Overview
The Prompt Engineer’s Markdown
AgentMark is a declarative, extensible, and composable approach for developing LLM applications using Markdown and JSX. AgentMark files enhance readability by displaying the readable inputs sent to the LLM, while providing lightweight abstractions for developers.
Motivation
The goal of AgentMark is to simplify the development of prompts & agents. We do this by:
- Supporting readable/portable Markdown + JSX.
- Decoupling your prompts from code
- Decoupling your model config through a unified interface
- Keeping everything local with our OSS runtime
Why extend Markdown?
Markdown works well for basic content but lacks the flexibility needed for templating, composable components, and organized content. AgentMark is built on TemplateDX, which introduces custom components and templating capabilities, enabling document composability, conditional rendering, and variable interpolation while maintaining Markdown’s readability and simplicity. This approach offers a powerful tool for creating dynamic, content-rich documents.
Supported Languages
Language | Support Status |
---|---|
TypeScript | ✅ Supported |
Python | ⚠️ Coming Soon |
Java | ⚠️ Coming Soon |
Others | Need something else? Open an Issue |
Have Questions?
We’re here to help! Choose the best way to reach us:
Join our Discord community for quick answers and discussions
Email us at hello@puzzlet.ai for support
Schedule an Enterprise Demo to learn about our business solutions
Was this page helpful?