← back
Mentoring the Machine — Eric Hou, Augment Code
Original: Mentoring the Machine — Eric Hou, Augment Code
Takeaway
Engineers should treat coding agents like mentees — invest in teaching them the codebase so they absorb the firefighting that destroys deep work.
Summary
- Eric Hou (Augment Code, ex-automotive standards engineer) frames the talk around a typical 'derailed Tuesday' for senior engineers: blocked design work, staging emergency, junior mentoring request.
- Cites industry stats: each interruption costs ~23 minutes recovery and engineers spend ~23% of time maintaining code, totaling ~$300B/year in context-switching cost.
- Pitches the Augment Extension as treating the AI agent as a mentee — engineers teach it codebase conventions so it can absorb the rote work and protect deep focus.
- Talk frames adoption gaps at organizations adopting agentic AI and how to close them by training engineers to mentor agents rather than micromanage them.
coding-agentsaugment-codedeveloper-productivity
Original description
You’d never let a swarm of fresh interns ship to prod on day one—same deal with AI agents. Mentoring the Machine dives into how acting like a tech lead (not just a user) turns those bots into real leverage. In this talk, Eric will deliver practical advice for working with AI agents in the SDLC. He'll also preview how effective use of AI agents changes the calculus of software engineering at both a micro and macro level. ---related links---