LLMOps Patterns for Robust Agentic Systems Development

Hosted by Aurimas Griciūnas

Fri, Jan 9, 2026

4:00 PM UTC (45 minutes)

Virtual (Zoom)

Free to join

256 students

Invite your network

Go deeper with a course

End-to-End AI Engineering Bootcamp
Aurimas Griciunas
View syllabus

What you'll learn

Design observable and debuggable agentic systems

Learn the importance and fundamentals of tracing, state management and decision logging patterns.

Make your agentic systems robust and stable

Learn the key failure modes of agentic systems and LLMOps patterns that help prevent costly disasters in production.

Build evaluation and cost controls into agents

Learn when evaluating agentic systems adds real value and when it is an unnecessary cost.

Why this topic matters

Agentic systems fail not because models are weak, but because they lack control, observability and constraints. This topic matters because production agents must be predictable, debuggable, and cost-aware. Understanding LLMOps patterns is what turns experimental agents into systems teams can safely deploy and operate.

You'll learn from

Aurimas Griciūnas

Founder & CEO @ SwirlAI | Former CPO @ Neptune.ai (acquired by OpenAI)

Aurimas Griciūnas is a recognized AI expert, LinkedIn Top Voice in AI, and the founder of SwirlAI. He previously served as Chief Product Officer at Neptune.ai where he worked closely with top ML teams to scale infrastructure, evaluation, and LLMOps practices across industries. With over a decade of experience at the intersection of data science, machine learning, and software engineering, Aurimas has led AI initiatives in both startups and enterprise environments. His mission is to bridge the gap between hype and reality by teaching engineers how to build systems that work in the real world. Students will benefit from his hands-on knowledge, technical depth, and product-first mindset - gained by solving actual engineering problems.

Sign up to join this lesson

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