Ortec Transistor (https://transistor.fm) https://feeds.transistor.fm/ortec Ortec podcast © 2026 Ortec aee623e9-eb8c-56ae-8387-b147fc43ded2 yes en Mon, 14 Sep 2026 07:48:10 -0700 Mon, 14 Sep 2026 07:48:24 -0700 Ortec episodic Ortec Ortec podcast Ortec podcast. Ortec No No Building a whole feature with AI - Thomas 2 2 Building a whole feature with AI - Thomas full 56c1b12c-9589-471c-87e7-3c0d8abad5da https://share.transistor.fm/s/c5979434 Thomas is a frontend developer at ORTEC, and together with his colleague Jacques, he wanted to try something out: could agentic AI actually build a full feature?  

 

In this episode, Thomas talks openly about how that experiment went, including the attempts that did not quite land the way they hoped, and what he and Jacques changed along the way to finally get it right. It is a grounded, practical story about what it really takes to work with agentic AI on something real, less about a big leap of faith and more about learning to be precise. 

]]> Thomas is a frontend developer at ORTEC, and together with his colleague Jacques, he wanted to try something out: could agentic AI actually build a full feature?  

 

In this episode, Thomas talks openly about how that experiment went, including the attempts that did not quite land the way they hoped, and what he and Jacques changed along the way to finally get it right. It is a grounded, practical story about what it really takes to work with agentic AI on something real, less about a big leap of faith and more about learning to be precise. 

]]> Wed, 09 Sep 2026 05:56:30 -0700 Ortec Ortec 435 Thomas is a frontend developer at ORTEC, and together with his colleague Jacques, he wanted to try something out: could agentic AI actually build a full feature?  

 

In this episode, Thomas talks openly about how that experiment went, including the attempts that did not quite land the way they hoped, and what he and Jacques changed along the way to finally get it right. It is a grounded, practical story about what it really takes to work with agentic AI on something real, less about a big leap of faith and more about learning to be precise. 

]]> No How far can you trust an agent? - Cynthia 2 2 How far can you trust an agent? - Cynthia full 82d8143d-33b9-4450-8f45-2127cb143321 https://share.transistor.fm/s/a08e0caa "Please fix the review comments." When Cynthia received this pull request for the third time, she realized something was off, not with the code, but with the way she was working. 

 

Cynthia is Senior AI Engineer at ORTEC and leads the team behind Art, ORTEC's AI assistant. A recent move to GitHub pushed her team's use of coding agents further than they expected, and that one frustrating pull request turned into a much bigger question about how far you can actually trust an agent to work on its own. 

 

In this episode, Cynthia shares what her team built to answer that question, and how it changed the way she thinks about her own job. 

]]> "Please fix the review comments." When Cynthia received this pull request for the third time, she realized something was off, not with the code, but with the way she was working. 

 

Cynthia is Senior AI Engineer at ORTEC and leads the team behind Art, ORTEC's AI assistant. A recent move to GitHub pushed her team's use of coding agents further than they expected, and that one frustrating pull request turned into a much bigger question about how far you can actually trust an agent to work on its own. 

 

In this episode, Cynthia shares what her team built to answer that question, and how it changed the way she thinks about her own job. 

]]> Wed, 09 Sep 2026 05:56:15 -0700 Ortec Ortec 461 "Please fix the review comments." When Cynthia received this pull request for the third time, she realized something was off, not with the code, but with the way she was working. 

 

Cynthia is Senior AI Engineer at ORTEC and leads the team behind Art, ORTEC's AI assistant. A recent move to GitHub pushed her team's use of coding agents further than they expected, and that one frustrating pull request turned into a much bigger question about how far you can actually trust an agent to work on its own. 

 

In this episode, Cynthia shares what her team built to answer that question, and how it changed the way she thinks about her own job. 

]]> No The investigation skill - Aleksandr 1 1 The investigation skill - Aleksandr full fe23774e-cbf1-4d34-bfb9-39b907f0804f https://share.transistor.fm/s/d47c44fd Anyone who's ever been on call knows the drill: something breaks, an alert fires, and before you can even think about fixing it, you first have to figure out what actually happened. That detective work, digging through logs, dashboards, deployment history, can eat up more time than the fix itself. Aleksandr, a backend engineer on the Home Delivery team, got tired of doing that same investigation dance over and over. So, he decided to see if agentic AI could help, not by fixing incidents, but by helping him investigate them. 

 

In this episode, Aleksandr walks us through what happened when he pointed agentic AI at real production alerts, and what he ran into along the way that changed how he worked with it entirely. 

]]> Anyone who's ever been on call knows the drill: something breaks, an alert fires, and before you can even think about fixing it, you first have to figure out what actually happened. That detective work, digging through logs, dashboards, deployment history, can eat up more time than the fix itself. Aleksandr, a backend engineer on the Home Delivery team, got tired of doing that same investigation dance over and over. So, he decided to see if agentic AI could help, not by fixing incidents, but by helping him investigate them. 

 

In this episode, Aleksandr walks us through what happened when he pointed agentic AI at real production alerts, and what he ran into along the way that changed how he worked with it entirely. 

]]> Wed, 09 Sep 2026 05:55:57 -0700 Ortec Ortec 376 Anyone who's ever been on call knows the drill: something breaks, an alert fires, and before you can even think about fixing it, you first have to figure out what actually happened. That detective work, digging through logs, dashboards, deployment history, can eat up more time than the fix itself. Aleksandr, a backend engineer on the Home Delivery team, got tired of doing that same investigation dance over and over. So, he decided to see if agentic AI could help, not by fixing incidents, but by helping him investigate them. 

 

In this episode, Aleksandr walks us through what happened when he pointed agentic AI at real production alerts, and what he ran into along the way that changed how he worked with it entirely. 

]]> No