Step-by-step tutorials on building voice and chat AI agents using OpenAI Agents SDK, Realtime API, function calling, multi-agent orchestration, and production deployment patterns.
9 of 1313 articles
Explore the emerging patterns shaping the future of agentic AI, from agent-to-agent communication protocols and autonomous ecosystems to multi-modal agents, evaluation standards, and trust architectures.
A complete end-to-end tutorial building a production-grade customer support system with triage, billing, refund, and FAQ agents using handoffs, RECOMMENDED_PROMPT_PREFIX, and prompt_with_handoff_instructions in the OpenAI Agents SDK.
Build a complete voice-powered customer support agent with triage, billing, refund, and FAQ handling using OpenAI Realtime API, tool integration, and session persistence.
Deep dive into HandoffInputData, input_filter functions, built-in handoff filters, custom filtering strategies, and input_type with Pydantic models for structured handoff metadata in the OpenAI Agents SDK.
Learn how to implement human-in-the-loop approval gates in the OpenAI Agents SDK using needs_approval, MCPToolApprovalRequest, and RunState to control sensitive agent operations.
Build a documentation chatbot using the OpenAI Agents SDK FileSearchTool with vector stores, citation handling, and hybrid retrieval for production-grade RAG chat agents.
Learn how to use the OpenAI Agents SDK ShellTool to give agents the ability to run system commands inside hosted containers, configure network policies, and manage container skills.
Build a production-ready MCP server that wraps your existing REST API endpoints as callable tools, using FastAPI and the MCP Python SDK to expose your business logic to AI agents.
