Lightning Lessons

Making Sense of Millions of Conversations for AI Agents

Hosted by Hugo Bowne-Anderson, PhD and Ivan Leo

Tue, Oct 21, 2025

12:30 AM UTC (30 minutes)

Virtual (Zoom)

Free to join

53 students

Invite your network

Go deeper with a course

Building LLM Applications for Data Scientists and Software Engineers
Hugo Bowne-Anderson and Stefan Krawczyk
View syllabus

What you'll learn

Summarise LLM & Agentic conversation data at scale

Compress millions of interactions without losing critical meaning.

Embed and cluster conversations

Identify recurring failure themes and unmet needs.

Separate capability gaps from data gaps

Target fixes that actually improve satisfaction and retention.

Build classifiers and feedback loops

Turn clusters into monitoring systems for continuous improvement.

Tie insights to business KPIs

Link issues directly to metrics like cost, revenue, and churn.

Why this topic matters

AI agents often look healthy in dashboards (200 OKs, valid schemas) yet still fail silently. At the scale of millions of conversations, no team can manually review logs to find what matters. This lesson, drawing on Kura’s pipeline of summarisation, embedding, and clustering, shows how to transform overwhelming data into product signal that drives reliable, measurable improvements.

You'll learn from

Hugo Bowne-Anderson, PhD

AI & data engineer, consultant, educator of 3+ million students (ex-Yale)

Hugo Bowne-Anderson is an independent data and AI consultant with extensive experience in the tech industry. He is the host of the industry Vanishing Gradients, where he explores cutting-edge developments in data science and artificial intelligence. As a data scientist, educator, evangelist, content marketer, and strategist, Hugo has worked with leading companies in the field. His past roles include Head of Developer Relations at Outerbounds, a company committed to building infrastructure for machine learning applications, and positions at Coiled and DataCamp, where he focused on scaling data science and online education respectively. Hugo's teaching experience spans from institutions like Yale University and Cold Spring Harbor Laboratory to conferences such as SciPy, PyCon, and ODSC. He has also worked with organizations like Data Carpentry to promote data literacy. His impact on data science education is significant, having developed over 30 courses on the DataCamp platform that have reached more than 3 million learners worldwide. Hugo also created and hosted the popular weekly data industry podcast DataFramed for two years. Committed to democratizing data skills and access to data science tools, Hugo advocates for open source software both for individuals and enterprises.

Ivan Leo

AI engineer at Manus building the future of agents.

Ivan Leo is an AI engineer at Manus, building the future of agents. Previously at 567 Labs, he explored how large language models think and how to optimize their real-world performance through rigorous experimentation and engineering. He is also one of the lead maintainers of Instructor, an open-source library with millions of downloads that helps developers get structured outputs from LLMs. Ivan’s background spans full-stack engineering at Credit Suisse and collaborations with teams at HubSpot, Raycast, and OpenAI. Based in Singapore, he’s part of a new generation of engineers turning research breakthroughs into reliable, production-grade AI systems.

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.