Scott & Mark Learn To...Vibe Coding, for Real (Again)

Scott & Mark Learn To...Vibe Coding, for Real (Again)

From Scott & Mark Learn To... by Microsoft

March 25, 2026 · 25 min · Season 1 · Episode 34

About this episode

Scott and Mark discuss the impact of AI coding agents on software development and the challenges faced in engineering.

In this episode,  Scott Hanselman  and  Mark Russinovich  dive into the realities of building complex software with AI coding agents. Mark shares his experience using modern models to implement a shared-memory transport for gRPC across Go and .NET, explaining how AI dramatically accelerated development while still requiring constant oversight. They discuss the surprising strengths and limitations of AI coding tools, to the massive productivity gains that make the frustration worthwhile. The conversation also explores the challenges of solving hard engineering problems, including an attempt to build a scrolling screenshot stitcher, and wraps with thoughts on the future of developer tooling and a potential live episode of the show.      Takeaways:      AI coding agents can speed up complex development but still require human oversight  Developers often need to guide and correct the model throughout the process  Even with challenges, AI can reduce months of work to days      Who are they?       View Scott Hanselman on LinkedIn    View Mark Russinovich on…

People in this episode

Hosts: Scott Hanselman, Mark Russinovich

Topics covered

  • AI coding agents
  • software development
  • gRPC
  • developer tooling
  • engineering challenges

Keywords

  • AI coding
  • software development
  • gRPC
  • Go
  • .NET
  • developer tools
  • engineering problems

Mentioned in this episode

Organizations: Microsoft

Products: gRPC, Go, .NET

More episodes of Scott & Mark Learn To...

Explore listener stats, chart rankings, contacts and more on the Scott & Mark Learn To... podcast page.