---
title: "OpenAI Agents SDK Deep Research Demo"
description: "A deep research agent built with the OpenAI Agents SDK and Temporal's durable execution, featuring a web UI, multi-agent coordination with clarifying questions, and optional PDF report generation."
canonical: "https://temporal.io/code-exchange/openai-agents-sdk-deep-research-demo.md"
source: "https://temporal.io/code-exchange/openai-agents-sdk-deep-research-demo"
published: "2025-11-29"
authors:
  - "Steve Androulakis"
  - "Garima Gupta"
  - "James Watkins"
  - "Candace van Oostrum"
  - "Alfred Chan"
  - "Bilal Karim"
  - "Shivam Ajmera"
  - "Angie Byron"
languages:
  - "Python"
tags:
  - "ai"
  - "openai"
  - "deep research"
reviewed_by_temporal: true
---

# OpenAI Agents SDK Deep Research Demo

A deep research agent built with the OpenAI Agents SDK and Temporal's durable execution, featuring a web UI, multi-agent coordination with clarifying questions, and optional PDF report generation.

- [View repo](https://github.com/temporal-community/openai-agents-sdk-deep-research-demo)

This demo extends the Deep Research workflow from [OpenAI Agents Python SDK Demos](https://temporal.io/code-exchange/openai-agents-python-sdk-demos.md) by adding a browser-based UI, making it easier to experience the full multi-agent research pipeline in action. It's designed to be run side-by-side with the Temporal UI to show durable execution in real time.

When given a research query, a Triage Agent can route the workflow to a Clarifying Agent for follow-up questions, or if the query is already specific enough, let research continue without them. An Instruction Agent processes the responses, then hands off to a Planner Agent that creates a web search plan. Multiple Search Agents execute queries in parallel, and a Writer Agent compiles the findings into a comprehensive markdown report.

Every agent invocation and tool call is backed by Temporal, meaning the workflow is fault-tolerant, observable, and resumable — even if it takes several minutes to complete. This makes it a practical reference for teams building production-grade research agents with the OpenAI Agents SDK.
