Page Comparison

Recommendations: PLEASE ADD YOuR IDEAS

• Create User Guides for Project maintainers to turn GitHub repos into user guides with a consistent look and feel
• Creating tokenized badging system for correctly creating usable guides
• Suppling Template (Make The Docs) with a graphic library to choose from
• Creating an AI Solution

31 Aug 2023 

Determine Paid tooling policy (make the Docs) vs. AI generators

Deciding between a paid tooling policy for documentation (often referred to as "Make the Docs") and utilizing AI generators involves considering various factors related to your organization's needs, resources, goals, and the nature of the content you're producing. Let's explore the advantages and considerations of each approach:

Paid Tooling Policy ("Make the Docs"):

Advantages:

1. Customization: Paid tools often offer a higher degree of customization. You can tailor the documentation layout, styling, and structure to align with your brand and user experience.
2. Control: With paid tools, you have more control over the documentation process. You can choose the documentation format, create custom templates, and integrate specific features as needed.
3. Specific Use Cases: If your documentation requires advanced features, integrations, or unique formatting, paid tools might be more suitable.

Considerations:

1. Cost: Paid tools typically involve ongoing costs, including licensing fees, subscription fees, or one-time purchases. You need to consider the budget implications.
2. Learning Curve: Some paid tools might have a steeper learning curve, requiring training and adaptation for your team.
3. Maintenance: Customization and control often come with increased responsibility for maintenance and updates.

AI Generators:

Advantages:

1. Speed and Efficiency: AI generators can quickly produce drafts of documentation, saving time for your technical writing team.
2. Consistency: AI tools can help maintain consistency in style, tone, and formatting across large documentation projects.
3. Augmentation: AI can complement your team's efforts by suggesting wording, generating examples, or even creating certain sections of the documentation.

Considerations:

1. Quality Control: While AI can assist with content creation, it might not fully replace the nuanced understanding and decision-making abilities of human technical writers.
2. Contextual Understanding: AI might struggle with understanding the context and nuances of your specific software, potentially leading to inaccuracies.
3. Review and Editing: Generated content will likely require thorough human review and editing to ensure accuracy, coherence, and user-friendliness.

Determining the Approach:

1. Content Complexity: Consider the complexity of your content. AI generators might work well for standardized, repetitive sections, while paid tools might be better for more intricate documentation needs.

2. Budget: Evaluate your budget constraints. Paid tools come with costs, whereas AI might involve an upfront investment in selecting and training a suitable AI platform.

3. Quality and Control: Consider how much control and customization you need over your documentation. If precision, branding, and customization are vital, paid tools might be preferred.

4. Resource Availability: Assess the skills and resources of your technical writing team. Implementing new tools or AI might require training or adjustments to workflows.

5. Hybrid Approach: Depending on your needs, you could even consider a hybrid approach, combining paid tooling for customization with AI generators for specific content generation tasks.

In conclusion, the decision between a paid tooling policy ("Make the Docs") and utilizing AI generators hinges on your specific circumstances, goals, and content requirements. Carefully evaluate the advantages, considerations, and implications of each approach to determine the best fit for your organization.

 - AI tools for generating user guides from Github

AI tools can indeed be quite helpful for generating user guides and documentation from GitHub repositories. These tools use natural language processing (NLP) and machine learning techniques to extract relevant information from your codebase and automatically create user-friendly documentation. Here are a few AI tools that you might consider using for this purpose:

1. Docuglot: Docuglot is an AI-powered documentation generator that can extract code comments, annotations, and other relevant information from your GitHub repository. It then converts this information into well-structured documentation. It supports various programming languages and integrates with GitHub repositories.

2. Kedro-AutoDoc: Kedro-AutoDoc is specifically designed for data science projects. It automatically generates documentation from Kedro projects, which are commonly used for building data pipelines. It extracts information from your codebase and turns it into user-friendly documentation.

3. Sphinx AutoAPI: While not strictly an AI tool, Sphinx AutoAPI is a plugin for the Sphinx documentation generator. It can automatically generate API documentation from code comments and docstrings in various programming languages. It might require some configuration, but it's a powerful tool for creating technical documentation.

4. Natural Docs: Natural Docs is an open-source documentation generator that can generate documentation from your code comments. While it's not AI-powered, it's a useful tool for creating user guides and technical documentation.

5. GitBook: GitBook is a platform that allows you to create documentation from your GitHub repository. While it's not AI-based, it provides a user-friendly interface and can integrate with your GitHub repository to automatically update documentation when you push changes.

6. Doxygen: Doxygen is a tool for generating documentation from source code. It's primarily used for C++, but it supports other programming languages as well. It extracts comments and code structure to create documentation.

Remember that while these tools can be helpful, there might be a learning curve involved in setting them up and configuring them to work well with your specific project. Additionally, generated documentation might still require human review and editing to ensure accuracy, coherence, and user-friendliness.

Meeting with David Boswell

...

• SG - Standard Guide

Note -  Trying to run Solang's documentation on MkDocs (this week)






Mentor - Bobbi (Bobbi@mcrell.com)
Chair and Contributor - Tripur Joshi (tripurjoshi3121@gmail.com)