RAG in the age of agents. SWE-Bench as a case study.

Lightning Lessons

Practical skills & tools to accelerate your career

Building AI-Native Products

RAG in the age of agents. SWE-Bench as a case study.

Hosted by Jason Liu and Colin Flaherty

Wed, Jun 25, 2025

5:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Learn directly from undefined

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

Invite your network

Go deeper with a course

Systematically Improving RAG Applications

Jason Liu

View syllabus

Wed, Jun 25, 2025

5:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Systematically Improving RAG Applications

Jason Liu

View syllabus

What you'll learn

Agent-Augmented RAG for Code Tasks

Students will learn how retrieval-agent systems achieve top performance on software engineering benchmarks.

Multi-Stage Reasoning in Code Agents

Students will explore how staged task decomposition improves agent performance on complex programming tasks.

Open-Source Agent Implementation Techniques

Students will gain insights into building effective code agents from analyzing top SWE-Bench solutions.

Why this topic matters

Understanding agent-augmented RAG transforms how developers solve complex code tasks. As AI coding assistants become essential tools, mastering these techniques gives you a competitive edge in building more powerful systems. This knowledge directly applies to creating better software solutions and advancing your career in AI engineering.

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.

Colin Flaherty

Working on something new

I was previously a founding member of technical staff at Augment Code, a leading AI coding company building everything from completion models to agents, all with deep awareness of your company's codebase and knowledge graph. We raised at a ~$1B valuation in early 2024. Prior to this, I was a researcher at Facebook AI Research, where I studied AI reasoning in the context of board games. I co-authored a paper in Science where we built an AI that reached human-level in the strategy game Diplomacy.

worked with