The GitHub Blog provides updates, announcements, and insights from the world's leading software development platform, covering topics such as new features, community highlights, and industry trends. Developers can learn about GitHub's latest developments, best practices for collaboration, and tips for maximizing productivity on the platform.

GitHub Blog

A developer shares an experimental approach to building applications by writing specifications entirely in Markdown and using GitHub Copilot to compile them into actual code. The workflow involves maintaining app logic in markdown files, using AI to generate Go code, and keeping documentation synchronized with implementation. This spec-driven development method aims to solve context loss issues with AI coding agents while enabling faster iteration and cleaner specifications.

Spec-driven development: Using Markdown as a programming language when building with AI

<blockquote>
Markdown as a programming language
</blockquote>
<img src="https://emoji.slack-edge.com/T0141MGU324/thomas_the_triggered_engine/b56dbd2aaf9f5958.gif" alt="triggered">

turing complete ~markdown~
how far have we come,
from machine code -&gt; assembly -&gt; compiled language -&gt; interpreted language -&gt; markdown

I had a similar idea recently, maybe this can be built out to have more dedicated markdowns.
Like:
<ul>
<li><code>Goal.md</code></li>
<li><code>Conventions.md</code></li>
<li><code>Feature.n.md</code></li>
</ul>
And have a ralph loop work on it, maybe have a chat input layer like claude code
Have it understand ADR files, docs that are already there and let it cook.

if you have time to create this markdown then you better off code yourself, i tried it, it takes a consierable amount of time, instead just code yourself, increase self skills

This seems similar to this: <a href="https://github.com/letta-ai/agent-file" target="_blank" rel="noopener nofollow">https://github.com/letta-ai/agent-file</a>