Video

Voice AI may be sold as a model problem, but the real bottleneck is whether the system can survive real-time demands, stay reliable, and do it at a cost that makes sense.

Luis Velasco works as a Forward Deployed Engineer at OpenAI. For him, code is becoming very cheap to produce, while building the system around the model is becoming critical.

Dana Lawson leads R&D at Netlify, overseeing engineering, product, and design. From where she sits, she sees the real shift clearly: one person or a tiny team can now cover far more ground.

Everyone is busy asking how big the model is, but the real question is what you fed it first - because if your PDFs are mangled and your OCR is sloppy, even the smartest LLM starts from the wrong answer.

Mike Chambers, Developer Advocate at AWS, says the real test of AI is not whether a demo looks smart, but whether the system around it can survive real-world use.

The fastest way to create technical debt in AI is still the oldest one: choosing a database because it feels comfortable.

AI can write the code. The harder question is whether anyone still understands what it was supposed to do six months later.

Building software is full of ups and downs. Some days, you're working with the best team you can find, and others it's up to you to fix something with no idea how it works and no access to documentation.

We asked engineers how far AI can really go in software delivery, and their answer was simple: it can speed things up, but people still have to make the decisions.

As AI tools reshape how software is built, the engineers in our new video say the job is shifting from writing every line by hand to guiding, reviewing, and orchestrating what AI produces.

Developers share how they handle deadlines, pressure, and team communication - and why small white lies sometimes help engineering teams keep moving.

At Devoxx UK, I spoke with Trisha Gee - author and one of the most recognized voices in the Java space - about what really happens when teams lean heavily on AI. Her take was far darker than the conference hype.

Production incidents are a context problem. By the time an engineers understand what's happening, they've already bounced across several different tools - and the incident is still ongoing. PagerDuty thinks MCP is the fix.