guardrails defining how the 
 agent behaves Here’s what this looks like in code when using OpenAI’s Agents SDK. You can also implement the same concepts using your preferred library or building directly from scratch here’s how you would equip the agent defined above with a series of tools when using the Agents SDK: Python 1 2 3 4 5 6 7 8 8 10 11 12 from import def agents Agent, WebSearchTool, function_tool reaching a maximum number of turns. 14 A practical guide to building agents For example, in the Agents SDK, agents are started using the method, which loops over the LLM until either: Runner.run() 01 A final-output

checkout • Gemini interactive quizzes • Canvas Create menu • LearnLM integration into Gemini 2.5 • SDK support for Model Context Protocol (MCP) definitions in Gemini API • Gemini Diffusion • SynthID