Agent Smith
SignalSmith’s Agent Smith brings AI-powered capabilities to your CDP operations, enabling faster audience building, conversational data exploration, and programmatic tool integration — all with built-in safety guardrails.
Capabilities
| Feature | What It Does | Who It’s For |
|---|---|---|
| NL Audience Builder | Describe an audience in plain English and get filter conditions generated automatically | Marketing analysts, growth operators |
| AI Agent | Conversational interface that performs multi-step CDP operations on your behalf | All users — data engineers, analysts, operators |
| MCP Server | Model Context Protocol server exposing SignalSmith as AI-accessible tools | Developers, AI engineers, automation builders |
| Guardrails | Safety boundaries that control what AI operations can do without human approval | Platform admins, security teams |
How It Works
The Agent Smith is built on three layers:
1. MCP Server (Tool Layer)
The MCP Server exposes SignalSmith’s capabilities as structured tools that any MCP-compatible AI client can invoke. It provides read tools (list models, get audiences, introspect sources) and write tools (create audiences, trigger syncs, configure destinations). Every tool call goes through the same authentication and authorization as the REST API.
2. Agent Service (Intelligence Layer)
The Agent Service runs AI-powered agent loops that can chain multiple tools together to accomplish complex tasks. When you ask “Create an audience of users who spent over $500 in the last 90 days,” the agent:
- Introspects your data sources to find relevant tables and columns
- Identifies or creates the appropriate traits
- Generates filter conditions
- Presents the result for your review
The agent delivers real-time progress updates as it works.
3. Guardrails (Safety Layer)
Guardrails enforce policies on AI operations. You define rules like “require human approval before deleting an audience” or “block AI from modifying production syncs.” Guardrails apply to all AI-initiated actions regardless of which client (chat UI, MCP client, API) triggered them.
Getting Started
Using the AI Chat (Fastest)
- Click the AI button in the SignalSmith UI sidebar
- Type a natural language request (e.g., “Show me my largest audiences”)
- The agent responds with results and can take follow-up actions
Using the NL Audience Builder
- Navigate to Segment > Audiences
- Click Create with AI
- Describe your audience in plain English
- Review the generated filter conditions
- Adjust if needed and save
Connecting an MCP Client
For developers who want to use SignalSmith tools in their own AI workflows:
- Generate an API key in Settings > API Keys
- Configure your MCP client (Claude Desktop, Cursor, etc.) to connect to your SignalSmith MCP Server
- Start using SignalSmith tools in your AI conversations
See the MCP Server documentation for detailed setup instructions.
Related Resources
- API Reference — REST API documentation
- Core Concepts — SignalSmith building blocks
- Security — Data handling and compliance