LangChain Podcast: Unify CTO on Self-Driving Style AI Eval Habits
Max Agency, LangChain's podcast, released an episode featuring Connor Heggie, Co-founder and CTO of Unify. Heggie discusses an evaluation habit he adopted from building vision models at a self-driving startup: watching real examples one by one as a team before trusting a model. This resource is relevant for technical professionals focused on LLM agent evaluation practices.
ImportanceLocalEvidenceE2 unreplicatedWrite-upQuick
Max Agency, a podcast under LangChain, published an interview on September 21, 2026, featuring Connor Heggie, Co-founder and Chief Technology Officer (CTO) of Unify.
According to the episode description, Heggie shares an evaluation method he brought from his previous work building vision models at a self-driving startup. The method emphasizes that team members should sit down and watch real case samples one by one before trusting the model's output.
The episode focuses on practical evaluation methods for Large Language Model (LLM) agents, specifically applying the habit of 'manual review of real examples' to building production agents.