Add LLM friendly contextual codebase rules

[luistoptal]

User story

As a developer
I want our codebase and documentation to be structured for AI compatibility
So that AI-powered tools can efficiently analyze, understand, and update the code

Acceptance criteria

Given: The project has centralized codebase rules that automatically provide context for LLMs
When: AI tools work on the codebase
Then: The rules describe the project structure, coding style, and architectural guidelines in a format optimized for automated parsing, and these rules are automatically provided as context to the LLM

Additional Info

• As reference for what this ticket intents as a goal, one can look at the cursor IDE rules: https://docs.cursor.com/context/rules-for-ai
• Setting up contextual rules allows LLMs to understand the project and provide useful and accurate answers much more effectively, this can potentially speed up development time and quality very noticeably
• Cursor is a propietary and paid IDE and it is not expected that the entire dev team uses it so a service agnostic solution would be required
• The solution should be easy to integrate with common ways to use LLMs in an IDE, of which there are a handful (cursor, github copilot, cline, continue.dev, ...)
• Devs should not be forced to use LLMs to code, so these rules should provide a useful alternative but its use not be enforced
• If a brief research does not provide a satisfactory solution, I think a reasonable solution would be to have a .llm-rules folder or similar that holds a good (minimal) starting point for contextual rules
• Research also what would be an optimal but minimal content for these rules

Product Backlog Item Ready Checklist

• Business value is clearly articulated
• Item is understood enough by the IT team so it can make an informed decision as to whether it can complete this item
• Dependencies are identified and no external dependencies would block this item from being completed
• At the time of the scheduled sprint, the IT team has the appropriate composition to complete this item
• This item is estimated and small enough to comfortably be completed in one sprint
• Acceptance criteria are clear and testable
• Performance criteria, if any, are defined and testable
• The Scrum team understands how to demonstrate this item at the sprint review

Product Backlog Item Done Checklist

• Item(s) in increment pass all Acceptance Criteria
• Code is refactored to best practices and coding standards
• Documentation is updated as needed
• Data security has not been compromised (with particular reference to the personal information we hold in GigaDB)
• No deviation from the team technology stack and software architecture has been introduced
• The product is in a releasable state (i.e. the increment has not broken anything)