Once you have more than one task going, you need a control tower. The agent view is a single screen showing every Claude Code session at once: what's running, what's finished, and what's blocked waiting on your answer. You can kick off a job, send it to the background, walk away, and jump back in only when it actually needs a decision — even from your phone. The idea of background work and being pinged when a job needs you spans every surface, but the claude agents view itself is a Power-Track (terminal) screen — it comes into its own once you're running many sessions at once, which is a power-user pattern.
A single conversation is easy to follow. Five of them at once is a juggling act —
and once you’re running subagents,
workflows, and a couple of long jobs, you genuinely have
five. The agent view (claude agents) is the control tower: one screen listing
every session, each tagged with what it’s doing — running, done, or blocked
waiting on you. It’s a Power-Track (terminal) screen, and worth being plain
about: it earns its place only once you’re juggling many sessions at once, which is a
power-user pattern. The everyday slice of this — “run it in the background, ping me
when it’s done” — you can simply ask for in Claude Desktop.
That last state is the useful one. Instead of watching a task crawl, you send it to the background and get on with something else; the view keeps it alive and tells you the moment it finishes or hits a question only you can answer. You attend to the work when it needs attention, not before.
It reaches past the terminal, too. With notifications on, a completed run or a pending decision can ping your phone — so a job you started before lunch can let you know it’s ready while you’re nowhere near your desk. The shape of the work changes from “sit and wait” to “kick it off and get called back.”
why it helps Run many tasks at once without losing track of any of them.
examples- Send slow jobs (a big test run, a long migration) to the background and let the view tell you when they're ready.
- The
claude agentsview is a Power-Track screen for juggling many sessions — most people don't need it until they're running several at once. - The view surfaces what's blocked on you — so you only jump in at the moments that actually need a human.
- Turn on notifications and a finished task or a question can reach your phone, not just your terminal.
Questions people ask
- How do I open the agent view?
- Run `claude agents` in the terminal — it's a Power-Track screen listing every Claude Code session at once: what's running, what's finished, and what's blocked waiting on your answer. It's most useful once you're juggling several sessions, which is a power-user pattern.
- Do I need the terminal for background work?
- Not for the everyday version. You can ask Claude in plain language to "run this in the background and ping me when it's done" and get notified — including on your phone. The `claude agents` control-tower view, for managing many sessions at once, is the Power-Track (terminal) piece.
- Can Claude keep working while I do something else?
- Yes. Send a slow job (a big test run, a long migration) to the background and the agent view keeps it alive, telling you the moment it finishes or hits a question only you can answer.
- Will I get notified when a background task needs me?
- Yes — turn on notifications and a finished run or a pending decision can ping your phone, not just your terminal, so a job you started before lunch can reach you while you're away from your desk.
- What does \"blocked\" mean in the agent view?
- It means a task has paused on a question only you can answer — a decision or an approval. The view surfaces what's blocked on you so you jump in only at the moments that actually need a human.