Function Calling (AI Tool Use)
Function Calling allows an AI assistant to trigger external APIs and webhooks by generating structured JSON parameters during a conversation.
Function Calling is an architecture where an AI model identifies user intent requiring external actions and generates structured JSON parameters to execute designated webhook tools.
How Function Calling works in practice
While standard RAG retrieves static knowledge, dynamic tasks (such as checking order shipping status or scheduling a meeting) require programmatic execution.
Developers define available functions with JSON schemas. When a user requests an action, the LLM outputs the structured parameters needed to invoke that endpoint.
How SiteMind implements Function Calling
SiteMind supports Custom Widget Tools with sync and fire-and-forget execution modes, JSON Schema validation, and optional in-chat visitor confirmation prompts.
Test our AI tools in your browser (100% Free)
Estimate support savings, token counts, or test prompt injection security guardrails with our zero-cost sandboxes.
Related Technical Concepts
Outbound Webhooks
Webhooks deliver real-time HTTP POST notifications to your backend whenever key events (like completed chats or captured leads) occur.
Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation (RAG) is a technique where an AI fetches verified passages from a knowledge base before answering, ensuring grounded, factual replies.
Conversational Lead Capture
Conversational lead capture collects prospective buyer contact information (name, email, phone) directly within natural chat conversations.
Test it on your own website in under 2 minutes.
Enter your domain to index your pages and preview live answers.