Managing Ambient Agents

Warp provides a centralized management view where you can monitor agent activity across your account and (where applicable) your team. It’s designed to answer, at a glance:

  • Which agents have been running recently (and what’s running right now)

  • Which runs succeeded, failed, or were canceled

  • Where an agent was triggered from (a local agent conversation, the Warp CLI, Slack, etc.)

  • How many AI credits those runs consumed

This management view includes your local (interactive) agents and Ambient Agent runs.


What appears in the management view

The management view includes two categories of agent activity.

Interactive agents

  • Initiated from the Warp desktop app.

  • The conversation is owned by you. It opens locally in Warp, and can be shared via a link when needed.

  • Credit usage reflects inference.

Ambient agent runs

  • Background executions initiated by triggers such as integrations and automations (for example: Slack, Linear, schedules, GitHub Actions, or API/CLI invocations).

  • Each run produces a shared session that can be inspected after completion (including logs, messages, and outputs).

  • Credit usage reflects inference + compute, shown as a single combined value in this view.

In the Personal tab, you can view all of the interactive and Ambient Agent conversations that you own. In the All tab, you can see everything from the personal tab, as well as any ambient sessions that are shared with you by your teammates; right now, this only includes things triggered from integrations.


The agents list

Each row represents a single item in the management view (either an interactive conversation or an ambient run). The list is intended to be scannable: you should be able to understand “what happened” without opening anything.

Fields you’ll see

Source

Where the agent was launched from. Common sources include:

Status

Warp uses a small set of statuses to help you quickly identify what needs attention:

Status
Icon
Description

Working

N/A

in progress (may include queued / running states)

Blocked

🟨

(interactive only)

the conversation is waiting on user input or a required step

Canceled

⬜️

(interactive only) the interactive conversation was canceled before completion

Failed / Errored

🔺

something went wrong (applies to both interactive and ambient)

Success

completed successfully (applies to both interactive and ambient)

Duration (for Ambient Agent tasks)

  • Shown for ambient runs to indicate how long the task executed.

  • Note: Interactive conversations generally don’t map cleanly to a single “run duration,” so this is currently omitted.


Inspecting an agent

The primary interaction is simple:

  • Clicking an ambient row opens the shared session for that run (logs/messages/output).

  • Clicking an interactive row opens the conversation locally in the Warp app.

This makes the management view a navigation surface: find the thing you care about, click once, and you’re in the right context to inspect or continue work.

Filtering

In both Personal and All views, you can open the filter menu and filter by:

  • Source (interactive, API, CLI, Slack/Linear, scheduled)

  • Day of creation

  • Creator

  • Status

This is the fastest way to isolate “everything that failed today,” “runs from Slack,” or “what a specific teammate triggered via integrations.”

Last updated

Was this helpful?