
We've moved all updates for this account to our main account: @QCon. Follow us there for all QCon San Francisco news, speaker announcements and conference updates!

Uncover emerging trends and practices from the world’s most innovative software professionals to help you validate your software roadmap. Celebrating 17 years.

We've moved all updates for this account to our main account: @QCon. Follow us there for all QCon San Francisco news, speaker announcements and conference updates!

Sarah Deitke is speaking at QCon San Francisco, Nov 16-18. #QConSF #APIDesign

The pattern is deliberate: managed code at the API layer, user code on the client, and no app touching secrets. Connectors share one consistent /api/... contract designed for agents to read and call.

350 Duolingo employees have used BuildingHub to create internal tools, with 800+ agent-built apps and no new backend for each one: buff.ly/fuSprXc

Nancy is speaking at QCon San Francisco, Nov 16-18. #QConSF #DistributedSystems

Separating the phases can deliver up to 5x higher throughput, but each request now spans heterogeneous hardware. Routing, scheduling, interconnects, and failure handling become distributed systems problems.

Prefill is compute-intensive. Decode is memory-bound. At Cerebras, Nancy Zheng's team built a production disaggregated inference platform to run them separately: buff.ly/ZXFGhJt

Vanessa is speaking at QCon San Francisco, Nov 16-18. #SiteReliability #IncidentManagement

Models change. Agents get new tools and permissions. Prompts change. The question is what incident-learning practices still hold up, and what needs to change with them.

By the time you've investigated an AI incident, the system may already have changed. Vanessa Huerta Granda, Resilience Engineering Manager @Enova, on Learning From Incidents when systems do not stand still: buff.ly/Ham8G0W

Sanjay is speaking at QCon San Francisco, Nov 16-18. #SoftwareReliability #QConSF

Deploy → Observe → Operate → Incident → Diagnose → Mitigate → Learn → Improve. The session follows the full lifecycle and asks which responsibilities belong in the platform versus the application.

Writing code is getting easier. Operating what gets shipped is not. Sanjay Singh, Staff Software Engineer @LinkedIn, on who owns production when AI increases software change volume: buff.ly/uCcKatw

Dan is speaking at QCon San Francisco, Nov 16-18. #AIEngineering #SoftwareArchitecture

One use case processes 150,000 research documents a week across 10,000 companies. Another has enabled domain experts to build 1,000+ dashboards and applications.

How do you standardize an AI platform enough to scale safely without centralizing every workflow? Dan Wolf of BlackRock on the architecture behind AIROS: buff.ly/1AjOkgE