[Nerdearla Argentina 2025] LLMs 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 @talyssonoc
2. Talysson Oliveira Software architect & Chief Learning Officer at Codeminer42 @talyssonoc beacons.ai/talyssonoc
3. codeminer42.com @codeminer42
4. First of all: what is a domain?
5. Domain - Finance - Health - Education - Commerce - Aviation - Mining - Transportation - … Problem A system of abstractions that describes selected aspects of a domain and can be used to solve problems related to that domain Domain Model
6. Airplane (domain) Plane model - Business relevance - Mentioned in conversations - Involved in business rules
7. How is the model cultivated?
8. Domain experts Development experts
9. Domain experts Development experts Domain model
10. Domain experts Development experts Domain model
11. Domain experts Development experts Domain model Ubiquitous language
12. Why domain experts may 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)
13. Can LLMs be used in these cases?
14. Yes!
15. Yes! I mean, kind of!
16. The model exists in the shared understanding of the team
17. LLMs can't cultivate a model
18. They can be used to provide information about the domain
19. Using LLMs to enrich your knowledge about the domain
20. Domain experts Development experts
21. Domain experts Development experts
22. Domain experts Development experts
23. Domain experts Development experts We do this first
24. Domain experts Development experts We do this first To make the best out of this
25. Domain Other Domain
26. If you don't know where you are going, any road will get you there. - Lewis Carroll
27. You can't "vibe" your way to something you can't recognize when you get there
28. Domain Problem
29. Example: Special in-flight meals
30. In-flight meals
33. What problem are we solving?
34. Special in-flight meals - 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
35. In-flight meals Logistics
40. In-flight trolleys (meal carts) In-flight meal shortage Cold chain HACCP (Hazard Analysis Critical Control Point) Long-haul flights Extra in-flight meals Turnaround schedules
41. Then, ask about these concepts in the same conversation (within the same LLM context)
44. Domain experts Development experts HACCP HACCP
45. Domain experts Development experts HACCP
46. Use LLMs to optimize the conversations with domain experts!
47. What if there are no domain experts?
51. The development experts become the domain experts
52. Use LLMs to empower your team while the team cultivates the domain model
53. Using LLMs to make the access to the model easier for the whole team
54. LLMs can't cultivate a model
55. You can't teach them the model LLMs don't think
56. But you can document the model as much as possible and feed it to a LLM
57. [...] the programmer's knowledge transcends that [knowledge] given in documentation [...] - Programming as Theory Building, Peter Naur, 1985
58. But it can be good enough! The documentation does not contain the totality of the model
59. Documenting the domain model - Sub-domains and bounded contexts - Scope and responsibilities - Ubiquitous language glossary - Context map - Use cases and user stories of your system - Tactical patterns - Aggregates, entities, value objects, repositories, domain services, …
60. Make the documentation LLM-friendly - Don't leave important concepts implicit - When images are needed, add a description as well - Explicitly state possible misunderstandings - E.g.: "Don't confuse <concept> with <another concept>"
61. Use tools to make it even more LLM-friendly - Use team workspaces in LLM chat tools - Connect the LLM to MCP servers of your documentation platform - GitHub - Confluence - Notion - Use well-known LLM-friendly formats for coding tools - AGENTS.md - CLAUDE.md
62. Keep your documentation updated! No documentation is better than bad/outdated documentation
63. LLMs as domain experts - LLMs can't be fully trusted, they can hallucinate - Arguably, humans can make mistakes too - The difference there is that humans can be held accountable - Human domain experts provide domain expertise and collaboratively cultivates the model - LLMs can be used to the former, but should not be used for the latter
64. Use LLMs to empower your team, not to replace it
65. ¡Gracias! @talyssonoc beacons.ai/talyssonoc @codeminer42 codeminer42.com