Prompt Buddy logoPrompt Buddy

openai · OpenAI Platform Docs

Agents Integrations and observability | OpenAI API

Explains how to integrate third-party tools and implement observability patterns to monitor agent performance, traces, and logs.

Import to Prompt Buddy

Derived skill

Files assembled from official documentation

Viewing SKILL.md

Agents Integrations and observability | OpenAI API

Explains how to integrate third-party tools and implement observability patterns to monitor agent performance, traces, and logs.

When To Use

Use when you need to implement monitoring, tracing, or third-party tool integration to track the behavior and performance of AI agents.

Reference Files

FileContainsUse For
SKILL.mdEntry point: scope, routing table, and workflow.Start here.
docs/agents-integrations-observability-and-openai-api-workflow-guide.mdA guide detailing how to integrate external surfaces into agent loops and implement runtime inspection and observability using the OpenAI API.Questions about a guide detailing how to integrate external surfaces into agent loops and implement runtime inspection and observabil...
examples/agents-integrations-observability-and-openai-api-openai-agents-mcp-tool-.textA JavaScript code example demonstrating how to initialize an OpenAI Agent with a hosted Model Context Protocol (MCP) tool.Exact payloads, commands, or snippets shown in A JavaScript code example demonstrating how to initialize an OpenAI Agent with a hosted Model Context Protocol (MCP)...
examples/agents-integrations-observability-and-openai-api-openai-agents-hosted-mc.textA Python code example demonstrating how to configure an OpenAI Agent with a HostedMCPTool using the hosted MCP server.Exact payloads, commands, or snippets shown in A Python code example demonstrating how to configure an OpenAI Agent with a HostedMCPTool using the hosted MCP server.
examples/agents-integrations-observability-and-openai-api-openai-agents-mcp-files.textA Node.js code example demonstrating how to integrate an OpenAI Agent with a Model Context Protocol (MCP) filesystem server.Exact payloads, commands, or snippets shown in A Node.js code example demonstrating how to integrate an OpenAI Agent with a Model Context Protocol (MCP) filesystem...
examples/agents-integrations-observability-and-openai-api-openai-agents-mcp-files-2.textA Python code example demonstrating how to integrate an OpenAI Agent with a Model Context Protocol (MCP) filesystem server using the agents library.Exact payloads, commands, or snippets shown in A Python code example demonstrating how to integrate an OpenAI Agent with a Model Context Protocol (MCP) filesystem s...
examples/agents-integrations-observability-and-openai-api-openai-agents-integrati.textA JavaScript code snippet demonstrating how to wrap an agent workflow with the withTrace function for observability.Exact payloads, commands, or snippets shown in A JavaScript code snippet demonstrating how to wrap an agent workflow with the withTrace function for observability.
examples/agents-integrations-observability-and-openai-api-openai-agents-python-tr.textA Python code example demonstrating how to use the Agent and Runner classes with the trace function to monitor agentic workflows.Exact payloads, commands, or snippets shown in A Python code example demonstrating how to use the Agent and Runner classes with the trace function to monitor agenti...

What This Skill Covers

  • After the workflow shape is clear, the next questions are which external surfaces should live inside the agent loop and how you will inspect what actually ha...
  • Main sections: Choose what lives in the SDK, MCP, Tracing, Next steps.

Workflow

  1. Open the most relevant file under docs/ for the exact documented workflow and wording.
  2. Open schemas/ files for exact structured contracts.
  3. Open examples/ files for concrete requests, commands, snippets, and manifests.
  4. Do not add behavior or configuration that is not present in the attached source files.

Canonical source: https://developers.openai.com/api/docs/guides/agents/integrations-observability