Customer support
FAQ & Knowledge Assistant
Answers common customer questions from your knowledge base and flags the ones that need a human.
How the data flows
Requests move between your backend and the AI workflows automatically. Here's the exact path a request takes.
AI workflow
faq_knowledge_workflow
Answers questions from the knowledge base
Backend event
question_received
Backend event
answer_ready
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
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
The primary model plus automatic fallback models if the primary is unavailable.
The structured JSON this workflow returns. Fields are defined by you and enforced by ModelRiver.
Fields you include in each request so the workflow can personalise its answer.
Identical requests are answered from memory within this window, which is faster and cheaper.
Steps that run automatically around this workflow, in order.
Runs live against your connected AI provider.
How to use it
- 1
Download the template
The file is a portable JSON bundle - safe to share and easy to read.
- 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
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
{
"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.