AI Integrations
WSO2 Integrator lets you build AI-powered integrations, including direct LLM calls, AI agents, RAG pipelines, MCP servers, natural functions, and voice agents.
AI Building Blocks
The shared connections and stores every AI feature is built from: model providers, embedding providers, vector stores, knowledge bases, chunkers, and data loaders.
Direct LLMs
The simplest AI block. Add a generate node to a flow, write a prompt, and bind the response to a typed value in a single round-trip.
AI Agents
Autonomous LLM-driven agents that reason over a system prompt, call tools, and keep memory across turns. Covers reusable definitions, multi-agent systems, gated tools, observability, and evaluations.
Retrieval-Augmented Generation (RAG)
Ground LLM responses in your own documents. Ingest documents into a knowledge base, then retrieve the relevant chunks at query time and inject them into the prompt.
Model Context Protocol (MCP)
Expose a service as MCP tools for AI assistants, or use tools from external MCP servers in your agents.
Natural Functions
Experimental. Write the function body in plain English. The LLM returns a value that conforms to your declared return type.
Voice Agent
Expose an AI agent over a voice channel. WSO2 Cloud handles speech-to-text and text-to-speech, so your service works only with text.
Getting started
- Build a Sentiment Analyzer: Your first AI integration with a direct LLM call.
- Build a Hotel Finder Agent: An agent with two custom tools and session-scoped memory.