Warehouse Inventory Transfer with Supply Chain Constraints

The problem

AI-recommended inventory transfers are validated before execution. Corules checks that the source location retains sufficient safety stock, the destination has demand forecasts supporting the transfer, and shipping costs are economically justified. Transfers that would cause stockouts are blocked. Borderline transfers escalate to supply chain planners.

Without deterministic enforcement, AI agents either block every edge case (adding manual overhead) or silently approve decisions that violate policy — with no audit trail to show auditors or regulators.

How Corules solves it

Corules sits between your AI agent and the action it wants to take. When the agent proposes a decision, Corules evaluates the full context against your compiled policy set in a single deterministic pass — no LLM, no ambiguity.

The result is a structured outcome: BLOCK — source_qty_after_transfer 120 below safety_stock['warehouse-east']['SKU-7742'] = 200. Transfer blocked.

Policy example

Corules policies are written in CEL (Common Expression Language). They are compiled once at publish time and evaluated deterministically at request time — no LLM, no variability.

// Inventory transfer policy (CEL)
context.source_qty_after_transfer >= params.safety_stock[context.source_location][context.sku]
  && context.destination_demand_forecast_30d >= context.transfer_qty * 0.8
  && context.transfer_unit_cost <= params.max_transfer_cost_per_unit[context.sku]

This expression is evaluated against the structured context your agent sends in the /v1/validate request.

Integration options

Corules integrates with the tools your teams already use. All integrations call the same REST API or MCP server — your policy logic stays in one place.

Frequently Asked Questions