​
Overview

These guides will show you how to set up different types of AI agent workflows with Trigger.dev. The examples take inspiration from Anthropic’s blog post on building effective agents.
prompt-chaining

Prompt chaining

Chain prompts together to generate and translate marketing copy automatically
routing

Routing

Send questions to different AI models based on complexity analysis
parallelization

Parallelization

Simultaneously check for inappropriate content while responding to customer inquiries
orchestrator-workers

Orchestrator

Coordinate multiple AI workers to verify news article accuracy
evaluator-optimizer

Evaluator-optimizer

Translate text and automatically improve quality through feedback loops

​
Example projects using AI agents

Human-in-the-loop workflow

Create audio summaries of newspaper articles using a human-in-the-loop workflow built with ReactFlow and Trigger.dev waitpoint tokens.

Mastra agents with memory

Use Mastra to create a weather agent that can collect live weather data and generate clothing recommendations.

OpenAI Agent Python SDK guardrails

Use the OpenAI Agent SDK to create a guardrails system for your AI agents.

OpenAI Agent TypeScript SDK playground

A playground containing 7 AI agents using the OpenAI Agent SDK for TypeScript with Trigger.dev.

Vercel AI SDK deep research agent

Use the Vercel AI SDK to generate comprehensive PDF reports using a deep research agent.