OpenAI Agents SDK
Build multi-agent applications with the OpenAI Agents SDK. Define agents, hand off between them, register tools, add guardrails, and trace runs — starting from a working scaffold and improving it step by step.
This skill develops apps on the OpenAI Agents SDK. It defines agents with instructions and tools, orchestrates handoffs between specialized agents, adds input and output guardrails, and enables built-in tracing to inspect runs. It starts from a runnable scaffold and layers in structure, tools, and safety checks as the app grows.
openai agents multi-agent tools guardrails
When to use
Use when building single- or multi-agent applications with the OpenAI Agents SDK, including handoffs, tools, guardrails, and tracing.
Examples
Multi-agent handoff
Route work between agents
Build an OpenAI Agents SDK app with a triage agent that hands off to a billing agent or a technical-support agent based on the question
Add guardrails
Validate inputs and outputs
Add input and output guardrails to my OpenAI Agents SDK agent so it refuses off-topic requests and never leaks system prompts