Customer support

1 Workflows1 Response Formats2 Backend Steps

FAQ & Knowledge Assistant

Answers common customer questions from your knowledge base and flags the ones that need a human.

Works with

Primary
Backup

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

Best for

  • Small businesses
  • No-code app builders
  • Support teams

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

faq_knowledge_workflow

Answers questions from the knowledge base

Backend event

question_received

Backend event

answer_ready

Customer receives the response

What you get

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

Workflow

faq_knowledge_workflow

Answers questions from the knowledge base

Response format

faq_answer_response

Answer and confidence for the customer question

answerconfidencetopicneeds_human

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.

faq_knowledge_workflow

Answers questions from the knowledge base

Model & backupsLearn more
xai · grok-4.5Backup 1: anthropic · claude-haiku-4-5-20251001

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

Response formatLearn more
faq_answer_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
customer_namequestion

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

Memory windowLearn more
30 minutes

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

Automated pipelineLearn more
question_receivedanswer_ready

Steps that run automatically around this workflow, in order.

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-faq-knowledge-assistant-template-v1.json1.8 KB
{
  "version": 1,
  "structures": [
    {
      "name": "faq_answer_response",
      "description": "Answer and confidence for the customer question",
      "example": {
        "answer": "You can reset your password from the login page.",
        "confidence": 0.92,
        "topic": "account",
        "needs_human": false
      },
      "schema": {
        "type": "object",
        "properties": {
          "answer": {
            "type": "string"
          },
          "confidence": {
            "type": "number"
          },
          "topic": {
            "type": "string"
          },
          "needs_human": {
            "type": "boolean"
          }
        },
        "required": [
          "answer",
          "confidence",
          "topic",
          "needs_human"
        ],
        "additionalProperties": false
      }
    }
  ],
  "workflows": [
    {
      "name": "faq_knowledge_workflow",
      "description": "Answers questions from the knowledge base",
      "provider": "xai",
      "model": "grok-4.5",
      "backups": [
        {
          "provider": "anthropic",
          "model": "claude-haiku-4-5-20251001"
        }
      ],
      "request_type": "chat",
      "system_instructions": "Answer the customer question using the knowledge base in the system instructions. Give a clear, friendly answer, rate your confidence, and flag questions that need a human agent. Never invent policies.",
      "structure": "faq_answer_response",
      "customer_fields": [
        "customer_name",
        "question"
      ],
      "test_mode": false,
      "cache_window_seconds": 1800,
      "backend_pipeline": {
        "enabled": true,
        "events": [
          {
            "name": "question_received"
          },
          {
            "name": "answer_ready"
          }
        ]
      }
    }
  ]
}

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.