Embrace Complexity with Insightful Management

1min Snip

00:00

Play full episode

Summary

Transcript

Episode notes

Effective management of complex systems requires proactive tools rather than reactive troubleshooting. By implementing a governance approach from day one, teams can quickly identify failures without sifting through numerous sources, significantly reducing downtime. Utilizing insights through user interface elements enables tracking of performance over time, capturing both failures and cost fluctuations, which simplifies operational oversight. Moreover, adopting a declarative strategy ensures that model deployment and versioning are handled systematically through code, leveraging version control systems like Git to streamline these processes.

LLMs are becoming more mature and accessible, and many teams are now integrating them into common business practices such as technical support bots, online real-time help, and other knowledge-base-related tasks. However, the high cost of maintaining AI teams and operating AI pipelines is becoming apparent.

Maxime Armstrong and Yuhan Luo are Software Engineers at Dagster, which is an open source platform for orchestrating data and AI pipelines. They join the show with Sean Falconer to talk about running cost-effective AI pipelines.

Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from information visualization to quantum computing. Currently, Sean is Head of Marketing and Developer Relations at Skyflow and host of the podcast Partially Redacted, a podcast about privacy and security engineering. You can connect with Sean on Twitter @seanfalconer.