
Walkthrough · Part 4 of 4
Hundreds of options collapse into one plan.
OR produces every valid resolution. The AI layer ranks, sequences, and explains them — lowest cost, fastest, minimum waste — on demand.
For commercial teams
What-If, a decision layer for sales.
The other person living inside a shortage is the sales owner — the face of every customer commitment, with no view into the plant. “Can you deliver 2,500 units by the 18th?” shouldn’t need a callback.
Sales describes the order in free text. What-If runs the same cross-plant analysis a planner would: BOM, inventory, open POs, transfer availability, air-freight feasibility. Out: a feasibility answer, a timeline, BOM blockers, an action plan to take back to the customer.
Commit with options, not guesswork.
In production
Proof & deployment.
Planr is live at a top-tier automotive filter manufacturer — eight plants, all import-dependent raw-material planning. Today: manual file upload. Phase 2: direct ERP integration, Oracle first.
No plant-count limit, no industry lock-in. The same OR engine fits pharma, specialty chemicals, and any multi-plant operation running on import-dependent raw materials. New verticals start with a discovery call — we sit with your planning team, map your reports and constraints, and fit the resolution families to your bottleneck before a single file moves.
Bring the clock back under control
Bring the decision back under a clock you control.
Planr runs at an eight-plant operation today. It adapts to your ERP via configuration, not a rebuild. Start with the lag report you already produce.