Michael Boiman
Quality Engineer · AI Architect
Frankfurt am Main
Freelance Quality Engineer & AI Architect. Available for projects, architecture reviews, and AI workshops.
-80%
Inquiries
through quality monitoring
96%
Quality
after migration (was 30%)
80%
Auto-generated
AI-driven tests
Everything AI needs today — reliability, measurability, self-correction — I spent 20 years building into systems that couldn't yet think. When LLMs arrived, I didn't need a new beginning. I just needed the last puzzle piece.
AI-Driven Chatbot for Trade-Fair Interaction
Challenge
Trade-fair visitors struggled to find relevant information on the website — high bounce rates and missed leads.
Solution
Interactive chatbot with RAG, GPT-4 and vector embeddings, delivering context-aware real-time answers from trade-fair content.
→ Higher visitor engagement on trade-fair websites, fewer lost leads through instant, relevant responses.
Email Classification and Processing Workflow
Challenge
Incoming emails had to be manually read, classified and transferred to SAP — time-consuming and error-prone.
Solution
End-to-end automation with Microsoft Graph API, GPT-3.5-Turbo, Azure Functions and SAP RFC integration.
→ Emails automatically classified, processed and transferred to ERP.
AI Context Orchestrator — Multi-Repo Development Platform
Challenge
Enterprise development across 20+ repos, multiple customers and diverse tools required constant context switching and manual coordination.
Solution
Central control system with ecosystem.yaml as single source of truth, 40+ production skills and hook-based permission system.
→ Fully automated AI workflows — from incident response to meeting documentation without manual effort.
Enterprise AI Consulting: From Strategy to Implementation
Challenge
Organizations recognize AI potential but lack a structured path from vision to measurable implementation.
Solution
End-to-end consulting with strategy development, ROI assessment, executive workshops and implementation support.
→ Measurable AI roadmaps with concrete business cases — from strategy directly to productive solutions.
Quality Dashboard - Real-time Overview
Challenge
Go/No-Go decisions required hours of manual data gathering across 10 test tools, 5 environments and multiple data sources.
Solution
Fully automated end-to-end pipeline with real-time dashboard, multi-source integration and automatic PDF report generation.
→ Go/No-Go in minutes instead of hours. Management decisions data-driven and in real-time.
When you have 10 tools and no overview, you have zero tools.
A million combinations no human can test. But a machine that never sleeps, can.
The best test is the one a developer never had to write.
Automation without measurability is just faster guessing.
Professional Experience
Workshop: Development with Generative Language Models
06/2025Developer Workshop - Agent-based Software Development
Developer Workshop: Comprehensive workshop on modern AI agent development with practical demos and live coding
Workshop Content
• Development with LLMs (Claude, Gemini, GPT-4o) and token optimization - all three models used equally in projects
• Model Context Protocol (MCP) & Agent-to-Agent (A2A) protocol implementation
• Google Agent Development Kit (ADK) for multi-agent systems and tool integration
• Agent orchestration with JSON-RPC and multi-agent systems
• Browser automation with Playwright-MCP for automated test generation
• Live demos: Jira integration, Elasticsearch queries, GitHub workflows
• Prompt engineering & rule-based agent control (.cursorrules, instructions)
• TDD workflows with AI assistance and automated PR creation
• Task Master AI agent for project management and code scaffolding
Technologies & Tools
• Anthropic Claude, Google Gemini, OpenAI GPT-4o (equal expertise across all three LLMs)
• Google Agent Development Kit (ADK), Model Context Protocol (MCP), Agent-to-Agent Protocol (A2A)
• GitHub Copilot, Cursor, VS Code AI extensions
• Playwright, browser automation, web scraping
• JSON-RPC, REST APIs, multi-agent communication
Complete workshop with slides, live demos, and practical exercises for modern AI-assisted development workflows.
LLM Infrastructure Architect & Automation Engineer
06/2025 – presentBKS - AI Research & Development
Development of LLM-orchestrated Enterprise Development Ecosystem: Fully integrated system for knowledge management, project automation, and development workflows with equal expertise in Claude, Gemini, and OpenAI GPT.
