QSC Agent Overview

The QSC Agent is a multi-tenant AI agent that dynamically discovers MCP tools, queries them, and returns strictly tool-based answers (text, product lists, or documentation summaries).

---

Quick summary

• Combine product search, documentation lookup, analytics, and custom services into a single assistant..

• Produce any output format your UI needs (lists, cards, Markdown/JSON, short summaries) by configuring output template via system prompt.

• Customize labels, priorities, and any metadata in your configuration to guide how the agent behaves.

• Swap, add, or remove capabilities simply by updating the MCP server list in agent configuration.

• The system prompt defines how the QSC Agent behaves when processing user requests, interacting with MCP tools, and formatting responses. It acts as a universal rulebook for tool usage, result handling, and output structure — not code. Everything is configurable, and you can adapt it to your tools, products, or documentation services.

Get started (quick)

• Decide what capabilities you need (product search, docs, analytics, etc.).

• Point one or more MCP servers at those capabilities.

• Provide example outputs or templates for the shapes you want returned.

• Update configuration — the agent will use the connected tools and produce the structure you defined.

• If the tool returns actions, they appear as interactive buttons in your chat UI.

• The Actions system ([[QSCACTION:...]]) allows your chat UI to display clickable buttons that trigger specific prompts back to the agent. This gives users a smooth, interactive shopping or browsing experience directly in chat.

Each action follows this pattern:

[[QSCACTION:type=ActionType,label=ActionLabel,prompt=PromptTemplate]]

Example configuration

{
  "mcp_servers": [
    { "url": "https://mcp-products.example/api", "label": "product_search" },
    { "url": "https://mcp-docs.example/api", "label": "documentation" }
  ],
  "openai_model": "gpt-5-turbo",
  "system_prompt": "<SYSTEM_PROMPT_STRING>",
  "openai_models": [
    { "label": "GPT-5 Turbo", "model": "gpt-5-turbo" },
    { "label": "GPT-4o", "model": "gpt-4o" }
  ]
}

Key Fields

Field	Type	Description
mcp_servers	Array	List of MCP tool servers (each tool endpoint)
url	String	Tool server API endpoint
label	String	Friendly name used by the agent
openai_model	String	Default OpenAI model used for inference
system_prompt	String	Defines the agent’s behavior and constraints
openai_models	Array	Optional list of available models for UI selection

Example Products Template can be used in system prompt

|---|---|---|
| ![Sneaker Model X](https://example.com/x.jpg)  
**Sneaker Model X**  
**Price:** $89  
**Brand:** RunMax  
**Color:** Blue  
**SKU:** 3266783  
[[QSCACTION:type=submit,label=Add Cart,prompt=add product with sku 3266783 to cart]]  
[[QSCACTION:type=submit,label=Buy Now,prompt=initiate purchase flow for sku 3266783 with qty 1]]
| ![Sport Jacket Supreme](https://example.com/jacket.jpg)  
**Sport Jacket Supreme - Red - Comfort Fit**  
**Price:** $149  
**Brand:** Supreme  
**SKU:** 992241  
[[QSCACTION:type=submit,label=Add Cart,prompt=add product with sku 992241 to cart]]  
[[QSCACTION:type=submit,label=Buy Now,prompt=initiate purchase flow for sku 992241 with qty 1]] | |

Summary

The system prompt defines how your agent behaves and what format it returns data in.

You can connect any number of MCP servers and tools to extend capabilities.

You can control every aspect — from product layout to interaction flow — through prompt configuration alone.

The [[QSCACTION:...]] syntax enables your chat UI to dynamically generate buttons and link back to agent actions.