How to do Observability right?
Hosted by Abi Aryan
Tue, Mar 24, 2026
5:00 PM UTC (1 hour)
Virtual (Zoom)
Free to join
Go deeper with a course
AI Systems Design & Inference Engineering
Abi Aryan
Founder and Research Engineering Lead @ Abide AI
Tue, Mar 24, 2026
5:00 PM UTC (1 hour)
Virtual (Zoom)
Free to join
86 students
Go deeper with a course
AI Systems Design & Inference Engineering
Abi Aryan
Founder and Research Engineering Lead @ Abide AI
What you'll learn
Single tool for ML Engineers and Biz teams?
A hands-on lab on observability for an agentic application and I'll show you how to use one OS tooling for all your team
What's the difference between observability and evals
Far too many people think evals is all they need and no one taught them about what metrics to track for agentic pipeline
Open source tools, not fancy libraries
Most people spend time confused between libraries (Langfuse, Logfire etc) instead of tracing what metrics they need
Why this topic matters
Observability for agents has been changing quitely in the past one year. The state of the art is no longer just model evals, but end-to-end visibility in why your agentic pipelines fail and where. Which tool did it call? Why? In this session, we will see how to do it right.
You'll learn from
Abi Aryan
ML Engineer with 10 years of experience in this field
Abi Aryan is the founder and lead research engineer at Abide AI, a deep tech company developing neurosymbolic models for reasoning in agents. With a decade of experience as an ML engineer building production-scale AI systems, she is also the author of two books:
- LLMOps (O'Reilly Publications)
- GPU Engineering for AI Systems (upcoming title from Packt Publishing, releasing Autumn 2026)
