AI without the noise

AI-Assisted Development and Workflow Automation

How AI workflows, custom AI skills and prompt engineering sped up software delivery at Helmsauer Gruppe. It also includes a concept for a RAG application.

Situation:

At Helmsauer Gruppe, a financial services group in Nuremberg, I worked on insurance and brokerage software. Tasks such as test creation and translations were repetitive and took time away from new features.

Task:

As senior full-stack developer, I set out to automate this work with AI. The goal was faster delivery at the same quality.

Action:

  • Built an AI workflow with Playwright and GitHub Copilot that generates Cypress test suites, so E2E tests are created faster.
  • Wrote a custom AI skill that replaces hard-coded strings in Angular templates with translation keys and generates the JSON translation files.
  • Applied deep prompt engineering knowledge to speed up the development process, so AI tools return useful results sooner.
  • Created a concept for a RAG application using NestJS, which answers questions from documents in plain language.
  • Containerized services with Docker and set up GitLab CI/CD pipelines, which automate deployments and make releases more reliable.

Result:

  • Cut E2E test creation time by 2 to 3 times with the AI-assisted workflow.
  • Automated Angular translations, which removes a manual and repetitive step from development.
  • Shortened routine development tasks through well-structured prompts.
  • Turned everyday development work into automated workflows. I bring the same approach to client projects today.

Technologies Used:

GitHub Copilot, Playwright, Cypress, Angular, NestJS, RAG, Prompt Engineering, Custom AI Skills, AI Workflow Automation, AI-Assisted Development, E2E Automated Testing, Docker, GitLab CI/CD

Other references

Provider-Independent RAG Application for Local and Cloud LLMs
A RAG application that answers questions from private documents with either a local or a cloud LLM. It keeps data on local hardware when needed and cites its sources.
Smart Home Automation Platform Grown to 50,000+ Users
Five years of building automation software for a smart home platform with about 50,000 active users. It shows my long experience in workflow automation, from devices to voice control.
Real-Time Industrial Dashboard for Precision Machinery
A real-time dashboard for precision machinery, built to handle high-frequency data streams and diagnostic alerts. It shows my experience in industrial automation and live monitoring.