Loading video...

Video Failed to Load

Go Home

AI observability platforms raised $1B+ to reinvent print debugging for the agent era. Reading traces manually is not a scalable production workflow. We think the stack should catch issues itself. Meet Respan.

1,350,804 views • 1 month ago •via X (Twitter)

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Why is observability so hard to do well - and so expensive, in general? What is "Observability 2.0" and is Open Telemetry any good? In today's episode of The Pragmatic Engineer Podcast, we answer all of these with Charity Majors , co-author of the O'Reilly book "Observability Engineering," former engineer at Parse/Facebook, and cofounder and CTO at Honeycomb Watch it here: • YouTube: • Apple: • Spotify: • Summary and transcript: Brought to you by our wonderful sponsors - check out their offerings: • Sonar — Trust your developers – verify your AI-generated code. • Vanta — Automate compliance and simplify security with Vanta ---- Topics we cover in this episode: • What is observability? Charity’s take • What is “Observability 2.0?” • Why Charity is a fan of platform teams • Why DevOps is an overloaded term: and probably no longer relevant • What is cardinality? And why does it impact the cost of observability so much? • How OpenTelemetry solves for vendor lock-in • Why Honeycomb wrote its own database • Why having good observability should be a prerequisite to adding AI code or using AI agents • And more! --- My biggest takeaways: 1. The DevOps movement feels like it’s in its final days, having served its purpose. 2. Lots of people get dashboards wrong! Charity doesn’t think that static dashboards are helpful to engineering teams at all. In fact, misusing dashboards is one of the most common observability practices. 3. Observability will be especially important for AI use cases in these ways: a) o11y for LLMs: to get data on how they behave and to be able to debug behaviors. This is relevant for teams building and operating AI models. b) o11y for code generated by AI: the generated code should have the right amount of observability in place. Once the code is deployed to production, developers need to be able to get a sense of how the code is behaving there!

Gergely Orosz

25,485 views • 1 year ago