# Making AI assistants better at email: Postmark's new documentation tooling

DevFeed: [Making AI assistants better at email: Postmark's new documentation tooling](<https://devfeed.tech/articles/making-ai-assistants-better-at-email-postmark-s-new-documentation-tooling-16081.md>)

Original publisher: [Read original article](<https://postmarkapp.com/blog/making-ai-assistants-better-at-email-postmarks-new-documentation-tooling>)

Author: Postmark team (fdossetto+postmark@activecampaign.com)

Published: 2025-11-24T18:13:00Z

Content type: article

Language: en

Sources: [Postmark (en-US)](<https://devfeed.tech/sources/postmark-en-us.md>)

Topics: [Documentation](<https://devfeed.tech/topics/documentation.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [MCP Server](<https://devfeed.tech/topics/mcp-server.md>), [API](<https://devfeed.tech/topics/api.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [Tooling](<https://devfeed.tech/topics/tooling.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [api](<https://devfeed.tech/tags/api.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code](<https://devfeed.tech/tags/code.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [error-handling](<https://devfeed.tech/tags/error-handling.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [security](<https://devfeed.tech/tags/security.md>), [tooling](<https://devfeed.tech/tags/tooling.md>)

## AI overview

Postmark describes three updates intended to help AI assistants provide more accurate email-integration guidance: an llms.txt file with structured API and documentation context, pre-built prompts for common integration tasks, and an experimental MCP server that connects assistants to Postmark capabilities.

## Source excerpt

Getting an AI assistant to help with your email integration shouldn't feel like explaining SMTP to your cat. But until recently, that's kind of what it was like - AI tools could tell you about email APIs, but they often got the details wrong or gave you outdated information. We've been thinking about this problem, and we've shipped three updates to make AI assistants genuinely useful when you're working with Postmark. What we built1. llms.txt: Context for AI assistants We published an llms.txt file that gives AI tools like ChatGPT and Claude accurate, structured information about Postmark's API, features, and best practices. Instead of AI assistants guessing or making assumptions about our documentation, they can now reference this file to give you correct details about authentication, endpoints, message streams, deliverability features, and integration patterns. How to use it: When you need help with Postmark integration, troubleshooting, or understanding specific features, paste https://postmarkapp.com/llms.txt into your AI tool. Your assistant will have the context it needs to provide better, more accurate guidance. 2. Pre-built AI prompts We added an AI prompts section to our documentation with ready-to-use prompts for common integration tasks. Each prompt is designed to generate production-ready code that includes error handling, best practices, and proper Postmark API usage. Copy a prompt, paste it into your AI tool, and get working code. Available prompts: Node.js email integration Rails with ActionMailer setup Laravel Mail configuration Password reset flows Event-driven notification systems Inbound email processing Better Auth integration You'll save time - no more documentation deep-dives just to send a welcome email. You'll also avoid common mistakes since the prompts include our recommendations for deliverability, security, and reliability. 3. Postmark MCP server: AI assistants that actually do things Earlier this year, we launched our Model Context Proto