MasterClass Builds AI Teaching Agents to Broaden Tutoring Access

Mandar Bapaye, chief product officer of Yanka Industries Inc., which does business as MasterClass, said the company’s MasterClass Executive program uses a multi-agent system to plan each lesson around how a learner engages. The system watches for signs such as cognitive overload and fading motivation, then changes its approach, Bapaye said during an interview on SiliconANGLE Media’s theCUBE at the Fully Connected event.

Bapaye said personalization requires a pedagogical framework beneath the technology. “It’s not just you throw an agent, throw a chatbot in with a student and let them figure it out,” he said. “Having a very … scientifically and pedagogically backed backbone of your agentic system is of prime importance.”

Bapaye spoke with Lukas Biewald, senior vice president of AI initiatives at CoreWeave Inc., who has advised the MasterClass team on the product’s development. Biewald said multi-agent systems need rigorous evaluation and repeated testing. “Let’s try a new model, let’s try a new rubric, let’s see how it does, and let’s just keep doing it again and again and again and make it iteratively better every day,” he said.

The shift is also feeding CoreWeave’s full-stack AI cloud push as companies move AI agents out of the lab and into production. CoreWeave recently announced that MasterClass has selected W&B Weave to trace, monitor and improve its teaching agents, Bapaye said.

In production, MasterClass runs about 10 agents behind every learner interaction and tracks inputs, outputs, tool calls and communication between agents. Bapaye said observability becomes difficult at that stage because thousands of people are interacting with the system. “Now, what you need to figure out is, ‘Hey, we did all this good stuff during the eval period, but during production, how are the agents behaving? Are the experiences we are giving really good?’” he said.

MasterClass built its own agent on Weave’s Model Context Protocol interface. Each night, that agent reviews the traces and flags issues and likely root causes, Bapaye noted.

The first MasterClass Executive cohort drew 30,000 applications for about 500 spots, and the second is nearing 50,000 applications. Bapaye framed the opportunity around cost, supply and quality. “It’s extremely costly to hire personal teachers, they are in very short supply … and the quality of teachers varies,” he said. “AI solves pretty much all of these three aspects.”