Behind the scenes of the engineering and AI serving thousands of dental clinics.
Why monitoring AI agents is a different game: traces, a single LLM evaluator, human review and prompts treated as code — our day-to-day routine.
Kaique Nogueira ·
· 5 min
Designing the identity of Camila, Capim's AI assistant: from user research to AI-generated videos — and the 113 new clinics that connected.
Bruno Rodilha and Larissa Corte ·
· 8 min
How we doubled our agent's escalation accuracy with error analysis and manual annotation — and why LLM-as-a-Judge wasn't the way.
Lucas Rego ·
· 6 min
