# Intro to Agent Builder

Source: https://www.youtube.com/watch?v=44eFf-tRiSg
Recap page: https://rapidrecap.app/video/44eFf-tRiSg
Generated: 2025-10-06T18:32:39.089+00:00

---
## Quick Overview

The video provides an introduction to Open AI's Agent Builder, a visual, no-code tool for connecting nodes to create AI workflows, demonstrating the creation of a travel agent workflow that first classifies user intent (flight info vs. itinerary) using a JSON-outputting classifier, then routes the request to either a specialized Flight Agent (with web search enabled) or an Itinerary Agent, culminating in publishing the workflow for API use.

**Key Points:**
- Agent Builder is a visual, no-code tool for creating AI workflows by connecting nodes like Start, Agent, File Search, and If/Else.
- A sample workflow is built to handle user requests, starting with a 'Classifier' agent configured to output JSON with a 'classification' property (e.g., 'flight_info' or 'itinerary').
- The workflow uses an 'If/Else' node to branch based on the classifier's output, routing 'flight_info' requests to a 'Flight Agent' and others to an 'Itinerary Agent'.
- The 'Flight Agent' is configured with instructions to act as a travel assistant, using the 'Web Search' tool to find up-to-date flight data and outputting the result as a custom 'Widget' format.
- The 'Itinerary Agent' is instructed to build a concise itinerary, avoiding time/timezone details in its output.
- The final workflow can be published, generating a Workflow ID for embedding into products using the ChatKit SDK or API calls.

![Screenshot at 00:05: The initial view of the Agent Builder workflow interface showing the 'Start' node connected to a placeholder 'My Agent' node, alongside the node selection panel displaying options like Agent, File search, and If/else.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-00-05.png)

**Context:** This video serves as an introductory tutorial to OpenAI's Agent Builder platform, a visual interface designed to allow users to construct complex sequences of AI actions, known as workflows, without writing extensive code. The presenter, Christina from OpenAI, guides the viewer through building a dual-purpose travel agent that can handle both specific flight lookups and general trip planning by leveraging conditional logic and specialized agents.

## Detailed Analysis

The tutorial introduces OpenAI's Agent Builder, a visual tool for creating AI workflows by connecting nodes. The presenter begins by showing the interface, where workflows start with a 'Start' node and branch using other components. The core demonstration involves creating a travel agent workflow. First, a 'Classifier' agent is added, instructed to determine if a user query is about flight information or general itinerary planning. This classifier is configured to produce structured JSON output with a 'classification' property, which the presenter sets to accept 'flight_info' or 'itinerary' as values. Next, an 'If/Else' node uses the output from the classifier to branch the workflow: if the classification is 'flight_info', the flow proceeds to the 'Flight Agent'; otherwise, it goes to the 'Itinerary Agent'. The 'Flight Agent' is given instructions to act as a travel assistant, always recommending a specific flight using airport codes and is explicitly granted access to the 'Web Search' tool to retrieve current flight data. The output format for the Flight Agent is set to a custom 'Widget' type, demonstrating the ability to render rich, structured UI output, exemplified by a flight card showing flight number, origin (SFO), destination (HND), and times. The 'Itinerary Agent' is instructed to build a concise itinerary based on the destination, explicitly told not to include timezones or background creative. Finally, the presenter demonstrates publishing the completed workflow, which generates a Workflow ID accessible via the ChatKit tab for integration into external products.

### Agent Builder Overview

- Visual tool for building AI workflows without code
- Connects nodes like Start, Agent, File search, If/else
- Workflows can be exported as code or published for API use.

### Workflow Construction

- Start with a 'Start' node
- Add a 'Classifier' agent configured for JSON output with a 'classification' property ('flight_info' or 'itinerary')
- Use an 'If/Else' node to route based on the classification result.

### Flight Agent Configuration

- Added to the 'flight_info' branch
- Instructed to recommend specific flights using airport codes
- Enabled the 'Web Search' tool for current data
- Output format set to a custom 'Widget'.

### Itinerary Agent Configuration

- Added to the 'else' branch
- Instructed to build a concise itinerary based on destination
- Explicitly told not to include timezones or background creative.

### Publishing and Integration

- Workflow published under the name 'Travel Agent'
- Provides a Workflow ID for integration via ChatKit or Agents SDK
- Demonstrates previewing the workflow execution, showing the classifier routing and the Flight Agent using web search to generate a rich widget output.

![Screenshot at 00:00: Title screen displaying 'Intro to Agent Builder' and the initial node connection options \(Start, Agent, File search, If/else\).](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-00-00.png)
![Screenshot at 00:05: The initial workflow structure showing 'Start' connected to 'My agent' in the main canvas.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-00-05.png)
![Screenshot at 00:48: The 'Start' node configuration panel open, showing setup for defining input variables like 'input\_as\_text'.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-00-48.png)
![Screenshot at 01:25: The 'Structured output \(JSON\)' configuration modal open for the Classifier agent, defining the 'classification' property and selecting 'ENUM' as the type.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-01-25.png)
![Screenshot at 01:38: The classifier output is defined with two enum values: 'flight\_info' and 'itinerary'.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-01-38.png)
![Screenshot at 01:41: An 'If/Else' node added to the workflow, branching the path based on the classifier's result.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-01-41.png)
![Screenshot at 02:06: The 'Flight Agent' being configured, named 'Flight Agent', with instructions to recommend specific flights using airport codes.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-02-06.png)
![Screenshot at 02:25: Configuring the 'Flight Agent' to use the 'Web Search' tool to access current flight information.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-02-25.png)
![Screenshot at 03:53: Preview mode showing the completed workflow routing a test query \('SFO to HND Oct 7'\) through the classifier to the 'Flight Agent', which returns a rich visual widget card.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-03-53.png)
![Screenshot at 05:04: The 'Publish workflow' dialog box confirming successful publication and showing the generated Workflow ID.](https://ss.rapidrecap.app/screens/44eFf-tRiSg/00-05-04.png)