Only 50% of companies monitor their ML systems. Building observability for AI is not simple: it goes beyond 200 OK pings. In this episode, Sylvain Kalache sits down with Conor Brondsdon (Galileo) to unpack why observability, monitoring, and human feedback are the missing links to make large language model (LLM) reliable in production. Conor dives into the shift from traditional test-driven development to evaluation-driven development, where metrics like context adherence, completeness, and ac...
All content for Humans of Reliability is the property of Rootly and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
Only 50% of companies monitor their ML systems. Building observability for AI is not simple: it goes beyond 200 OK pings. In this episode, Sylvain Kalache sits down with Conor Brondsdon (Galileo) to unpack why observability, monitoring, and human feedback are the missing links to make large language model (LLM) reliable in production. Conor dives into the shift from traditional test-driven development to evaluation-driven development, where metrics like context adherence, completeness, and ac...
Command Under Pressure: David Owczarek on Incident Leadership and Human-Centered Reliability
Humans of Reliability
23 minutes
4 months ago
Command Under Pressure: David Owczarek on Incident Leadership and Human-Centered Reliability
Incident response is as much about people as it is about systems. In this episode, David Owczarek, a veteran engineer leader and seasoned incident commander, joins Silvan Kalache to unpack the human dynamics behind effective reliability leadership. Drawing on experiences across startups and global enterprises, David shares what really matters when everything breaks, including: – How incident response strategies shift between small companies and large enterprises – Why not every engineer shoul...
Humans of Reliability
Only 50% of companies monitor their ML systems. Building observability for AI is not simple: it goes beyond 200 OK pings. In this episode, Sylvain Kalache sits down with Conor Brondsdon (Galileo) to unpack why observability, monitoring, and human feedback are the missing links to make large language model (LLM) reliable in production. Conor dives into the shift from traditional test-driven development to evaluation-driven development, where metrics like context adherence, completeness, and ac...
