[Explore DDD 2026] LLM AIs as domain experts

Collaborating with domain experts is essential to practicing DDD, but sometimes it can be challenging for various reasons. Maybe the communication is not in tune to make the domain knowledge possible to use yet, or their availability to answer your questions is not enough, you might even not have a proper domain expert on the team! These might be occasions where an LLM AI primed to act like a domain expert might be just what you need. So in this talk, we’ll discuss how to use LLMs as powerful tools when practicing DDD!

Transcript

1. LLMs as domain experts
2. Talysson Oliveira Software architect & Chief Learning Officer at Codeminer42 @talyssonoc talysson.com
3. dddbrasil.com.br linkedin.com/company/dddbrasil youtube.com/@ddd-brasil
4. ⚠ This is not a "how to drive a project with AI" talk Also not an "AI is bad/good" talk talysson.com
5. Can LLMs be used as domain experts? talysson.com
6. Can LLMs be used as domain experts? Can LLMs automate DDD practices? talysson.com
7. Automating Domain-Driven Design: Experience with a Prompting Framework Eisenreich, T., Jusic, H., & Wagner, S. (2026, March 27) https://arxiv.org/abs/2603.26244v1
8. Requirements Input Ubiquitous Language Establishment + Event Storming Simulation System Prompt: DDD Specialist and Architecture Sparring Partner Bounded Contexts Identification Aggregate Design Technical Architecture Mapping Eisenreich, T., Jusic, H., & Wagner, S. (2026, March 27) https://arxiv.org/abs/2603.26244v1 Domain Model
9. Ubiquitous Language Establishment Event Storming Simulation Errors accumulate without guidance Bounded Contexts Identification Aggregate Design Technical Architecture Mapping Eisenreich, T., Jusic, H., & Wagner, S. (2026, March 27) https://arxiv.org/abs/2603.26244v1
10. Ubiquitous Language Establishment Event Storming Simulation Errors accumulate without guidance Bounded Contexts Identification Aggregate Design Technical Architecture Mapping Eisenreich, T., Jusic, H., & Wagner, S. (2026, March 27) https://arxiv.org/abs/2603.26244v1
11. Can LLMs automate DDD practices? Some of them talysson.com
12. Should we automate these DDD practices? talysson.com
13. Ubiquitous Language Establishment Builds a shared understanding of the model Event Storming Simulation Errors accumulate without guidance Bounded Contexts Identification Aggregate Design Technical Architecture Mapping talysson.com Requires understanding of the model
14. Ubiquitous Language Establishment If you fully automate these Event Storming Simulation Errors accumulate without guidance Bounded Contexts Identification Aggregate Design Technical Architecture Mapping talysson.com You won't be able to guide these
15. Does it mean we should not use AI with DDD? No, but humans should be active, especially in the groundwork talysson.com
16. What about SDD? Spec-Driven Development talysson.com
17. Idea Specification Implementation Refinement talysson.com Validation
18. "The code is a lossy projection from the specification" AI Engineer. (2025, July 12). The New Code - Sean Grove, OpenAI. https://www.youtube.com/watch?v=8rABwKRsec4
19. A set of properties a useful specification needs - Communicates meaning and intent - Uses a consistent and unambiguous vocabulary - Define a scope to which it applies talysson.com
20. DDD spent 20 years solving a problem SDD just discovered it has: Effective and meaningful communication talysson.com
21. We just need to write very detailed specifications! … right? talysson.com
22. "[...] would be an utterly simple person […] if he thinks written words are of any use except to remind him who knows the matter about which they are written, […] if you question them [the words], wishing to know about their sayings, they always say only one and the same thing [...]" - Phaedrus, Plato, 370 BC talysson.com
23. "[...] the programmer's knowledge transcends that [knowledge] given in documentation [...]" - Programming as Theory Building, Peter Naur, 1985 talysson.com
24. "The code is a lossy projection from the specification" talysson.com
25. "The code is a lossy projection from the specification" The specification is a lossy projection from the model talysson.com
26. The model isn't a document or the code It is shared understanding and intuition talysson.com
27. Where is AI useful when practicing DDD? talysson.com
28. LLMs as domain experts talysson.com
29. LLMs as domain experts Why would we want LLMs as domain experts? talysson.com
30. To represent a problem + solution, we need a domain model To explore a domain model, we need domain knowledge To have domain knowledge, we need domain experts And sometimes, domain experts may not be available talysson.com
31. Why would domain experts not be available - Their available time is scarce - The access to them is not easy or practical - The communication is not in tune yet - The team doesn't have domain experts (yet) talysson.com
32. How can LLMs help us in these cases? talysson.com
33. Ubiquitous language Domain experts talysson.com Development experts
34. Domain experts talysson.com Development experts
35. Domain experts talysson.com Development experts
36. Domain experts Development experts We do this first talysson.com
37. To make the best out of this Domain experts Development experts We do this first talysson.com
