Building Deep Research Agents with the OpenAI Agents SDK
This three-part tutorial series walks you through building a durable, multi-agent deep research application with human-in-the-loop capabilities using Temporal and the OpenAI Agents SDK.
- Part 1: Setting the Stage - Clone the template repository (a non-durable research agent), run it, and understand how the multi-agent pipeline works.
- Part 2: Creating the Workflow - Build the research manager to orchestrate agents and the Workflow to manage state and human-in-the-loop interactions.
- Part 3: Running Your Application - Create the Temporal Worker with the OpenAI Agents plugin, and test durability by surviving crashes.
tip
Sign up here to get notified when we drop new educational content.
Part 1 · ~20 min
Setting the Stage
Clone the template repository for a non-durable research agent, run it, and understand how the multi-agent pipeline works.
Start Part 1 Part 2 · ~60 minCreating the Workflow
Build the research manager to orchestrate agents and the Temporal Workflow to manage state and human-in-the-loop interactions.
Start Part 2 Part 3 · ~30 minRunning Your Application
Create the Temporal Worker with the OpenAI Agents plugin, run the application end to end, and test durability by surviving crashes.
Start Part 3Get notified when we launch new educational content
New courses, tutorials, and learning resources - straight to your inbox.