Background Agents for Genomics and Cloud Ops

on YouTube ↗23m

" summary

Genomics platform runs at exabyte scale on AWS and uses background agents to triage runs, write incident reports, and merge safe code changes into main after unit, integration, canary tests. Agents cut troubleshooting from hours or days to minutes, complete about 122 tickets out of 189 per sprint, and generate daily ops summaries and incident postmortems. Session logs feed nightly reflection so self‑evolving skills improve tool‑call efficiency, and measured drops in tool calls per session show real gains.

AI-written summary · about

" chapters (6)

1. 0:00Background agents for genomics platforms
2. 3:21Choose the right environment, then start small
3. 6:01When cloud-scale genomics jobs fail
4. 8:46Incident reports and operational agents
5. 12:01Letting the bot merge into main
6. 15:01Self-evolving skills and the specificity paradox

" related talks

• 19mAgents in Action: How Google is Automating Operational ToilMaria-Hendrike Peetz · DevOpsDays Zurich 2026
• 19mBuilding Agents at Cloud ScaleAntje Barth · AI Engineer World's Fair 2025
• 21mAgentic Monitoring in ProductionSujith N S, Leonel Candido da Silva · Agent Conf 2026
• 05h 56mFrom the main stage to the terminalAja Hammerly, Addy Osmani, Jason Davenport, Omar Sanseviero, Logan Kilpatrick, Philip Kiely, Katie Nguyen, Stephanie Wong, Jay Rodge, Dave Elliott, Ben Gilbert, David Rosenthal, Shubham Saboo, Yasmeen Ahmad, Khulan Davaajav, Tomek Porozynski, Muhammad Farooq, Sam Witteveen · Google Cloud Next '26
• 14mImproving Cloud Reliability at Scale Using Gen AIChetan Bansal · Reliability @Scale 2024
• 29mBuild and scale reliable multi-agent systems on AWSMelanie Li, James Luo · AWS Summit Sydney 2025
• 17mTransforming Robotics Service with Agentic AI onPatrick Domcke, Stefan Hudelmaier · Hannover Messe 2026
• 07mCloud architecture for population-scale analyses of genomes and AI.Paweł Sztromwasser · DevOpsDays Poznań 2021