> ## Documentation Index
> Fetch the complete documentation index at: https://trigger.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# AI agents overview

> Real world AI agent example tasks using Trigger.dev

## Example projects using AI agents

> [card] [Claude changelog generator](https://trigger.dev/docs/guides/example-projects/claude-changelog-generator.md)
>
> Automatically generate professional changelogs from git commits using Claude.

> [card] [Claude GitHub wiki agent](https://trigger.dev/docs/guides/example-projects/claude-github-wiki.md)
>
> Generate and maintain GitHub wiki documentation with Claude-powered analysis.

> [card] [ClickHouse chat agent](https://trigger.dev/docs/guides/example-projects/clickhouse-chat-agent.md)
>
> Build a chat agent that answers questions about your ClickHouse data with charts, tables and maps
> using `chat.agent()` and generative UI.

> [card] [Human-in-the-loop workflow](https://trigger.dev/docs/guides/example-projects/human-in-the-loop-workflow.md)
>
> Create audio summaries of newspaper articles using a human-in-the-loop workflow built with
> ReactFlow and Trigger.dev waitpoint tokens.

> [card] [Mastra agents with memory](https://trigger.dev/docs/guides/example-projects/mastra-agents-with-memory.md)
>
> Use Mastra to create a weather agent that can collect live weather data and generate clothing
> recommendations.

> [card] [OpenAI Agent Python SDK guardrails](https://trigger.dev/docs/guides/example-projects/openai-agent-sdk-guardrails.md)
>
> Use the OpenAI Agent SDK to create a guardrails system for your AI agents.

> [card] [OpenAI Agent TypeScript SDK playground](https://trigger.dev/docs/guides/example-projects/openai-agents-sdk-typescript-playground.md)
>
> A playground containing 7 AI agents using the OpenAI Agent SDK for TypeScript with Trigger.dev.

> [card] [Vercel AI SDK deep research agent](https://trigger.dev/docs/guides/example-projects/vercel-ai-sdk-deep-research.md)
>
> Use the Vercel AI SDK to generate comprehensive PDF reports using a deep research agent.

> [card] [Smart Spreadsheet](https://trigger.dev/docs/guides/example-projects/smart-spreadsheet.md)
>
> Enrich company data using Exa search and Claude with real-time streaming results.

> [card] [Batch LLM Evaluator](https://trigger.dev/docs/guides/example-projects/batch-llm-evaluator.md)
>
> Evaluate multiple LLM models in parallel with the Vercel AI SDK and stream the results to a
> Next.js frontend using Trigger.dev Realtime.

> [card] [Claude thinking chatbot](https://trigger.dev/docs/guides/example-projects/claude-thinking-chatbot.md)
>
> Build a Next.js chatbot that streams Claude's extended thinking to the frontend with the Vercel
> AI SDK and Trigger.dev Realtime.

## Chat agents

Build a durable, multi-turn chat agent with [`chat.agent()`](https://trigger.dev/docs/ai-chat/overview). A durable session per conversation, with streaming and resumability handled for you.

> [card] [Chat agent](https://trigger.dev/docs/guides/ai-agents/chat-agent.md)
>
> Create a durable, multi-turn chat agent with `chat.agent()`, then add tools to it.

> [card] [ElevenLabs Voice agent](https://trigger.dev/docs/guides/example-projects/elevenlabs-voice-agent.md)
>
> Build a spoken-conversation voice assistant on `chat.agent()`, with streaming speech-to-text and
> text-to-speech from ElevenLabs and server-side voice activity detection.

> [card] [Ask Trigger chat agent](https://trigger.dev/docs/guides/example-projects/ask-trigger-chat-agent.md)
>
> Build a chat agent that teaches Trigger.dev with interactive node-graphs, quizzes and cards,
> using `chat.agent()`, generative UI and live docs grounding through an MCP server.

## 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).

> [card] [Prompt chaining](https://trigger.dev/docs/guides/ai-agents/generate-translate-copy.md)
>
> Chain prompts together to generate and translate marketing copy automatically

> [card] [Routing](https://trigger.dev/docs/guides/ai-agents/route-question.md)
>
> Send questions to different AI models based on complexity analysis

> [card] [Parallelization](https://trigger.dev/docs/guides/ai-agents/respond-and-check-content.md)
>
> Simultaneously check for inappropriate content while responding to customer inquiries

> [card] [Orchestrator](https://trigger.dev/docs/guides/ai-agents/verify-news-article.md)
>
> Coordinate multiple AI workers to verify news article accuracy

> [card] [Evaluator-optimizer](https://trigger.dev/docs/guides/ai-agents/translate-and-refine.md)
>
> Translate text and automatically improve quality through feedback loops


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.