Zip ML Engineer Dexter Lee on LangGraph Adoption

Dexter Lee, Staff Machine Learning Engineer at Zip, explains the shift in his team's AI development workflow after adopting LangGraph and LangSmith. Previously, Zip relied on custom code for calling LLMs, managing pipelines, and storing results, which resulted in weeks-long feature additions and insufficient trace details.

According to the episode description, integrating LangGraph and LangSmith allowed the team to access node interaction and LLM call traces without additional coding. This change facilitated quicker adoption by other internal teams and enabled the establishment of an initial evaluation setup to prevent regressions.