OpenAI Agent Builder (TypeScript)

OpenAI Agent Builder is a visual canvas for creating multi-step agent workflows. Export production-ready TypeScript code and add the AI Gateway for:

Complete observability of agent workflows
Cost tracking and optimization
Reliability features (fallbacks, retries)
Access to 3,000+ LLMs
Guardrails for safe agent behavior

Quick Start

Design in Agent Builder

Open OpenAI Agent Builder and create your workflow using the visual canvas.

Export Code

Click Code → Agents SDK to get the TypeScript implementation.

Install Packages

npm install @openai/agents openai

Add the AI Gateway

Replace the OpenAI client with the AI Gateway:

import { Agent, run, setDefaultOpenAIClient, setOpenAIAPI } from '@openai/agents';
import { OpenAI } from 'openai';

const client = new OpenAI({
    baseURL: "https://aigw.portkey.ai/v1",
    apiKey: 'YOUR_PORTKEY_API_KEY',
    defaultHeaders: { "x-portkey-provider": '@openai-prod' }
});
setDefaultOpenAIClient(client);
setOpenAIAPI('chat_completions');

// Your Agent Builder workflow code continues as exported...

Update the model field to use the AI Gateway’s format: @openai-prod/gpt-4o

Setup

Add Provider in Model Catalog

Go to Model Catalog → Add Provider. Select your provider (OpenAI, Anthropic, etc.), enter API keys, and name it (e.g., openai-prod).Your provider slug is @openai-prod.

Get AI Gateway API Key

Create an API key at stratacloudmanager.paloaltonetworks.com.Pro tip: Attach a config for fallbacks, caching, and guardrails—applies automatically.

Production Features

Observability

All workflow executions are logged: Add trace IDs and metadata for filtering:

defaultHeaders: {
    "x-portkey-provider": '@openai-prod',
    "x-portkey-trace-id": 'workflow-session-123',
    "x-portkey-metadata": JSON.stringify({
        workflow_type: 'research',
        _user: 'user_123',
        environment: 'production'
    }),
}

Reliability

Enable fallbacks via Configs:

const client = new OpenAI({
    baseURL: "https://aigw.portkey.ai/v1",
    apiKey: 'YOUR_PORTKEY_API_KEY',
    defaultHeaders: {
        "x-portkey-config": JSON.stringify({
            strategy: { mode: 'fallback' },
            targets: [
                { override_params: { model: '@openai-prod/gpt-4o' } },
                { override_params: { model: '@anthropic-prod/claude-sonnet-4' } }
            ]
        }),
    }
});

Automatic Retries

Handles temporary failures automatically

Load Balancing

Distribute across multiple keys

Conditional Routing

Route based on request attributes

Fallbacks

Switch to backup providers automatically

Guardrails

Add input/output validation:

defaultHeaders: {
    "x-portkey-provider": '@openai-prod',
    "x-portkey-config": JSON.stringify({
        input_guardrails: ['guardrail-id-xxx'],
        output_guardrails: ['guardrail-id-yyy']
    }),
}

Guardrails can:

Detect and redact PII
Filter harmful content
Validate response formats
Apply custom business rules

Guardrails Guide

PII detection, content filtering, and custom rules

Caching

Reduce costs with response caching:

defaultHeaders: {
    "x-portkey-provider": '@openai-prod',
    "x-portkey-config": JSON.stringify({ cache: { mode: 'semantic' } }),
}

Prompt Templates

Use the AI Gateway’s prompt management for versioned prompts:

Switching Providers

Use any of 3,000+ models:

// Prefix the model with the provider slug to pick the integration.
model: '@openai-prod/gpt-4o'
model: '@anthropic-prod/claude-sonnet-4-20250514'
model: '@google-prod/gemini-2.0-flash'

Supported Providers

See all 3,000+ supported models

Enterprise Governance

Set up centralized control for your workflows.

Add Provider with Budget

Go to Model Catalog → Add Provider. Set budget limits and rate limits.

Create Config

Go to Configs:

{
  "override_params": { "model": "@openai-prod/gpt-4o" }
}

Create Team API Keys

Go to API Keys. Create keys per team, attach configs.

Distribute to Teams

Teams use their AI Gateway API key:

const client = new OpenAI({
    baseURL: "https://aigw.portkey.ai/v1",
    apiKey: 'TEAM_PORTKEY_API_KEY'  // Config attached to key
});

Governance & Administration

Access control, encryption, and audit trails

FAQ

Can I use the AI Gateway with existing Agent Builder workflows?

Yes. Export your workflow, add AI Gateway client initialization, and your code works unchanged.

Does the AI Gateway work with all Agent Builder features?

Yes. Handoffs, tools, guardrails—all work with the AI Gateway observability and reliability.

How do I track workflow costs?

Add metadata to your requests. Filter by workflow type, user, or environment in the dashboard.

Can I use my own API keys?

Yes. The AI Gateway stores your provider keys securely. Rotate keys without code changes.

Resources

OpenAI Agents SDK

Full SDK integration guide

Configs

Fallbacks, caching, and routing

OpenAI Agents Docs

Official documentation

Last modified on September 15, 2026

Integrations

LLM Integrations

Cloud Platforms

Guardrails

Plugins

Vector Databases

Agents

AI Apps

Libraries

Tracing Providers

MCP Clients

MCP Servers

OpenAI Agent Builder (TypeScript)

Quick Start

Setup

Production Features

Observability

Reliability

Automatic Retries

Load Balancing

Conditional Routing

Fallbacks

Guardrails

Guardrails Guide

Caching

Prompt Templates

Switching Providers

Supported Providers

Enterprise Governance

Governance & Administration

FAQ

Resources

OpenAI Agents SDK

Configs

OpenAI Agents Docs

​Quick Start

​Setup

​Production Features

​Observability

​Reliability

Automatic Retries

Load Balancing

Conditional Routing

Fallbacks

​Guardrails

Guardrails Guide

​Caching

​Prompt Templates

​Switching Providers

Supported Providers

​Enterprise Governance

Governance & Administration

​FAQ

​Resources

OpenAI Agents SDK

Configs

OpenAI Agents Docs

Quick Start

Setup

Production Features

Observability

Reliability

Guardrails

Caching

Prompt Templates

Switching Providers

Enterprise Governance

FAQ

Resources