Coding Agents Lunch & Learn Session 9 : End-to-End MLOps with Autonomous Agents

In this session, we’ll explore how coding agents can orchestrate a full MLOps pipeline, from data ingestion to deployed models, without manual intervention.

Leo Walker will walk us through a real project built at the Stanford “LLM x Law” Hackathon, where agents were used to:

1. Pull and process data from external APIs
2. Use LLMs for parsing and data cleaning
3. Train classification and regression models
4. Deploy model weights to Hugging Face
5. Expose models via MCP servers for agent-to-agent interaction

We’ll discuss how this approach shifts workflows from manual pipelines to coordinated agent systems, and what that means for the future of MLOps and applied AI.

This session is ideal for anyone interested in:

1. AI agents in production workflows
2. Automating ML pipelines
3. Practical applications of LLMs beyond prompting