Today we’re officially launching our latest collaboration with GitHub: the Swimm for GitHub Copilot extension. Now, developers using GitHub Copilot Chat can turn Copilot responses into high-quality, code-coupled documentation, simplifying the process of capturing key insights about your codebase.
Each new document created also adds valuable context, making GitHub Copilot “smarter” and improving its ability to generate more accurate, organization-specific responses.
Enhancing AI with code-coupled documentation
AI tools like GitHub Copilot have transformed software development, but they have limitations—especially when it comes to understanding complex, legacy code. Large language models (LLMs) can only work with the data they’ve been trained on, which means they often struggle with older code or understanding the intent behind certain decisions.
If the underlying information isn’t clear, complete, and up-to-date, even the best AI tools will struggle. This is why documentation is so crucial: garbage in, garbage out—but with Swimm, it’s gold in, gold out. Or in even more simple words: the quality of output is determined by the quality of input.
The Swimm GitHub Copilot extension ensures that the context behind your code—the reasons behind decisions, best practices, and team knowledge—gets documented as you code. This keeps documentation aligned with your code and makes your AI tools more effective.
How the extension works
1. Start a conversation with Copilot chat
Get started by asking Copilot a question about your code. For example:
- What testing frameworks are used in this project?
- How do I set up this module?
Copilot pulls the answers directly from your codebase, providing helpful responses right within the development workflow.
2. Generate documentation automatically
Once you have the information you need, use Swimm’s command to turn chat outputs into a structured document. Swimm formats everything into easy-to-read markdown, capturing what your code does and why it’s set up that way.
3. Add missing business context & tribal knowledge
Once you’ve created the document, enrich it by adding your own insights. This is where you can include those “unwritten rules” that only the most experienced developers on your team know– like why a certain method was chosen, or how a specific part of the system works.
4. Always up to date
Whenever changes are made to your code, Swimm automatically updates the related documentation. This means that documentation is always aligned with code, accurate, and trustworthy.
5. Smarter AI outputs
The more documentation you create, the smarter Copilot becomes. Each new document adds context and detail that Copilot can use to give more accurate answers in the future. This feedback loop helps Copilot learn more about your codebase, improving its responses and making it a more reliable coding assistant over time.
Why every organization using GitHub Copilot should also use Swimm
For developers
- Less time spent creating documentation: Just fill in the blanks—no need to start creating a document from scratch
- More accurate Copilot outputs thanks to up-to-date and context-rich documentation
For team leads
- Eliminate knowledge loss
- Ensure that developers, whether old or new, have access to the context and knowledge they need, when they need it
For enterprise:
- Preserve institutional and tribal knowledge with minimal disruption to your teams’ workflows
- Increased adoption of your AI tools and stack thanks to trusted outputs
A new era for documentation
By integrating directly with GitHub Copilot, we make sure that creating and maintaining documentation is as easy as generating code. You don’t have to worry about missing context or outdated docs—everything stays up to date and aligned with your code.
With this extension, documentation becomes a natural part of your workflow. It saves time, reduces confusion, and captures the valuable knowledge that helps your whole team work better together. Plus, it even makes Copilot smarter, so your AI assistant provides more helpful suggestions over time.
