Learn from the source, then go deeper.

Video lesson

Agentic SDLC at Uber: From Platform Building Blocks to a Managed Software Factory

A source-grounded lesson on Uber's six-layer agent platform and the end-to-end loop it supports: research, design, coding, early validation, CI, review, and maintenance. The central idea is that useful agentic engineering depends less on a lone coding model than on controlled access, relevant context, prepared execution environments, reusable skills, staged evidence, and feedback loops.

Video lesson

Understanding is the new bottleneck — Geoffrey Litt, Notion

Video lesson

Forward-Deployed Engineering: Platform, Outcomes, and Adoption

A source-grounded introduction to forward-deployed engineering as a model for delivering customer outcomes on a reusable technical platform.

Video lesson

Agent Harnesses: From General Loops to Evidence-Driven Custom Systems

A source-grounded lesson on how agent harnesses assemble context, run tools, specialize workflows, and use private evals plus observability to improve the model, context, or harness.

Video lesson

Why Agentic Systems Need Ontologies

A source-grounded lesson on pairing probabilistic LLM agents with formal ontologies, graph representations, and validators so flexible generation and action planning can be checked against domain-aware rules.

Video lesson

The Next Bottleneck: Scaling Forward-Deployed Engineering with AI

A source-grounded lesson on why customer-specific business understanding is the next bottleneck for AI deployment, and how forward-deployed engineering, specialized agents, and enterprise platforms can scale that work.

Video lesson

Closed-Loop Multimodal Evals: From Routing to Marketplace Feedback

A source-grounded lesson on building a production multimodal image-enhancement system with selective routing, bounded editing, layered QA, offline human alignment, online drift correction, and marketplace feedback.