How to Find the Agent Failures Your Evals Miss with Scott Clark - #767
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)Show Notes
In this episode, Scott Clark, co-founder and CEO of Distributional, joins us to explore how teams can reliably operate and improve complex LLM systems and agents in production. Scott introduces a Maslow’s hierarchy of observability: telemetry for logging, monitoring for known signals, and post-production or online analytics to surface unknown unknowns. We dig into examples of real-world failures Scott’s team has seen in production systems, such as “lazy” tool-use hallucinations that standard evals miss, and how mapping traces into vector fingerprints enables clustering and topic discovery to uncover emergent behaviors. Scott explains how analytics can feed the data flywheel by generating evals, guardrails, and training data, and why online, adaptive approaches are essential for non-stationary models. We also touch on practical how-to’s such as instrumentation with OpenTelemetry, the GenAI semantic conventions, and the role of dedicated analytics tools.
The complete show notes for this episode can be found at https://twimlai.com/go/767.
More from The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
AI agents need the institutional knowledge experienced employees rely on: why a system works a certain way, which policies apply, and what never made it into the documentation. Capturing that knowledge is hard. Keeping it useful as people and agents add more may be harder.
In this episode, Zoe Weil, co-founder and CEO of Sequen, joins us to discuss how ranking systems can use live behavioral signals to optimize for purchases rather than clicks or search relevance alone. Zoe explains why approaches developed at data-rich social platforms don’t necessarily translate to retailers and how Sequen uses scroll speed, hover duration, and other in-session interactions to infer shopper intent without relying on user identity.
In this episode, Diogo Almeida, co-founder and CEO of TypeSafe, joins us to discuss Jev, TypeSafe’s recently released model for bringing fast, reliable intelligence directly into software. We explore the idea of “machine-native intelligence” and why Diogo believes models optimized for generating text are poorly suited to many of the decisions required for real-world automation. He explains how Jev differs from traditional classifiers and LLM-based approaches, the role of reinforcement learning from calibrated decisions (RLCD), and why calibration and reliability are central to making AI useful as a software primitive. We also discuss the relationship between models and code, why Diogo believes AI systems should become more engineered rather than relying on a single model to do everything, and how Jev-like models could reshape agents, tool use, and the architecture of AI-powered software.
AI systems have gone from struggling with grade-school math to helping solve research problems that have resisted mathematicians for decades, including Navier-Stokes.
Voice AI has gotten remarkably good, but natural conversation remains a high bar. Small delays, awkward interruptions, or the wrong tone can quickly break the illusion—and adding vision and visual presence only raises the stakes.