Key Responsibilities
• Open Source MCP Server Portfolio: Development and publication of 3+ MCP servers on GitHub (bks-wiki-mcp, hubspot-mcp-bks, bks-codex) with uvx distribution, Claude Desktop integration, and multi-format support (Markdown, JSON, YAML)
• Multi-Agent Orchestration System: Implementation of production-ready A2A system with Orchestrator Agent (routing hub) and Knowledge Agent for inter-agent communication, capability-based Agent Cards, and JSON-RPC 2.0
• Git Wiki Transformation: Migration of Confluence knowledge base to structured Git-based wiki with hierarchical organization and multi-repository architecture (submodules for customer projects)
• MCP Navigation Server: Development of Model Context Protocol server (Python) with intelligent hierarchy navigation, automatic content discovery, and SharePoint integration
• Google ADK Integration: Implementation of Google Agent Development Kit for multi-agent systems and advanced tool integration
• GitHub Project Automation: LLM-driven issue management with 7-mandatory-field system, automatic categorization, smart repository mapping, and review queue management
• Development Workflow Automation: GitHub Actions workflows for fully automatic issue-to-PR transformation (assignment → feature branch → implementation → code review → PR)
• Self-Documenting System: LLM automatically writes project status, meeting protocols, and issue updates back to Git wiki; closed loop of wiki reading → work execution → results documentation → Git commit with structured logging
• Time Tracking Integration: Commit-based work time analysis with automatic Clockify synchronization, intelligent project assignment, and BKS formatting
• Claude Code Plugin Ecosystem: Development of 40+ production skills for enterprise workflows — log analysis, deployment verification, incident handling, email management, meeting transcription, PDF/certificate generation, SharePoint integration
• Context Orchestrator: Central multi-repo control system with ecosystem.yaml as single source of truth for 20+ repositories, automatic cross-repo navigation and structured work tracking with archiving
• Hook-based Permission System: Smart Guard with project-specific security rules for Git operations — branch protection, secret detection and deployment gates
• Production Operations E-Invoicing: Ongoing management of an e-invoicing platform for a leading online job platform — automated incident management, log analysis, weekly reporting and go-live tracking
Tools & Technologies
• LLM Orchestration: Claude, Google Gemini, OpenAI GPT, GitHub Copilot (equal expertise), Model Context Protocol (MCP), Google Agent Development Kit (ADK)
• AI Development Platform: Claude Code, Plugin Architecture (Skills, Hooks, Commands, Agents), YAML/Markdown Configuration
• Multi-Agent: A2A Protocol, Orchestrator/Knowledge Agents, Agent Cards, JSON-RPC 2.0, SSE Streaming
• Backend: Python 3.13, FastAPI, uvx Distribution, Git Submodules
• Automation: GitHub Actions, GitHub GraphQL API, gh CLI
• Integration: SharePoint API, Clockify API, Elasticsearch, Natural Language Processing
• Development: Bash Scripting, jq, Docker, Multi-Agent Systems
Quality Engineer
09/2025 – 02/2026TÜV Süd
Quality Engineering for an enterprise platform for AI-powered document processing in medical device certification (MDR/IVDR) with AI chat integration and data pipeline automation.
