Preview build · all 32 pages in one file · for review and comments
Book a working session
Home / Agents
Supply chain AI agents

Four pillars. Every agent sits in one.

Supply chain decisions cluster into four families, and they are not independent: what demand is really doing changes what the plants should run, which changes what you should hold, which changes what you can promise. The agents are organized the same way. These are our most frequently used agents — the library keeps growing as customers push into more sophisticated agent roles and responsibilities.

What demand is really doing

Forecasting & Planning

Ahead of the report that says so. Internal and external demand sensing, supplier and distributor forecasting, SKU-level forecasting, and full-horizon forecast and planning.

Moves forecast accuracy and the cost of reactive replanning
  • Full Forecast & Planning
  • Demand Sensing
  • Supplier Forecast
  • Distributor Forecast

Also in the library: SKU Forecasting · Monthly Forecast Digest · Internal Demand Sensing · External Demand Sensing · Forecast Intelligence · Full Horizon Forecast & Planning KPIs

What the plants can actually run

Operational Planning

Master production scheduling and S&OP optimization, purchase order excellence, lead-time and safety-stock optimization, and scenario analysis across both.

Moves schedule attainment and planning cycle time
  • S&OP Optimization
  • MPS Optimization
  • Safety Stock Optimization
  • PO Excellence

Also in the library: S&OP Automation · MPS Automation · Lead Time Optimization · Ship Complete · Bill of Operations Intelligence · S&OP & MPS Scenario Analysis · S&OP & MPS Scenario Optimization

What to hold, and where

Supply & Inventory Optimization

Classification, slow-moving inventory, multi-echelon inventory optimization, vendor-managed inventory opportunity, and supplier reliability.

Moves working capital and inventory health
  • MEIO
  • ABC Classification
  • Slow-Moving Inventory
  • VMI Opportunity
  • Supplier Reliability

Also in the library: Supplier Performance · Warehouse Capacity & Throughput · Purchase Assortments · Purchase Automation

What you can safely promise

OTIF Optimization

Capable-to-promise, promise-date jeopardy, unexpected customer orders, customer promise intelligence, and revenue and OTIF optimization.

Moves on-time in-full and revenue at risk
  • Revenue & OTIF Optimization
  • Capable-to-Promise
  • Promise Date Jeopardy
  • Unexpected Customer Order

Also in the library: Order Promising · Customer Promise KPIs · Customer Promise Date Intelligence · Customer Lead Time Digest · Revenue & OTIF Scenario Analysis · Revenue & OTIF Scenario Optimization

In concert

Context passes forward. Constraints pass back.

A single agent answering one question well is useful. A set of agents answering across the chain, against one another, is what changes the decision.

Step one

Demand informs the plan

A shift in sensed demand does not stop at the forecast. It reaches master scheduling as a change in what the plants should be building, before the monthly cycle would have surfaced it.

Step two

The plan informs inventory

A resequenced build changes what needs to be on hand and where. Safety stock, replenishment and slow-moving positions are re-evaluated against the schedule that will actually run.

Step three

Inventory informs the promise

What is genuinely available — across plants and DCs, net of what the schedule has committed — is what capable-to-promise answers with. Not a static availability figure.

Step four

The promise pushes back

A promise that cannot be held without breaking a higher-priority commitment returns as a constraint on the plan. The loop closes rather than escalating to a person.

Why coordination is the point

Left alone, each pillar optimizes itself: inventory carries less, service carries more, the plant runs the longest campaigns it can. Each answer is locally correct and the combination is bad. The coordination is what stops four right answers from producing one wrong outcome.

What an agent hands you

Every recommendation arrives as a decision package.

Not an alert, and not a number on a dashboard that someone still has to explain. A decision package is the whole case for one action — explained in full, saved, and auditable. It is what makes a recommendation something a planner can approve in minutes and defend to a customer a month later.

01 · The trigger

What opened it

The signal that made this a decision, and the constraint it collided with. A nine-day supplier slip. Committed orders past available-to-promise.

02 · What was consulted

Which systems answered

Every system the agents read for this decision and what each one contributed — ERP, WMS, OMS, planning, MES, supplier feeds.

03 · The recommendation

One reconciled action

Not four competing suggestions from four agents. One action, with the rule from your ontology that governed it stated alongside.

04 · The alternatives

Priced, not listed

What the options not taken would have cost. This is the part that turns a recommendation into a decision someone is willing to sign.

05 · The expected impact

The metric it moves

Which financial or service measure this action changes, and by how much — stated before the approval, not reconstructed afterward.

06 · The record

Kept and exportable

Who approved, edited or rejected it, when, and why. Retained with the package, exportable for audit, and fed back into your Judgment Layer.

Why the package matters more than the model

A recommendation nobody can interrogate does not get approved, and one nobody can reconstruct six months later does not survive an audit. The decision package is what makes an agent’s output usable by a business rather than interesting to a data team. Every package is logged, and every approval and override strengthens the decision memory the next one draws on.

See decision packages worked in full  The rules that govern them

Purpose-built, not repurposed

Every agent exists because a decision was costing someone money.

These agents were not adapted from general-purpose building blocks and pointed at supply chain afterward. Each starts from a decision manufacturers and distributors actually lose money on.

Multi-plant master scheduling

Sequencing across sites that share supply, capacity and customers — the decision our first production deployment was built on.

Multi-level bills of material

One purchased component moving through three BOM levels into four finished goods, traced without a planner rebuilding it in a spreadsheet.

Capacity and constraint reasoning

What the line can actually run this week, against what the plan assumes it can.

Batch variability and yield

Process environments where the input is not uniform and the output cannot be assumed — including perishability and shelf-life constraints.

MES and OT signals

What the floor knows, in the same decision as what the ERP recorded — rather than in a separate report nobody reads in time.

Multiple ERPs

Reconciled against the definitions that exist today, with no requirement to standardize the estate first.

Start here

Which decision would you start with?

Bring the one your team loses the most time or margin on. We will show which agents would touch it, what they would reason on, and what would reach your planner.