Workshop "Everything AI" with Olaf Monien at Hotel Hesselet, April 28 - 29, 2026

 Olaf Monien:

Everything AI

April 28 and 29, 2026
Hotel Hesselet, Christianslundsvej 119, 5800 Nyborg

About Olaf Monien

Olaf Monien  is a globally recognized Delphi expert and long-time Embarcadero MVP, known for his deep technical insight and practical approach.

He has worked professionally with Delphi for decades and is a frequent speaker at international conferences and workshops.

Olaf specializes in modern Delphi development, software architecture, and high-performance systems.

In recent years, his focus has expanded strongly into Artificial Intelligence, demonstrating how AI can be both embedded into Delphi applications  and used to enhance the development process itself.

His presentations are valued for their clarity, real-world relevance, and engaging delivery.

We are very much lookring forward to seeing you at the workshop.

Because of a limited number of rooms at Hotel Hesselet, we suggest that you register for the workshop as soon as possible.

You find the registration form here

Please note that you must register on Friady March 27, 2026 at latest.

If you want to participate in the workshop, but did not register in time, please send an email including contact info to dapug@veco.dk. There is a good chance that we can find a solution.

Workshop participation requires that you or your company is a paying member of DAPUG. The annual membership fee of DKK 800 covers all registrants for that company. If you are not representing a company you will need to have a personal membership of DAPUG, which is also an annual fee of DKK 800

Workshop registration fee is DKK 7.800 per participant. This includes both workshop days, including all meals and accommodation.

Worksthop Agenda

Tuesday: Day 1 - AI-Assisted Development with Delphi

08:00 – Arrival

09:30 – Welcome

• The Impossible Intro - What AI can do for Delphi developers
• Overview of Day 1 and Day 2
• Wi-Fi, Delphi toolchain check
• Git intro for beginners
• Clone workshop repo, build + tests green

10:00 – AI Fundamentals

• What is an LLM? (Transformer, tokens, context window)
• Model landscape: GPT-5, Claude, Gemini, Llama, Mistral, DeepSeek
• Provider vs. model vs. API
• Cloud vs. local: latency, cost, privacy
• API basics: prompt, completion, streaming, temperature

10:15 – AI Today: State of the Art

• From autocomplete to agents
• What works, what doesn't
• Opportunities for Delphi teams
• Risks: hallucinations, security, licensing, "silent breakage"
• Where does my data go?
• Markdown as the "glue" in AI development (README, CLAUDE.md, prompts, conventions)

10:45 – Break

11:00 – Coding Agents in Practice

• Live comparison: Claude Code, Kilo.ai, Chucki.ai
• Tasks: implement feature, refactor legacy, fix bug, explain code
• Steering agents effectively, avoiding "AI drift"

11:30 – UI Development with AIFrom thought to design: AI-assisted UI workflows

• Tools: Figma, Pencil
• MCP (Model Context Protocol): connecting AI to external tools and data

12:00 – Lunch

13:00 – Hands-on Block 1: Build the Project

• Teams work through prepared backlog (6-10 tickets)
• Gates: build green, tests green, review, prompt log

14:00 – Break

14:10 – Hands-on Block 2: Model Shootout

• Compare cloud + local models in real repo
• Criteria: planning, refactoring, tests, debugging, Delphi idioms
• Outcome: task → model matrix

15:00 – Coffee Break

15:15 – Day 1 Wrap-up: Workflow Kit

• Delphi prompt library
• Review checklist + AI safety rules
• Repo conventions
• Model/tool selection matrix

16:00 – A word from Noyau

18:30 – Drinks / 19:00 – Dinner

Wednesday: Day 2 - AI Inside Delphi Applications

07:00 – Breakfast & Check Out (Please Check Out from your room before 09:00)

09:30 – Session 1: Models for App Problems

• Perspective shift: not "writing code" but "solving user problems"
• Micro-exercise: same prompt, different models
• Evaluation: correctness, latency, format, cost, privacy

10:15 – Session 2: Production AI Layer in Delphi

• Provider abstraction (cloud/local interchangeable)
• Streaming, timeouts, retries, cancellation
• Logging with redaction
• Cost awareness hooks

10:45 – Break

11:00 – Session 3: Tools / Function CallingImplement tool dispatcher

• Examples: DB query, log parser, validation, reports
• Flow: model → tool call → Delphi → result → model

12:00 – Lunch

13:00 – Session 4: Generic vs. Component Integration

• A) Hand-rolled: HTTP/JSON, full control
• B) MakerAI-style: Delphi-native components
• Refactoring: app code depends only on interfaces
• Backend swappable

14:00 – Coffee Break

14:15 – Hands-on Block: Ship AI Features

• Smart Customer Search — "Show me all customers from Hamburg who didn't order last
• year"
• Invoice/Document Parser — PDF/scan → structured data (OCR + LLM)
• Feature Brainstorm — attendees pitch & implement their own AI feature idea

Each feature: UI entry point, tests, safety checklist

15:00 – Break

15:10 – Final Wrap-up: Production Checklist

• Security & privacy
• Latency & UX
• Cost controls
• Observability
• Testing & rollout

16:00 – Evaluation & Goodbye