L01 Brief: Course intro + the AI coding landscape
EECS AASE Podcast, season 1, episode 1

Transcript of the published audio. The episode is AI-generated from
course materials; this transcript is produced locally from the audio.

This is the brief on Tuesday's opening lecture for EECS 498. This Tuesday,
September 1st, 2026, kicks off a 15-week journey into applied-agentic
software engineering, exploring what software development really looks like
when an AI agent is actually doing the typing for you. So it begs a huge
question. If an AI is writing the code, what exactly are you, the human
engineer, actually responsible for?

Well, first it's all about the mindset shift to becoming a code curator.
While the actual code production gets handed over to AI, judging that code
remains your fundamental responsibility. You can kind of think of yourself
like a managing editor or even a museum curator. You're not mass-producing
the content anymore. You're applying expert judgment to decide exactly what
makes the final cut.

Second, we'll get into the mechanics of a brand new skill, which means
mastering the big three, context, model, and prompt. And let's just push
back on a huge misconception right here. This is absolutely not just some
glorified spellchecker or a simple autocomplete feature. It's a highly
complex, distinct discipline.

Finally, we'll dive into the setup and your foundational habit for the whole
semester. Treating the AI model as literally just a line of configuration
rather than a locked-in vendor. It's super empowering because if a model
isn't working out, you aren't stuck at all. You just swap out the
configuration and keep right on building.

Tuesday's lecture will completely redefine your job from typing code to
directing agents, setting the stage for the next 15 weeks of building,
breaking, and growing them.