AN

Speaker

Aleksandr Nikolenko

Infrastructure Engineer @ Perplexity

Serbia

I am an engineer at Perplexity working on core search architecture and long-running AI agent infrastructure. I specialize in building high-throughput systems, secure sandboxed execution environments, and stateful agent retrieval pipelines that allow LLM agents to program their own search workflows.

linkedin

At MDC 2026

Sessions

Presentationtba

Delegating Work to Agents: Goal, Verifier, Workspace

"How do you hand off a critical production migration to an AI agent and achieve a safer outcome than doing it by hand? In this talk, I will share a real-world case study: moving search architecture from a legacy Python service to a new path in under one month, deleting roughly 50,000 lines of old code, and reaching zero traffic on the old service without relying on users to discover regressions. Key Topics & Takeaways: - Defining a clear goal with a measurable pass condition instead of giving vague instructions. - Running continuous output verification against live traffic samples to catch ranking-order divergences and schema mismatches before code review. - Creating safe execution boundaries where agent-generated implementations can fail without production risk. - Where agent autonomy ends and human engineering authority remains essential."

← Back to all speakers