38. Example: Special in-flight meals talysson.com
39. In-flight meals talysson.com
40. talysson.com
41. talysson.com
42. You can't "vibe" your way to something you can't recognize when you get there talysson.com
43. What problem are we solving? talysson.com
44. Special in-flight meals system - Allow airlines to offer special in-flights meals paid in advance - Customers order special meals up to 5 hours before the boarding - A list of meals is sent to a specialized company, which will cook and deliver them directly to the airports - Customers can rate their experience and be part of a loyalty program and get discounts and gifts talysson.com
45. In-flight meals Logistics talysson.com
46. talysson.com
47. talysson.com
48. talysson.com
49. talysson.com
50. In-flight trolleys (meal carts) Turnaround schedules Extra in-flight meals Cold chain Long-haul flights talysson.com HACCP (Hazard Analysis Critical Control Point) In-flight meal shortage Standardization
51. Then, ask about these concepts in the same conversation (within the same LLM context) talysson.com
52. talysson.com
53. talysson.com
54. HACCP Domain experts talysson.com HACCP Development experts
55. HACCP Domain experts talysson.com Development experts
56. Use LLMs to prime yourself for conversations with domain experts talysson.com
57. But there are two catches! talysson.com
58. 1 An LLM will give you the industry-average knowledge This knowledge/vocabulary might not work for your case talysson.com
59. 2 LLMs are sycophants "You're absolutely right!" The "tone" you use with LLMs might push them towards the wrong direction talysson.com
60. Pay close attention to the confidence provided by conversations with LLMs talysson.com
61. What if there are no domain experts? talysson.com
62. talysson.com
63. talysson.com
64. talysson.com
65. Use LLMs to empower your team while the team explores the domain model talysson.com
66. Can LLMs help during EventStorming? talysson.com
67. Yes But the LLM is never in the room talysson.com
68. Roles played outside of the EventStorming room 1. Make the industry-average knowledge useful - 2. 3. Generate candidate domain events before the session, read and compare with the wall only afterwards Role-play the absent stakeholder - Generate questions the absent stakeholder would make, never answers - Direct the questions to this person after the session Check the graph structure - talysson.com Events with no trigger or consumer, orderings that can't happen, …
69. Using LLMs to make the access to the model easier for the whole team talysson.com
70. LLMs don't think You can't give them model intuition talysson.com
71. But you can document the model as much as possible and feed it to a LLM talysson.com
72. The documentation does not contain the totality of the model But it can be good enough! talysson.com
73. Documenting the domain model - Sub-domains and bounded contexts - Scope and responsibilities - Ubiquitous language glossary - Context map - Specifications, use cases and user stories of your system - Tactical patterns talysson.com - Aggregates, entities, value objects, domain services, … - Architecture Decision Record (ADR)
74. Written (or at least guided) by a human - Your documents should use the ubiquitous language - Actively guide it not to let LLMism sneak into it - Otherwise your docs will eventually look like this: - - "This check is load-bearing in the process" - "And it answers the question plus expose one more wrinkle" - "And the trap is zero-dollar invoices" Said no human domain expert ever talysson.com
75. Fill the gaps where an LLM could hallucinate - Don't leave important concepts implicit - When images are needed, add a description as well - Explicitly state possible misunderstandings - E.g.: "<concept> is not the same as <another concept>" - Zero documentation is better than misleading/outdated documentation - But zero documentation means the LLM gets more… creative - Treat hallucinations as a sign of a gap in your docs talysson.com
76. Checking the ubiquitous language with LLMs 1. Synonyms - 2. Homonyms - 3. "Find one word that is used for more than one concept" Glossary drift - 4. "Find two or more words used for the same concept" "Find terms in code that aren't in the glossary, and vice-versa" Name vs behavior - talysson.com "The glossary says XYZ, does the code agree?"
77. Use tools to make it even more LLM-friendly - Use team workspaces in LLM chat tools - Connect the LLM to MCP servers of your platforms - - Version control system (GitHub, Gitlab, …) - Wiki (Confluence, Notion, …) - Project management (Jira, Linear, …) Use well-known LLM-friendly formats talysson.com - AGENTS.md / CLAUDE.md - Mermaid diagrams - Skills for well-defined patterns
78. talysson.com
79. LLMs as domain experts - LLMs can't be fully trusted, they can hallucinate - Arguably, humans can make mistakes too - The difference being that humans: - Can actually think - Have long-term memory - Can be held accountable - Domain experts provide expertise and collaboratively explore the model - LLMs can be used to the former, but should not make decisions on the latter talysson.com
80. It's ok to let LLMs write the code But the model belongs to humans talysson.com
81. Thank you! @talyssonoc talysson.com