Roundtable: Redefining Good Software in the Age of Agentic Coding

For most of our careers, “good software” has been defined under a very specific constraint:

writing and changing code was expensive.

In the last few years, and especially in the last six months with tools like Claude Code and Codex CLI, that constraint is breaking.

We suddenly live in a world where creating large amounts of new code is cheap and fast.

That means some of our old intuitions about “good” and “bad” code might not hold anymore. If code is abundant, then what is scarce now? What should we actually be optimizing for?

We’ll explore:

1. How should we redefine “good software” when code is easy but understanding might still be hard?
2. What are the new best practices in this world?
3. And what are the anti-patterns we’re already starting to see with agentic coding workflows?

Expect a fast, candid conversation about how engineering judgment needs to evolve as AI becomes a core contributor to software creation.

Host: Ben Segal, Senior Director of Engineering @ Swift Navigation

Ben leads the engineering team behind the Skylark Cloud GNSS Correction Service—a global, real-time platform enabling precise positioning for autonomous systems, mobile devices, and geospatial applications. He brings deep experience building and scaling cloud services, real-time data systems, and ML-powered platforms, and holds multiple patents in advanced positioning technologies. An entrepreneurial builder at the intersection of deep tech and software, Ben has guided multiple products from concept to launch.