# AI agents overview

> Source: https://trigger.dev/docs/guides/ai-agents/overview

[​](https://trigger.dev/docs/guides/ai-agents/overview#example-projects-using-ai-agents)

Example projects using AI agents
----------------------------------------------------------------------------------------------------------------------------

Claude changelog generator
--------------------------

Automatically generate professional changelogs from git commits using Claude.

Claude GitHub wiki agent
------------------------

Generate and maintain GitHub wiki documentation with Claude-powered analysis.

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.

Smart Spreadsheet
-----------------

Enrich company data using Exa search and Claude with real-time streaming results.

[​](https://trigger.dev/docs/guides/ai-agents/overview#agent-fundamentals)

Agent fundamentals
------------------------------------------------------------------------------------------------

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](https://www.anthropic.com/research/building-effective-agents)
.

![prompt-chaining](https://mintcdn.com/trigger/uys6iMwf9B_ojh8r/guides/ai-agents/prompt-chaining.png?fit=max&auto=format&n=uys6iMwf9B_ojh8r&q=85&s=8bc4a5c5ff644c6b7c675672d5cab313)

Prompt chaining
---------------

Chain prompts together to generate and translate marketing copy automatically

![routing](https://mintcdn.com/trigger/uys6iMwf9B_ojh8r/guides/ai-agents/routing.png?fit=max&auto=format&n=uys6iMwf9B_ojh8r&q=85&s=2f586095b267c7d969afdc0a1e167071)

Routing
-------

Send questions to different AI models based on complexity analysis

![parallelization](https://mintcdn.com/trigger/uys6iMwf9B_ojh8r/guides/ai-agents/parallelization.png?fit=max&auto=format&n=uys6iMwf9B_ojh8r&q=85&s=385b3c71db00c3995cb3de787ef462b4)

Parallelization
---------------

Simultaneously check for inappropriate content while responding to customer inquiries

![orchestrator-workers](https://mintcdn.com/trigger/uys6iMwf9B_ojh8r/guides/ai-agents/orchestrator-workers.png?fit=max&auto=format&n=uys6iMwf9B_ojh8r&q=85&s=05a71d4ef13664e4e73ed32bfd2a942c)

Orchestrator
------------

Coordinate multiple AI workers to verify news article accuracy

![evaluator-optimizer](https://mintcdn.com/trigger/uys6iMwf9B_ojh8r/guides/ai-agents/evaluator-optimizer.png?fit=max&auto=format&n=uys6iMwf9B_ojh8r&q=85&s=60942bcc65c91600a84882c90eabc016)

Evaluator-optimizer
-------------------

Translate text and automatically improve quality through feedback loops

Was this page helpful?

YesNo

[Previous](https://trigger.dev/docs/guides/community/sveltekit)
[Generate & translate copyCreate an AI agent workflow that generates and translates copy\
\
Next](https://trigger.dev/docs/guides/ai-agents/generate-translate-copy)

⌘I

Assistant

Responses are generated using AI and may contain mistakes.