AI for your Customers, AI for your Code: mastering both sides of the game

Join us for a practical session on taking AI from prototype to production. Through a real-world customer-service case and a review of modern AI coding tools, our speakers will share hands-on lessons, evaluation strategies, and pragmatic best practices you can apply immediately. The event closes with a roundtable discussion and networking.

What you will take away

• A clear, use-case-driven view of AI Engineering: architecture, productionization and pitfalls.
• Practical insights from a Scheppach customer-service project using agentic AI.
• An overview of AI-for-coding tools (Copilot, Claude Code, Cline, etc.) and where they help — and where they don’t.
• Best practices for integrating AI into development workflows: requirements engineering, code review, testing and evaluation.
• Realistic expectations for productivity gains and operational responsibilities (monitoring, metrics, human-in-the-loop)..

Who should attend
Engineers, product managers, technical leads, AI enthusiasts and anyone responsible for designing, evaluating or deploying AI systems who wants practical, production-focused guidance.

RSVP
Reserve your spot and bring your toughest production questions — this session focuses on actionable takeaways you can use on your next AI project.

BRIEF AGENDA

1. Welcome & Intro
2. Talk 1: AI Engineering
3. Talk 2: AI for Coding
4. Roundtable/Discussion
5. Networking & Closing

FULL AGENDA

🎤 Talk 1: AI Engineering
Focus: Use case-driven approach using Scheppach customer service project with agentic AI.
Key topics:

• What is AI Engineering?
• Real-world use case: Scheppach customer service with agentic AI
• Productionization of AI systems
• Evaluation strategies and metrics
• Lessons learned from production deployment

💻 Talk 2: AI for Coding
Focus: Overview of AI coding tools and practical insights on effective usage.
Key topics:

• AI coding assistants landscape (Microsoft Copilot, Claude Code, Cline, etc.)
• Use cases: Code generation, refactoring, testing
• Best practices for AI-assisted development
• Critical insight: Importance of requirements engineering
• Can't rely too heavily on AI-generated tests
• Workload shift: from implementation time → requirements engineering & code review
• Limitations and when AI doesn't help
• Productivity gains and realistic expectations

🎬 Round Table
Round table & Discussion round