LLM Commerce Gateway Integration

Overview

LLM Commerce Gateway exposes inventory, pricing, suppliers, and order operations as structured tool interfaces for LLM-driven workflows. Loop Engine governs the workflow state around those tools so recommendations and actions happen through explicit transitions.

The boundary is strict: Commerce Gateway handles commerce data access and operation execution, while Loop Engine handles state, actor attribution, guard enforcement, approval gates, and audit records.

Architecture

1Demand Spike Signal
2       |
3       v
4Loop Engine -------------------- engine.start('procurement.loop')
5       |                        state: GATEWAY_QUERY
6       |
7       v
8AI Actor ----------------------- GET /inventory/:sku
9       |                        GET /demand-forecast/:sku      Commerce
10       |                        GET /suppliers/:sku      ----> Gateway API
11       |                        (read only)
12       |
13       v
14Loop Engine -------------------- guard: confidence_threshold >= 0.80
15       |                        state: PENDING_APPROVAL
16       |
17       v
18Human Approves ----------------- engine.transition('approve_order', humanActor)
19       |
20       v
21Automation Actor --------------- POST /purchase-orders          Commerce
22       |                        (write post-approval only) ---> Gateway API
23       |
24       v
25Loop Engine -------------------- transition('place_order') -> engine.close(outcome: 'po_created')

Three governed workflows

| Loop | Trigger | AI queries | Guard | Write operation | |------|---------|------------|-------|-----------------| | Procurement | Demand spike / low stock | Inventory, forecast, suppliers | confidence >= 0.80 + human approval | createPurchaseOrder | | Price change | Competitor price, margin alert | Price history, demand elasticity | confidence >= 0.85 + human approval | updatePrice | | Inventory adjustment | Expiry, damage, shrink | Current lots, expiry dates | human approval | writeDownInventory |

Using @loop-engine/adapter-commerce-gateway

1import { createLoopSystem } from '@loop-engine/sdk'
2import { CommerceGatewayClient, buildProcurementActor } from '@loop-engine/adapter-commerce-gateway'
3 
4const gatewayClient = new CommerceGatewayClient({
5  baseUrl: process.env.COMMERCE_GATEWAY_URL!,
6  apiKey: process.env.COMMERCE_GATEWAY_API_KEY!
7})
8 
9const procurementActor = buildProcurementActor({
10  gatewayClient,
11  llmProvider: 'claude', "cmt">// switch to 'openai' for GPT-4o
12  apiKey: process.env.ANTHROPIC_API_KEY!,
13  confidenceThreshold: 0.8
14})
15 
16const { engine } = await createLoopSystem({ loops: [procurementLoop] })
17const evidence = await procurementActor({ instance: { data: { sku: 'LMB-BRS-001' } } })

The governance boundary

Commerce Gateway handles data access and commerce operations. Loop Engine governs the workflow around those operations.

| System | Owns | |------|------| | Commerce Gateway | Commerce data (inventory, pricing, orders, catalog), LLM tool definitions for commerce operations, and commerce API execution | | Loop Engine | Workflow state, actor attribution, guard enforcement, human approval gates, transition audit trail, and learning signals |

Neither system needs to know the internal workings of the other. The adapter is the only coupling point.

Full procurement walkthrough

DEMAND_SPIKE starts procurement.loop and moves to GATEWAY_QUERY.

AI actor reads inventory, demand-forecast, and suppliers from Commerce Gateway.

LLM emits recommendation evidence (recommendedQty, supplierId, confidence, rationale).

confidence_threshold passes and loop moves to PENDING_APPROVAL.

Human approves; automation actor calls createPurchaseOrder; loop executes place_order and closes with po_created.