The most productive use of my time is often putting the agents on do not disturb — but that red notification badge keeps paying out little dopamine hits.
Here's something I'm struggling with: often the most productive use of my time involves shutting out codex and claude code, putting the agents on do not disturb, and using my brain to think through a problem or crank through an actual draft of my thoughts.
But that red 20 badge is calling me... an agent needs quick input to keep going on some task. I'm the blocker! I hate being the blocker.

Also, it's a nice little dopamine hit. What did the agent slot machine pay out this time? Another pr could be shipped! Another task could be getting completed!
I just want to feel confident the agents are making progress while I'm working on where I add unique value. But is it really that important if they're stuck for an hour?
I am working on delegation. Either through a better orchestrator, hiring human contract help (DMs are open) or both.
I believe deep work still has leverage. I just have to wire my brain to bet on that belief more often.
After a year with Claude Code as my daily driver, the Codex desktop app's interface for managing many agent threads and automations has me reaching for it more and more.
Right model, right task. In Claude Code you can pin a model per skill—I drop to Sonnet or Haiku when the full power of Opus isn't needed to stay inside my limits.
15 billion tokens, 302 Linear issues shipped to production, just me in Claude Code. Real 'headcount equivalent' territory—and a reminder to measure impact, not just output.
Get More Like This
Follow along as I build and share what I learn
Found this helpful? Share it with your network!