Project Insights + Project Tasks

Project / Repo Insights

Generate with classic techniques, supporting libraries and AI a full overview for the user and GitLab the product (in the sense that the product has information for tasks, suggestions and so on) about a specific projects code base. LLM are also quite good at converting unstructured data to a pre-given JSON format for example.

Information that can be gathered

• Project Type
• Languages used
• Frameworks used, Frameworks for specific tasks (like which frontend framework, testing framework is used, etc.)
• Call Trees and Code graphs
• Test coverage
• Actual usage data from production
• Actual stack traces from review/production/etc
• Graphs of deployed web sites
• Commit History + Statistics of project files
• Linting warnings
• Regex explanations

Project Tasks

Automatic actions

The idea is to have a list of suggested actions. which then can use a combination of LLM, classic tooling, codemods, etc. Actions are automatically checked if applicable at all, prioritised and ranked (as each output still needs confirmation by users). They would be YML based so users + organisations can extend themselves.

• Remove technical debt (e.g. Replace jquery with modern JS)
• Reduce test coverage
• Reduce complexity of functions/code
• Setup + configuration (Create Docker container, Harden configuration, setup security, create management scripts ...)
• Refactor suggestions of too high complexity
• Create automatic code documentation
• Translate application
• Create boilerplate scripts based on patterns
• Convert code from 1 language to another
• Modernise code (JS code, JS to Typescript?)
• Fix Linting warnings
• Automatically write redme.md setup instructions for your project