How do you stay aware of what your AI coding agents are doing?
I've been running Claude Code, Cursor, and Codex pretty heavily for the last few months and I keep hitting the same loop:
1. Start a task in one agent
2. Switch to something else (Slack, Twitter, another terminal)
3. Come back 30-40 minutes later
4. Agent finished 35 minutes ago. Or worse, it's been waiting for my approval the entire time.
The more agents I run, the worse it gets. There's no unified way to know what's happening across them.
Curious what other people's setups look like:
- Do you just keep terminals visible and check manually?
- Built any custom notification scripts?
- Use something like ntfy or Pushover?
- Just... accept the wasted time?
I've been building something in this space (push notifications + approval flows for AI agents) and I'm trying to understand if everyone's workflow is as janky as mine, or if some of you have figured out something clever.
Would love to hear what's working and what's not.
Replies
The learning angle is underrated here.
When you're new to AI coding agents, the wait-and-miss loop isn't just wasted time — it breaks the feedback you need to actually learn what the agent is doing. Agent gets stuck, waits 30 min, you come back to a half-finished state and have no idea what decision it was waiting on.
I started adding checkpoint comments to my CLAUDE.md: "after each major step, describe what you did and what you're about to do next." Not a notification system, just making the agent narrate. It doesn't solve the async problem, but it means when I do check back, I can actually see where it got stuck and why — which is how I'm learning what these tools can and can't handle autonomously.
What's the most common approval request you see people missing?
i like to use cmux's built in notification.
for approval flow my solution is permission/allow list that i keep fine-tuning + hooks for gating
Same problem here. Running Claude Code, Cursor, and Copilot means I have 3 different tabs just to track what is running. What helped was adding a cost dimension to the awareness problem - we started using aicosts.ai to track spend per-agent. Turns out some agents were burning way more tokens than others on the same task. Now I can see both status and cost in one place.
For just status, have you tried something simple like a shared terminal dashboard? We use tmux with named sessions per agent.