GenAI tools promise speed, but without solid domain models, they hallucinate and create waste. This talk shows how Domain Modeling techniques give AI the structure it needs while AI gives the speed teams crave to understand their domain more quickly. Attendees will learn concrete techniques—prompt libraries, RAG knowledge bases, code-generation guardrails—to move from sticky notes to production-grade code in a single sprint. We will examine how GenAI can be integrated with Domain Modeling techniques to better assist teams during development.

Target Audience: Architects, Managers, Project Leaders, Coaches, Developers, Product Owners, Decision Makers
Prerequisites:Basic understanding of architecture and development, and some familiarity with domain modeling
Level: Practicing

Extended Abstract:
While most development processes—even agile ones—emphasize the outer loop of the software-delivery lifecycle (prioritizing, estimating, tracking and releasing), very little guidance exists for the core activity that turns ideas into working software: systematically modelling the domain and translating it into clean, maintainable code. Domain Modeling techniques such as Domain-Driven Design (DDD) tackle exactly that problem, yet it remains the domain of a small cadre of senior engineers and is often ignored by agile teams in favor of a vague “emergent design” ideal.

Over the past two years, we have applied Domain Modeling techniques in multiple agile projects augmented by the latest generative-AI tooling—ChatGPT, Claude, GitHub Copilot, Codex CLI, and vector-RAG indexes. We discovered a powerful feedback loop:

• Domain Modeling gives GenAI precise hooks (ubiquitous language, events, invariants) so prompts stay grounded.
• GenAI compresses heavy domain modeling chores—capturing workshop notes, synthesizing business rules, scaffolding aggregates, generating exhaustive tests—into minutes instead of days.

This session shares field-tested recipes for inserting Domain Modeling techniques (Event Storming, context mapping, tactical patterns) into agile cadences and steering GenAI at each step to produce refined business rules, acceptance criteria, architectural decisions, starter code, and living documentation. Attendees leave with actionable templates, pitfalls to avoid, and metrics that prove the payoff.