Free Lesson

System Design for AI Agents, for Engineers (2026)

30 min
Jun 16, 2026 1:00 PM
Virtual (Zoom)

In this video

What you'll learn

Tell normal distributed systems from genuinely new

Spot which parts of an agent system are old problems you already solve and which break your assumptions.

Name the decisions that matter with an LLM in the path

Boundaries, state, failure modes, and evaluation: the calls that decide whether it works in production.

Reason about reliability and cost like a Staff engineer

Handle non-determinism, retries, latency, and token cost as first-class design constraints, not afterthoughts.

Why this topic matters

Every team is wiring an LLM into production, and most guidance is written for product managers, not the engineers who have to make it reliable. The result is senior engineers shipping agent systems on instinct. This session gives you the engineer's mental model: what's ordinary distributed-systems work, what genuinely breaks, and the few decisions that decide whether it survives real traffic.

You'll learn from

Ehsan Gazar

Ehsan Gazar

Principal Engineer, 500+ mentees, 16 years in production

See all products from Gaz