How to Build Self-Improving AI via Data-Driven Loops

Lightning Lessons

Practical skills & tools to accelerate your career

How to Build Self-Improving AI via Data-Driven Loops

Hosted by Jason Liu and Hamish Ogilvy

386 students

What you'll learn

Design Dynamic Query Planners

Students will learn to build flexible AI query planners that adapt execution strategies in real-time.

Create Composable Search Primitives

Students will understand how to develop modular search components that can be dynamically assembled by AI systems.

Implement Self-Learning Feedback Loops

Students will learn to connect search systems to data feedback for continuous improvement.

Why this topic matters

Understanding self-improving AI systems is crucial as they represent the future of software development. By mastering data-driven learning loops, you'll build systems that get better over time without manual intervention. This skill will differentiate you in the job market and prepare you for the next wave of AI innovation where adaptability trumps static solutions.

You'll learn from

Jason Liu

Consultant at the intersection of Information Retrieval and AI

Jason has built search and recommendation systems for the past 6 years. He has consulted and advised a dozens startups in the last year to improve their RAG systems. He is the creator of the Instructor Python library.

Hamish Ogilvy

VP of AI, Algolia

Hamish was a founder of search.io, a proprietary search engine and one of the first production scale vector + full text search engines handling billions of queries a month. Search.io was later acquired by Algolia where he is now the Vice President of AI. He has 10+ years experience designing and building search engines and distributed systems. Prior to this he specialised in data and analytics. He holds a PhD in Physics

Worked with