MLOps.community A Playground for AI/ML Engineers
18 snips
Jan 23, 2026 Paulo Vasconcellos, Principal Data Scientist for Generative AI Products at Hotmart and co-founder of Data Hackers, builds AI tools for creators and learners. He discusses using LLMs alongside classic NLP for speed and cost. He explores multilingual model choices, agent-as-a-product creator tools, Hotmart Tutor as a 24/7 teacher, and engineering tradeoffs for scalable ML and safety guardrails.
AI Snips
Chapters
Transcript
Episode notes
Weigh Tradeoffs Before Replacing Models
- Evaluate tradeoffs before replacing classical models with LLMs, weighing training cost, drift, and infrastructure.
- Maintain pipelines for continuous training and monitoring if you choose classical approaches.
Hotmart Tutor: AI As A Digital Teacher
- Hotmart Tutor is a 24/7 AI teacher that answers students using only the creator's content and RAG components.
- Paulo said it uses LLMs, retrieval, fallbacks, and guardrails and has been a major success for creators and students.
Measure Agents By Feedback And Retention
- Measure agent success via user feedback and repeat engagement, not just initial usage.
- Paulo emphasized thumbs-up/down and weekly return rates as stronger indicators of tutor value.