Make Your Agents Trustworthy: Evals for the Super IC

Hosted by Aurimas Griciūnas

Thu, May 28, 2026

3:00 PM UTC (45 minutes)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Featured in Lenny’s List
End-to-End AI Engineering Bootcamp
Aurimas Griciunas
View syllabus

What you'll learn

Spot the failure modes your agents will hit in production

Learn which silent failures break IC agent workflows: hallucinated sources, dropped steps, drifted intent.

Catch a real agent failure and fix it live with evals

See one specific failure picked from a working multi-agent system, written into an eval, and resolved end to end.

Build evals into your agent iteration loop

Keep your agent crew compounding output instead of drifting silently as you ship changes.

Why this topic matters

Super ICs compound output by deploying agents that work when no one is watching. The problem is agents fail silently. They hallucinate, drop steps, and drift. Without evals, you stop noticing until the leverage is already gone. This lesson shows how to spot real agent failure modes, write targeted evals that catch them, and turn an unsupervised agent crew into reliable leverage.

You'll learn from

Aurimas Griciūnas

Example: VP at Top Company (ex-Role at Previous Company)

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.

See all products from SwirlAI

Sign up to join this lesson

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