We have been developing an AI-powered documentation framework that automates generating user-facing documentation. We’ve designed a Notion-like user interface for editing content while maintaining support for MDX.
We would love your feedback on this and any additional features you would like to see.
Currently, we are also working on the capability to automatically generate documentation from your repository using AI.
Our main focus is to create high-quality documentation as we improve. We are also considering how this documentation will be used by future developers and AI agents. One of our ideas is to implement an interface similar to Perplexity, but integrated with WebLLM, so users won’t have to worry about costs. You can find more information about it here; although it currently has many issues, we plan to launch a fine-tuned version of the LLM to enhance its performance. You can play with it here: https://demo.akiradocs.ai/aiSearch. Heads up its very slow and tends to break but we are improving on it constantly!
Additionally, we are exploring ways to improve the consumption of these documents and ensure they reach customers when they need them. Unfortunately, this project will be closed-source!
We have been developing an AI-powered documentation framework that automates generating user-facing documentation. We’ve designed a Notion-like user interface for editing content while maintaining support for MDX.
We would love your feedback on this and any additional features you would like to see.
Currently, we are also working on the capability to automatically generate documentation from your repository using AI.
Do I understand correctly, this solution focuses on producing documentation, but not consuming it. Is this correct understanding?
Our main focus is to create high-quality documentation as we improve. We are also considering how this documentation will be used by future developers and AI agents. One of our ideas is to implement an interface similar to Perplexity, but integrated with WebLLM, so users won’t have to worry about costs. You can find more information about it here; although it currently has many issues, we plan to launch a fine-tuned version of the LLM to enhance its performance. You can play with it here: https://demo.akiradocs.ai/aiSearch. Heads up its very slow and tends to break but we are improving on it constantly!
Additionally, we are exploring ways to improve the consumption of these documents and ensure they reach customers when they need them. Unfortunately, this project will be closed-source!