← back

Developer Experience in the Age of AI Coding Agents – Max Kanat-Alexander, Capital One

22.5K views · Dec 23, 2025 · 18:19 min · Watch on YouTube ↗
Takeaway

Make your codebase, tooling, and documentation match how the rest of the industry works so agents inherit decades of training-set fluency.

Summary

  • Capital One's DX lead argues the 'no regrets' investments for the agent era are the same things that helped humans: standard toolchains, deterministic validation, structured codebases, and written-down context.
  • Stop fighting the training set — use industry-standard package managers, linters, and mainstream languages so agents aren't reasoning about your bespoke amalgamation.
  • Prefer CLIs/APIs over computer-use/browser orchestration where accuracy matters; agents are most accurate in their native text interface.
  • Tests on untestable codebases produce 'I pressed the button and it pressed successfully' theater — refactor for testability first.
  • Tribal knowledge and unwritten meeting decisions are agent-invisible; document why, not what.
developer-experiencecoding-agentsenterprise
Original description
It feels like every two weeks, the world of software engineering is being turned on its head. Are there any principles we can rely on that will continue to hold true, and that can help us prepare for the future, no matter what happens? Max uses research, data, and his 20+ years working in enterprise Developer Experience teams to talk through what we can do now that will prepare us for an agentic future, no matter what that future holds.

Speaker: Max Kanat-Alexander  |  Executive Distinguished Engineer, Capital One
https://x.com/mkanat
https://www.linkedin.com/in/mkanat/
https://max.kanat.us/


Timestamps

00:00 The "New Hotness" Fatigue & Unpredictability 
01:58 The "No Regrets" Investment Framework
02:55 Input 1: Standardized Development Environments 
04:40 Input 2: Native CLIs and APIs for Agents 
05:08 Input 3: Deterministic Validation & Actionable Errors 
06:45 Input 4: Structure of Systems & Legacy Code 
14:35 The Necessity of Apprenticeship in Code Review 
15:00 The Vicious Cycle: Bad Codebases Break Agents 
15:54 The Virtuous Cycle: Better DevEx Accelerates Agents 
16:30 Summary Checklist & Conclusion