PoC: Leveraging AI for Active Development

[sebastian-sommerfeld-io]

As a maintainer of the Source2adoc application, I want to explore the potential of AI-driven feature requests and development to ensure continuous improvement and innovation within the app. This initiative is aimed at leveraging cutting-edge technologies to enhance user experience and maintain the app's relevance in a rapidly evolving landscape.

As a maintainer, I seek to integrate AI into the development process of source2adoc to streamline feature requests and further advancements. By harnessing the power of AI, I aim to accelerate the pace of development while ensuring that user feedback is promptly addressed and incorporated into the app. Using AI should ensure the App remains under active development while minimizing manual effort.

To achieve this, I envision implementing a Proof of Concept (PoC) that demonstrates the capabilities of AI in analyzing user suggestions, prioritizing feature requests, and generating insights for future development roadmaps. This PoC will serve as a foundation for establishing an AI-driven development pipeline that empowers the source2adoc team to adapt swiftly to evolving user needs and technological trends.

By embracing AI-driven development, we aim to foster a culture of innovation, agility, and responsiveness within the source2adoc community, ensuring that the app remains at the forefront of document conversion technology. This PoC represents the first step towards a future where AI plays a central role in shaping the evolution of source2adoc, empowering us to deliver unparalleled value to our users.

Possible functionalities of the AI-enabled development process include (as suggested by ChatGPT)

1. Feature Request Analysis: The AI system will analyze incoming feature requests from users, categorize them based on relevance and feasibility, and provide insights into the most requested features.

2. Prioritization: Leveraging machine learning algorithms, the system will prioritize feature requests based on various factors such as user feedback, market trends, and technical feasibility, ensuring that development efforts are focused on high-impact features.

3. Trend Identification: By analyzing user interactions and industry trends, the AI system will identify emerging needs and technological advancements, enabling proactive development of features to stay ahead of the curve.

4. Automated Development Support: The AI system will assist developers by generating code snippets, suggesting design patterns, and providing recommendations for implementation, thereby accelerating the development process and reducing manual effort.

5. Continuous Learning: Through iterative feedback loops, the AI system will continuously learn from user interactions and development outcomes, refining its algorithms to better serve the evolving needs of Source2adoc users.

My ideas about possible features

• Somehow use an AI to generate user stories (based on collected data - sommerfeld-io/source2adoc#13)
  • Force AI to write user stories. AI should think about personas (= adopt a certain point of view when writing stories)
  • Think about how to handle the user stories ... add label and establish some sort of backlog refinement for all these AI-driven user stories.
  • Maybe add a label "from-ai" or similar and add a column to my GitHub project "ready-for-refinement" or similar. Think about a "ready-for-development" column as well.
  • "ready-for-refinement" could be interesting anyway - even for stories written by me (because I often add a remark that there is work to be done instead of the story content) ... but when I do this for every story, "Backlog", "Ready for Development" and "Next" (instead of "Selected") would suffice.
  • Tasks are always "Ready for Development", user stories are not
• Prefer GitHub Copilot as AI because all these user stories and all the data and input passt to the AI will enhance the learning of GitHub Copilot for this app.

See

https://github.com/cli/cli/actions/runs/9086700583/workflow

[sebastian-sommerfeld-io]

Google Gemini Free Tier

https://ai.google.dev/docs

Request

curl \
  -H 'Content-Type: application/json' \
  -d '{"contents":[{"parts":[{"text":"Explain how AI works"}]}]}' \
  -X POST 'https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash-latest:generateContent?key=<API_TOKEN>'

Response

{
  "error": {
    "code": 400,
    "message": "Gemini API free tier is not available in your country. Please enable billing on your project in Google AI Studio.",
    "status": "FAILED_PRECONDITION"
  }
}