Like It or Not, You're the CTO Now by Baruch Sadogursky, Developer Advocate @ Port.ai
Ever had your CTO appear at your desk and ask about the one decision you weren't sure of all month? How the hell did they know to ask about that? You're going to need that ability, because now you have developers reporting to you whether you want it or not - AI coding agents.You built a nice agentic workflow: your agents write the code and review each other's work. Next, you give them an architect, a tester and a team-lead and you can have a whole software factory running while you do something else, and you go "oh my god". And then you look at what it shipped and ask, "What is this crap?" Annoyingly, the AI reviewers approved all of it.In this talk Baruch is showing both how you build your software factory, and how you run it. What skills from the engineering leadership are directly applicable to AI context management and how can you gain the uncanny omni-presence ability of a true CTO to ask your agents the right questions at the right time?
Baruch Sadogursky is Head of Developer Relations at Port, where he helps engineering teams build an agentic SDLC and give their agents the right context. Previously, he spent years at JFrog convincing people that artifact repositories matter. He was right about that, too. Baruch is a Java Champion and co-author of "Liquid Software" and "DevOps Tools for Java Developers".
You can see everything (but it might cost you) by Hannah Rifkin, Customer Engineer @ MotherDuck
While curating high quality context is not a new idea, it has taken on increasing importance in the agentic era. Unsupervised agents can add unnecessary bloat to context layers, noticeably impacting response quality. In this conversation, we will talk through strategies to create a healthy context layer for your organization.
Full text on Luma
.