AI agents are writing code, investigating incidents, and changing how infrastructure teams work. For SREs, that brings new questions about reliability: when to trust an agent, how to catch its mistakes, and who owns the outcome.

Join leaders from Replit, NVIDIA, and Sequoia Capital for a panel on how agents are changing the work of running production. We’ll explore practical experience, emerging approaches, and the engineering judgment that remains essential as teams delegate more work to AI.

What we’ll discuss:

  • Agents on-call: Using agents to triage alerts, gather context, and investigate incidents—and recognizing when an investigation is heading in the wrong direction.

  • Infrastructure at a new pace: Adapting testing, code review, and deployment processes as agents increase the volume of code teams produce.

  • Keeping humans accountable: Preserving architectural understanding and ownership when agents handle more of the implementation.

  • The changing SRE role: How agent-driven workflows affect hiring, learning, and the skills reliability teams need next.

The panel

  • Bogomil Balkansky - Partner at Sequoia Capital

  • Vishakha Sadhwani - Sr. Solutions Architect at NVIDIA

  • Niall O’Higgins - Engineering Lead at Replit

  • Sylvain Kalache (Moderator) - Head of AI Labs at Rootly AI

Who Should Attend

  • SREs & DevOps Engineers: Teams managing distributed cloud scale, high availability, and multi-nines uptime.

  • MLOps & Platform Engineers: Engineers building inference pipelines, model serving platforms, and GPU orchestration layers.

  • Incident Commanders & Ops Leads: Leaders guiding Sev-1 response playbooks, runbooks, and on-call practices.

  • Technical Leaders (CTOs, VPs, Directors): Decision-makers balancing rapid AI deployment with platform stability and customer trust.

Agenda

  • Check-in & Networking: 5:30 p.m. - 6:30 p.m.

  • Fireside Chat: 6:40 p.m. - 7:20 p.m.

  • Audience Q&A: 7:20 p.m. - 7:35 p.m.

  • Networking & Social Hour: 7:35 p.m. - 8:30 p.m.

  • End: 8:30 p.m.

About Rootly AI

Rootly AI is the AI-native on-call and incident response platform that provides proactive support to help Site Reliability Engineers resolve incidents faster, improve system resilience, and streamline on-call operations. It’s your always-on SRE copilot that automates root cause analysis and identifies patterns that drive continuous improvement—trusted by hundreds of companies like LinkedIn, NVIDIA, Replit, Elastic, Canva, Clay, Tripadvisor, and Shell.