Welcome to the Pieces AI productivity podcast, where we dig into how experts use AI to be more productive, as well as geeking out in general on different AI topics.
đ In this episode, Jim is joined by Phillip Carter, Principal PM at Honeycomb and observability geek. Phillip talks about observability, and how much of an impact bad observability can have on teams. Jim and Phillip then talk about how AI can try to help with adding observability, and how that really a lot of the time the problems are best solved by humans - as they understand the constraints of systems better than an AI can. For example, can an AI developer tool add the right logging, but if it does will it add too much and cost a fortune on your observability platform side? All this and more in this episode.
đ Links:
Connect with Phillip on LinkedIn
đ Try Pieces for free: â â https://pieces.appâ â
đĄ Learn more about Pieces features: â â https://pieces.app/featuresâ â
ï»ż
Connect with Pieces:
X: â â https://x.com/getpiecesâ â
Bluesky: â â https://bsky.app/profile/getpieces.bsky.socialâ â
LinkedIn: â â https://www.linkedin.com/company/getpieces/â â
Instagram: â â https://www.instagram.com/getpieces/â â
Discord: â â https://pieces.app/discordâ â
In this episode:
0:00:00 - Intro
0:03:38 - Phillips initial thoughts in AI in coding from 2022
0:04:44 - Can I help spot patterns in observability data
0:13:12 - A future where AI can preemptively find incidents
0:19:35 - How can AI developer tools help add observability to your code?
0:23:51 - AI is great for adding decent logging and metrics to legacy apps
0:26:43 - AI doesnât understand your business context and constraints like cost
0:28:22 - AI developer tools lack context of decisions in collaboration tools (unlike Pieces!)
0:31:35 - Could AI agents ensure observability is included in your code?
0:32:46 - Humans are more important than AI
0:37:42 - Adding code to Honeycomb that AI would fail to do right
0:42:34 - AI cannot replace junior engineers because where would senior engineers come from?
