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...
The Domino Effect of Outages with Nuno Tomás, Founder of isDown.app
Humans of Reliability
34 minutes
9 months ago
The Domino Effect of Outages with Nuno Tomás, Founder of isDown.app
🎙️ Humans of Reliability: Keeping systems up and the lights on isn’t just about technology—it’s about the people behind it. In this episode, we’re thrilled to chat with Nuno Tomás, founder of IsDown.app, a vendor outage monitoring tool transforming how teams handle third-party incidents. Nuno shares his journey from software engineer to entrepreneur, the pivotal 4 a.m. moment that inspired Isdown, and the challenges of balancing startup life with family. We dive into the complexities of incid...
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...
