The system I use has names for each task which helps keep track of them, and usually for larger tasks they’re based on a GitHub issue. If I’m ever confused about what an agent is doing, I just ask it what it’s doing. If you want this more often, you could add custom instructions telling the agent to always summarize the current state (in whatever way you find most useful) at the end of a turn.
The system I use has names for each task which helps keep track of them, and usually for larger tasks they’re based on a GitHub issue. If I’m ever confused about what an agent is doing, I just ask it what it’s doing. If you want this more often, you could add custom instructions telling the agent to always summarize the current state (in whatever way you find most useful) at the end of a turn.
Do you keep track of current tasks in a notes and then keep revisiting them?
I was working on an app that maintains a round-robin queue of tasks so that I can switch around them.
My UI lists task by most recently interacted (and has an explicit archive button). I think Claude Code for the web has a similar UI.