Prompt Engineering Expert

CXO AI OS is an agent system made up of six building blocks. Instead of using AI as a chat window, it creates a system that knows a company's context, makes decisions according to its rules, and acts on its behalf.

• For SMEs: guided sprint followed by ongoing operation for a team, department or prioritized cluster, based on an AI assessment
• For self-employed people: program in which participants build their own agent system
• Sequence in the company: assessment, prioritization, sprint, operation
• Implementation in Claude Cowork or ChatGPT Work, without programming
• Architecture: Chief of Staff, Goals, Advisors, Agents, Context, Catalog

• Design, development, and productive rollout of an Enterprise HR Copilot based on Microsoft Copilot Studio to automate internal HR processes
• Development of an AI-supported assistant for answering employee inquiries based on a SharePoint knowledge base and internal company HR documentation
• Integration of the Copilot into Microsoft Teams, including welcome logic, user guidance, and role-based routing
• Automation of HR processes and approval workflows with Microsoft Power Automate to reduce manual processing steps
• Development of realistic HR documents and response templates with Azure OpenAI, taking business requirements and consistent company policies into account
• Implementation of prompt strategies, knowledge management, and response optimization to improve response quality and user acceptance
• Close collaboration with business departments to analyze requirements and integrate the AI solution into existing company processes

Technologies:

Microsoft Copilot Studio, Microsoft Teams, Azure OpenAI, SharePoint, Power Automate, Power Platform, Microsoft 365, Prompt Engineering, Workflow Automation

• Lecturer in AZAV-certified, one-month training programs on AI fundamentals and practical applications, with several cohorts since February 2026
• Design and delivery of all modules for participants from different professional fields
• Teaching how generative AI works, its areas of application and limitations, as well as prompting and evaluation practices
• Created all teaching materials and exercise formats independently
• Supporting participants throughout the entire course period

• Development of a system for capturing, storing, and using knowledge
• Assessment of the current status and requirements for capturing employees’ tacit knowledge
• Creation of the appropriate taxonomy for the individual specialist areas
• Establishment of a suitable technical architecture
• Conducting expert interviews with the help of Artificial Intelligence (AI)
• Concept for data backup
• Analysis and evaluation of the approach and results
• Incorporation of organizational changes

The client operates a SaaS platform for managing rail and intermodal transport (Rail-Flow Transport Management Platform).

For two of its customers, it was looking for a 3-month project management replacement. Both customers offer rail and intermodal transport services. Implementation progress differs: one customer is already live and wanted its Phase 2 enhancements implemented; the other customer is implementing its MVP and entering an intensive testing phase.

As part of the assignment, project management was taken over, including management of the internal development team (offshore Turkey).

• Took over complete project management for 2 customer projects, including the roles of Product Owner and Co-Scrum Master
• Managed agile implementation teams consisting of business analysts, implementation consultants, developers (offshore) and QA staff
• Ensured compliance with and further development of project governance
• Planning and rollout management: creation and maintenance of project and rollout plans as well as coordination of role assignments with the client’s management
• Requirements and change management: management of contractual requirements, bugs and changes
• Customer and project communication: organization and moderation of status meetings and steering committees
• Identification of project risks, initiation of countermeasures and escalation
• Ensured correct and timely invoicing for project services together with Finance

Methods: Scheduling (forward- and backward-based), including milestone planning, structured interviews, multi-project management (in English)

Tools / Technologies: Jira, Confluence / Atlas, Claude (Skills, Artifacts), MS Outlook

• Functional requirements management for DIVID, the Umweltbundesamt platform for administering the single-use plastics fund. Focus: entitled parties, sub-entitled parties, and benefit reports.
• Consolidation and analysis of specifications, Jira, Confluence, functional concepts, and UX designs. Independent structuring and delimitation of requirements, as well as identification of contradictions, gaps, and dependencies.
• Creation and quality assurance of implementable user stories with clear, testable acceptance criteria. Preparation of decision alternatives and coordination with business, development, UX, and QA through team refinement.
• Conducting manual and technically assisted accessibility tests. Coordinating findings with QA and the Product Owner for further planning and implementation.
• Result: more consistent requirements, clearly defined processes and stories, and transparent open decisions. Separation of assumptions from confirmed requirements; better basis for implementation, refinements, and QA test cases.

Tools used: Jira, Confluence

• I support medium-sized clients with their funding needs.
• I evaluate operational business processes and translate complex legal and regulatory requirements into business requirements, target models and actionable roadmap epics.
• I use Generative AI tools and automation in a targeted way to efficiently create requirements documentation, process analyses, evaluations, meeting preparation materials, customer analyses and decision papers.

• Claude Code subagents, MCP, Pydantic V2, pytest, bandit

• Designed and shipped 3 specialized agents that hand work down a line: a research agent writes a cited implementation spec, a coding agent builds the modular code and its tests, a review agent ranks findings by severity and applies the fixes. Each handoff is a structured document, so no stage depends on another agent's context window.

• Connected the research agent to an academic-research MCP server (Semantic Scholar, ArXiv, Hugging Face Hub, citation snowballing) so every reference traces to a tool result rather than the model. Gated commits behind ruff, mypy, pytest and bandit, required human sign-off before installs and commits, and persisted session state on disk so long runs survive a context reset.

• Fundamentals of electronics measurement, electropneumatic circuits & protective measures according to DIN-VDE
• Installation, wiring and commissioning of PLC-controlled Systems

• Set up backend assistants, prompt engineering, customer communication, growth strategy

• Successful implementation of AI shopping assistants e.g. Thalgo.de

• Product Analytics, Mobile App Tracking & Tracking Governance (B2C Mobility App) – agile project management (Scrum/Kanban)
• Product Ownership for Product Analytics and Mobile App Tracking of the EnBW mobility+ app; gathering, prioritizing, and translating business requirements into actionable concepts and Azure DevOps user stories with acceptance criteria.
• Derivation of tracking requirements when introducing new app features (including Resilient Map), definition of tracking parameters (screens, events, custom definitions), and ensuring privacy-compliant tracking (Firebase, GA4, Adjust) based on the tracking concept.
• Design and adaptation of dashboards and funnel reporting for campaigns (GA4 validation, onboarding and order flow analyses, conversion funnels, charging start flow) to identify drop-off points and optimization potential.
• Management of the technical raw data export (Adjust to BigQuery) and connection to the data warehouse/data lakehouse, including data mapping; collaboration with international development teams, Data Engineering, Marketing/Sales, and Product Management.
• Establishment of standardized tracking architecture, naming conventions, and governance; analysis and expansion of tracking (new features and “blind spots”), test design, handover to testers, and quality assurance and approval before releases; documentation in Conceptboard.

• Built a customized MediaWiki instance, including installation, MySQL database, SSL, and automatic backups
• Set up user roles (Admin, Mod, Verified, User) and a permissions system
• FlaggedRevisions for editorial review workflows · Commenting and rating extensions

• Develop custom AI agents delivering 90%+ reduction in manual workload and significant efficiency gains
• Provide end-to-end AI strategy consulting: from digital assessment to implementation and change management
• Design and deliver tailored training programs and workshops on AI adoption, prompt engineering, and automation
• Support clients in implementing scalable AI solutions integrated with existing technology stacks
• Focus areas: AI strategy, automation, workflow optimization, and capability building

Stabilization of an Azure/.NET landscape in live operation.

• Architecture, DevOps, and operational readiness; technical decisions under time pressure
• Azure DevOps, monitoring, ETL/ELT, cloud security, FinOps, and data-mesh-related topics

Technologies: Azure DevOps, .NET, CI/CD, monitoring, FinOps