Ecommerce

2 Workflows2 Response Formats3 Backend Steps

Order Status & Tracking Assistant

Handles order inquiries - status, delays, changes - and drafts a helpful reply fast.

Works with

Primary
Backup

Pick your providers and models. The download is customized to your selections.

Best for

  • DTC brands
  • Shopify sellers
  • Small ecommerce

How the data flows

Requests move between your backend and the AI workflows automatically. Here's the exact path a request takes.

Customer request arrives

AI workflow

order_triage_workflow

Classifies the order inquiry and starts the reply pipeline

Backend event

inquiry_received

draft_reply fires, then starts order_reply_workflow

Backend event

reply_ready

AI workflow

order_reply_workflow

Drafts a helpful reply about the order

Customer receives the response

What you get

Every template is built from two kinds of pieces: Workflows and Response Formats.

Workflow

order_triage_workflow

Classifies the order inquiry and starts the reply pipeline

Workflow

order_reply_workflow

Drafts a helpful reply about the order

Response format

order_triage_response

Classification of the order inquiry

inquiry_typeorder_lookupurgencyneeds_agent

Response format

order_reply_response

Drafted reply about the order

status_explanationcustomer_replynext_steps

Details

The full specification of each workflow, with plain-English explanations. Everything below is set in the downloaded file and can be changed after import.

order_triage_workflow

Classifies the order inquiry and starts the reply pipeline

Model & backupsLearn more
openai · gpt-5.6-terraBackup 1: anthropic · claude-haiku-4-5-20251001

The primary model plus automatic fallback models if the primary is unavailable.

Response formatLearn more
order_triage_responseReturns a structured object instead of free-form text.

The structured JSON this workflow returns. Fields are defined by you and enforced by ModelRiver.

Customer data it usesLearn more
order_idcustomer_message

Fields you include in each request so the workflow can personalise its answer.

Memory windowLearn more
10 minutes

Identical requests are answered from memory within this window, which is faster and cheaper.

Automated pipelineLearn more
inquiry_receiveddraft_replystarts order_reply_workflowreply_ready
How multi-step pipelines work

Steps that run automatically around this workflow, in order.

Production mode

Runs live against your connected AI provider.

order_reply_workflow

Drafts a helpful reply about the order

Model & backupsLearn more
anthropic · claude-haiku-4-5-20251001Backup 1: openai · gpt-5.6-terra

The primary model plus automatic fallback models if the primary is unavailable.

Response formatLearn more
order_reply_responseReturns a structured object instead of free-form text.

The structured JSON this workflow returns. Fields are defined by you and enforced by ModelRiver.

Customer data it usesLearn more
order_idcustomer_message

Fields you include in each request so the workflow can personalise its answer.

Production mode

Runs live against your connected AI provider.

How to use it

  1. 1

    Download the template

    The file is a portable JSON bundle - safe to share and easy to read.

  2. 2

    Open a project in ModelRiver

    Sign in, pick a project, and make sure the AI providers used by this template are connected. You can connect them from the Providers section.

  3. 3

    Import it

    Open the Import button in your project, paste or upload the file, review the preview, and confirm. Everything is created atomically, so nothing is overwritten. How import & export works

Template file

Technical users can inspect the raw bundle below.

View full template JSON
modelriver-order-status-assistant-template-v1.json3.6 KB
{
  "version": 1,
  "structures": [
    {
      "name": "order_triage_response",
      "description": "Classification of the order inquiry",
      "example": {
        "inquiry_type": "status_update",
        "order_lookup": "order #10432",
        "urgency": "medium",
        "needs_agent": false
      },
      "schema": {
        "type": "object",
        "properties": {
          "inquiry_type": {
            "type": "string",
            "enum": [
              "status_update",
              "delivery_delay",
              "change_request",
              "other"
            ]
          },
          "order_lookup": {
            "type": "string"
          },
          "urgency": {
            "type": "string",
            "enum": [
              "low",
              "medium",
              "high"
            ]
          },
          "needs_agent": {
            "type": "boolean"
          }
        },
        "required": [
          "inquiry_type",
          "order_lookup",
          "urgency",
          "needs_agent"
        ],
        "additionalProperties": false
      }
    },
    {
      "name": "order_reply_response",
      "description": "Drafted reply about the order",
      "example": {
        "status_explanation": "The order is packed and ready for pickup.",
        "customer_reply": "Your order #10432 is packed and should ship today.",
        "next_steps": "Track it at your account page"
      },
      "schema": {
        "type": "object",
        "properties": {
          "status_explanation": {
            "type": "string"
          },
          "customer_reply": {
            "type": "string"
          },
          "next_steps": {
            "type": "string"
          }
        },
        "required": [
          "status_explanation",
          "customer_reply",
          "next_steps"
        ],
        "additionalProperties": false
      }
    }
  ],
  "workflows": [
    {
      "name": "order_triage_workflow",
      "description": "Classifies the order inquiry and starts the reply pipeline",
      "provider": "openai",
      "model": "gpt-5.6-terra",
      "backups": [
        {
          "provider": "anthropic",
          "model": "claude-haiku-4-5-20251001"
        }
      ],
      "request_type": "chat",
      "system_instructions": "Classify the order inquiry: status update, delivery delay, change request, or other. Identify the order reference, set urgency, and flag anything that needs a human agent.",
      "structure": "order_triage_response",
      "customer_fields": [
        "order_id",
        "customer_message"
      ],
      "test_mode": false,
      "cache_window_seconds": 600,
      "backend_pipeline": {
        "enabled": true,
        "events": [
          {
            "name": "inquiry_received"
          },
          {
            "name": "draft_reply",
            "target_workflow": "order_reply_workflow"
          },
          {
            "name": "reply_ready"
          }
        ]
      }
    },
    {
      "name": "order_reply_workflow",
      "description": "Drafts a helpful reply about the order",
      "provider": "openai",
      "model": "gpt-5.6-terra",
      "backups": [
        {
          "provider": "anthropic",
          "model": "claude-haiku-4-5-20251001"
        }
      ],
      "request_type": "chat",
      "system_instructions": "Draft a clear, friendly reply about the order. Explain the status, avoid inventing tracking details, and point the customer to where they can track it themselves.",
      "structure": "order_reply_response",
      "customer_fields": [
        "order_id",
        "customer_message"
      ],
      "test_mode": false
    }
  ]
}

Looking for something else?

More templates are on the way. In the meantime, you can build your own workflows from scratch in the ModelRiver console.