Quantifiable Achievements
• 820 BDD test scenarios across 28 feature files with 100% API coverage (66/66 endpoints)
• 88 KQL queries verified for Azure Monitor Workbooks, 8 workbooks tested, 2 newly created
• 54% scenario reduction through systematic equivalence class optimization
Key Responsibilities
• BDD API Test Framework: Development of comprehensive test framework with Python/Behave, self-healing authentication, HTML report generator with embedded API responses
• E2E Test Automation: Playwright E2E test suite for complete user journey (Setup -> Upload -> Transformation -> Download) with 500 error handling and route mocking
• Performance & Monitoring: Development of Azure Monitor Workbooks (QA Live Testing Companion, Error Investigation Assistant) with KQL for end-to-end monitoring
• Bug Analysis & Quality Intelligence: Implementation of comprehensive bug tracking system with WIQL queries, automated dashboards, and executive PDF reporting
• Pipeline Integration: Test automation in Azure DevOps CI/CD pipelines with HTML report upload to Azure Test Results
• AI-Powered Automation: Development of automation skills for workflow optimization, bug analysis, and incident response with measurable time savings
Tools & Technologies
• Testing: Behave, Playwright, TypeScript, Python, pytest, Page Object Model, Fixtures
• Monitoring: Azure Monitor Workbooks, KQL, Application Insights, Log Analytics
• Backend: FastAPI, Python, Pydantic, SQLModel, Azure Functions, Azure Service Bus
• Frontend: React, TypeScript, Vite, TanStack Router
• AI Integration: Azure OpenAI (GPT-4o), LangChain, Azure AI Search, Embeddings
• DevOps: Azure DevOps Pipelines, Git, Docker, Azure Blob Storage, Poetry
AI-driven Automated QA Environment for Energy Infrastructure
07/2024 – 01/2025AkkuSwap Startup
QA Leadership for EU-wide Battery Swap Infrastructure: AI-driven simulation tool for battery swap station network with energy infrastructure integration
Key Responsibilities
• QA concept, design and implementation for AI-driven simulation of EU-wide infrastructure
• QA framework development for inhouse AI server infrastructure
• Proof-of-concept for automated testing of AI-driven simulations
Energy Sector Connection
• 50 Hertz Participation: 50 Hertz (Elia Group subsidiary) participated in research project eHaul, the predecessor of AkkuSwap
• Direct energy sector experience with critical infrastructure quality requirements
• Understanding of 99.99% reliability standards for energy transmission systems
Technical Stack
• Infrastructure: Linux, Docker, Azure OpenAI
• Automation: pytest, AI code generation integration patterns
• Monitoring: Grafana, Azure Monitoring
• Energy Systems: Battery swap infrastructure, grid integration simulation
Key Achievements
• Established QA methodology for AI-driven infrastructure simulation
• Created testing framework for energy sector critical systems
• Validated proof-of-concept with measurable reliability improvements
Presentation: Efficient Documentation through Automation
04/2025Enterprise Presentation - AI-powered Documentation Workflows
Enterprise Presentation: Demonstration of modern automation approaches for centralized, current documentation and sustainable project success
Key Focus Areas
• Single Source of Truth: Central truth in Confluence, avoiding redundant versions
• Shift-Left Documentation: Parallel code and documentation development for higher currency
• Automation First: Bots and CI/CD jobs for recurring tasks, automatic updates
• OpenAPI Documentation: Automatic generation on code merge, Consumer-Driven Contracts
• Documentation Debt Management: Dashboard-based visibility, Tech-Debt labels
• Automated Quality Assurance: Unit tests, integration, end-to-end reports
Technical Solutions
• Template-based standardization with mandatory and optional fields
• Label system instead of traffic lights for multi-dimensional filtering (status:draft, domain:payments)
• Semantic Release for automatic release notes
• Code changes aligned with documentation
• KPI/OKR dashboards for measurable progress
Tools & Integration
• Confluence, GitHub, Jira, MkDocs, OpenAPI
• CI/CD pipeline integration for documentation automation
• Monitoring and dashboard creation for Documentation Debt
Earlier Positions
Education
Diploma in Computer Science (UAS)
Cologne University of Applied Sciences, Gummersbach
2000 – 2005
ISTQB Certified Tester
2005
Certified Dynatrace Diagnostics Basic Training
2025
Languages
Skills
Quality Engineering · Playwright · Cucumber/Gauge · Python · LLMs (Claude/Gemini/GPT/Copilot) · MCP & A2A Protocols · Google ADK · LangChain · Peppol/E-Invoicing · CI/CD · Kubernetes · Azure Functions · Grafana · Elasticsearch · REST APIs · Docker · JMeter · Gatling