← Back to context

Comment by recroad

18 hours ago

I just don’t understand how people are getting negative value out of AI or even only 20% productivity boost. I can only conclude that people don’t know how to use agents.

I mean, it doesn’t really matter if it caused by people failing to use the agents well or not. You cannot assume everybody to use the technology the best way possible

Are you mostly creating new things or integrating with complex, undocumented, untestable systems?

  • Mostly brownfield systems in Java, Elixir and TS. I use OpenSpec in explore mode and point the agent to all the different repositories (when not working in a monorepo) to identify changes. Once done, i switch to propose mode and spend at least 15 minutes there iterating over the plan until I'm satisfied with the TDD approach (agents need tests to verify their work). Then apply and review. This also auto generates docs etc.