​🦄 ai that works

​A weekly conversation about how we can all get the most juice out of todays models with @hellovai & @dexhorthy

​https://www.github.com/hellovai/ai-that-works

​

​

​We've all heard a lot about memory. There are some useful abstractions out there that help you bootstrap memory quickly and add it to agents, but at the end of the day, you may want to open the black box and tune things yourself. Without a deep understanding of all the options for memory and how these tools are architected, its hard to weight the tradeoffs outside of basic vibe checks.

​In this episode, we'll build a recipe for AI agents that explores a few different memory techniques and how you can build an open-box implementation that you can tune and customize over time.

​Pre-reading

​To prevent repeating the basics, we recommend you come in having already understanding some of the tooling we will be using:

• ​Discord

• ​Cursor (A vscode replacement)

• ​Programming languages

  • ​Application Logic: Python or Typescript or Go

  • ​Prompting: BAML (recommend video)

​Meet the Speaker 🧑‍💻

​​​Meet Vaibhav Gupta, one of the creators of BAML and YC alum. He spent 10 years in AI performance optimization at places like Google, Microsoft, and D. E. Shaw. He loves diving deep and chatting about anything related to Gen AI and Computer Vision! 

Meet Dex Horothy, founder at Human Layer - a YC company. He spent 10+ years building devops tools at Replicated, Sprout Social and JPL. DevOps junkie turned AI Engineer.