Uploaded June 2026 | Updated November 2026, 1 day ago
How do you make sure everyone on your AI team is actually looking at what the models are doing in production? At Benchling, they've built it into the rhythm of how the team operates.
Nicholas Larus-Stone walks through three distinct patterns: a weekly "fire chief" rotation responsible for surfacing traces at the all-hands tech operations meeting, a thumbs-up/thumbs-down feedback loop from users that flags traces worth investigating, and feature-level trace review that engineers and PMs do after every launch or beta. It's a concrete playbook for anyone trying to build real observability culture — not just tooling — into an AI team.
This clip is from Max Agency, a podcast about how the best AI agents are actually being built. Hosted by Harrison Chase, CEO of LangChain, each episode goes deep with the builders designing, deploying, and learning from real agent systems in the wild. From architecture decisions to evals, tooling, and failure modes, Max Agency is for people who want to understand what it really takes to build useful agents.
#aiagents #observability #langchain
How do you make sure everyone on your AI team is actually looking at what the models are doing in production? At Benchling, they've built it into the rhythm of how the team operates.
Nicholas Larus-Stone walks through three distinct patterns: a weekly "fire chief" rotation responsible for surfacing traces at the all-hands tech operations meeting, a thumbs-up/thumbs-down feedback loop from users that flags traces worth investigating, and feature-level trace review that engineers and PMs do after every launch or beta. It's a concrete playbook for anyone trying to build real observability culture — not just tooling — into an AI team.
This clip is from Max Agency, a podcast about how the best AI agents are actually being built. Hosted by Harrison Chase, CEO of LangChain, each episode goes deep with the builders designing, deploying, and learning from real agent systems in the wild. From architecture decisions to evals, tooling, and failure modes, Max Agency is for people who want to understand what it really takes to build useful agents.
#aiagents #observability #langchain










