Support Bot

Build a customer support agent that answers questions using your knowledge base.

System prompt

You are a customer support agent for Acme Corp. Answer questions about
our products, pricing, and policies.

Always search the knowledge base before answering. If the knowledge base
doesn't have the answer, say "I don't have that information, let me
connect you with a human agent."

Be friendly, concise, and professional. Never make up information.

MCP server: Document Store

The support bot needs an MCP server that exposes your knowledge base. The MCP server would expose tools like:

• search_docs — semantic search across FAQ, product docs, and policy documents
• get_document — retrieves a specific document by ID
• list_categories — lists available document categories

This could be backed by a vector database indexing your existing documentation, or a simple search over your help center content.

API example

curl -s -X POST https://zhenfy.ai/api/agent/v1/agents \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Acme Support",
    "system_prompt": "You are a support agent for Acme Corp. Always search the knowledge base before answering.",
    "tools": [
      {
        "url": "https://docs.acme.com/mcp",
        "secrets": {"Authorization": "secret:acme-docs-key"}
      }
    ]
  }'

Integration

Each customer gets their own session. Call the Zhenfy chat API from your website, app, or support platform to send messages and receive responses.