.png&w=1536&q=75)
Free Lesson
Stay Ahead in AI: Evaluate Any New LLM in 15 Minutes
Part of The AI Evaluation Handbook
30 min
Oct 14, 2025 5:00 PM
Virtual (Zoom)
In this video
What you'll learn
Spot signals that actually matter, fast
I'll teach you reliable, structured methods for testing and evaluating new LLMs the day they come out.
Decide fit fast: SOTA, niche, or avoid
We'll talk about how to map models to your toolkit so you don't skip out on task-specific strengths and weaknesses.
The flaws with benchmarks and OPO (other people's opinions)
You might go... why does this guy hate benchmarks so much? By the end of this session, you will, too!
Why this topic matters
New AI models are launching weekly. Most people look to outdated benchmarks or biased influencers to try to evaluate what tools and LLMs to use. But we should all be building an instinctual understanding of how to judge these tools and models ourselves. And it's not as hard as it might sound. You'll learn how to form your own evidence-based perspective that you can trust.
You'll learn from
Sherveen Mashayekhi
Founder & CEO @ Free Agency, AI Product Leader & Investor
Clients hired at companies like...
