Lessons learned from building cool products (winners of MLOps Discord demos)

Today, we have wonderful speakers to share their lessons from building cool products!
00:20 Lessons learned from building a hybrid system (LLM + NLU + RAG) for intent classification (Denys Linkov)
15:04 Lessons learned from building a copilot for Obsidian (Eugene Yan)
28:57 Lessons learned from building a reproducible notebook for AI/ML using graphs (Akshay Agrawal)
46:17 Lessons learned from replicating Tesla's data flywheel for food images (Daniel Bourke)
1:05:37 Lessons learned from programming agents using graphs (Yoan Sallami)
1. Eugene Yan, senior data scientist at Amazon: lessons on building a copilot for Obsidian github.com/eugeneyan/obsidian...
2. Denys Linkov, head of ML at Voiceflow: lessons on building a hybrid system (LLM + NLU + RAG) for intent classification www.voiceflow.com/blog/benchm...
3. Akshay Agrawal, co-founder of Marimo and developer/maintainer of CVXPY (700K monthly downloads): lessons on building a reproducible notebook for AI/ML github.com/marimo-team/marimo
4. Daniel Bourke, co-founder of Nutrify, creator of zerotomastery.io and the popular TH-cam channel under his name (170K subs): lessons learned replicating Tesla's data flywheel for food images nutrify.app/launch
5. Sallami Yoan, co-founder of SynaLinks: lessons from programming agents using graphs github.com/SynaLinks/HybridAGI
The problems they solve are important, and we’re impressed by their approaches. Fun fact: Akshay, Daniel, and Sallami are all bootstrap founders. It’s really cool how far they’ve been able to take their products!

[@mrdbourke]

Great presentations and products! Thank you for having me!