Manouk Draisma
@ManoukDrai47041
Agent Simulations are the new unit testing.
In agent demos, everything’s smooth. In prod? You get messy inputs, long chains, weird edge cases — that’s when things snap. We treat agents like code → write scenario tests first, simulate full workflows, then iterate until green. Think TDD, but for LLMs. More on how we do it…
“Do I really need evals?” The real q: how do you know your AI agents will behave in prod? Prototypes don’t need them. Scaling products do. That’s why we built Agent Simulations; Unit tests for AI. The only way to know if you can ship reliably. OSS: github.com/langwatch/scen…
AI SDK Observability Integration: @LangWatchAI Observability and evals are crucial when developing AI applications. You can use LangWatch with the AI SDK to monitor and evaluate your LLM calls:
United States Trends
- 1. #Worlds2025 46.3K posts
- 2. Doran 18.9K posts
- 3. #T1WIN 29.3K posts
- 4. Good Sunday 46.6K posts
- 5. Faker 33K posts
- 6. Sam Houston 1,620 posts
- 7. Oregon State 4,749 posts
- 8. #T1fighting 3,619 posts
- 9. Vergil 8,795 posts
- 10. Boots 30K posts
- 11. Lubin 5,917 posts
- 12. Option 2 4,349 posts
- 13. #Toonami 2,731 posts
- 14. Keria 11.4K posts
- 15. Hyan 1,484 posts
- 16. Frankenstein 127K posts
- 17. Louisville 14.5K posts
- 18. UCLA 7,829 posts
- 19. #GoAvsGo 1,607 posts
- 20. Oilers 5,380 posts
Something went wrong.
Something went wrong.