Runs and schedules
The Agents Command Room shows running agents, switched-on agents with their next run, and past runs with their output and cost, plus schedules and emails.
The Agents Command Room is where you follow your agents at work: what is running right now, which agents are switched on and when they run next, and every recent run with what it produced and what it cost. Everyone can open it. This page also covers the schedule and the run emails, then failures and costs.
The Agents Command Room
Open Agents in the header, then Agents Command Room. The page has three sections, one under the other: Running now, Switched on and Previous runs.
What you see depends on your role. An administrator sees every agent of the organization and every member’s personal agents, and can start any of them; the line at the top reads “Every agent of your organization, and every member’s personal agents.” Everyone else sees their own personal agents only, since the organization’s agents are run and followed by its administrators. On an account without an organization, you see the agents of the brands you own.
Each agent carries a chip that says whose it is: Organization, or Personal. On a personal agent, an administrator also sees the owner’s name after Personal.

Running now
The runs going on at this moment, scheduled or started by hand, with their count next to the heading. Each row names the agent, whose it is and where it runs, then a chip: running, or waiting for the next pass for a scheduled run queued until the scheduler’s next daily pass. On the right, Scheduled or Started by and the person’s name, then the time it started. While something runs, the page reads the lists again every few seconds by itself, so a finished run moves down to Previous runs without a reload. With nothing going on, the section reads “Nothing is running right now.”
Switched on
The agents that run on their own, with their count. Each card shows:
- The agent’s name, whose it is, and its interval, such as every 24h.
- What one run covers: Each brand, in a run of its own, The organization’s own data, or One run over followed by the brands it reads together. After it, under reads:, the data it reads.
- Last run: with the date of its last scheduled run, or not yet, and Next run: with the date of the next one. A run started by hand doesn’t move either date.
Editors and above also get a Run now button on each card. It starts a real, billed run of that agent at once. The run appears under Running now while it goes, and the card then reads Done. with the run’s cost. When some of the agents run brand by brand, a Run now on menu above the cards picks the brand they run on; agents that read a set of brands run over their own set. An administrator who runs a member’s personal agent runs it with that member’s settings.
When nothing is switched on, an administrator reads “No agent is switched on in this organization. Add one from the Organization tab or the Catalog.” Switch an agent on from the Organization or Personal tab, or add one from the Catalog; see organization and personal agents.
Previous runs
The 50 most recent finished runs, newest first, whether they ran on schedule or someone started them by hand. Two menus at the top narrow the list: Brand (when your organization has more than one brand), and, for an administrator, Agents of, set to Everyone, The organization or one member.
Each row shows:
- The agent’s name, whose it is, and where the run was filed: the brand’s name, the brands read together for a run over several, The organization, no brand for a run over the organization’s own data, or A removed brand.
- An outcome chip: the number of findings, report written, nothing changed, no data to read, or failed.
- How it started, Scheduled or Started by and a name, and when it finished, in your own date and time settings.
- What it read, under Read:.
Click a row to open it. The first line gives the model and the tokens in and out, then the billed cost in your organization’s currencies. A run that cost nothing shows no amount. The output follows: each finding with its severity, explanation and suggested action for a watcher or custom agent, the report itself for a report agent, or the reason for a failed run.

Test runs from an agent’s editor are the only runs you won’t find here. Their result shows in the editor, where you started them.
An empty list reads “No run yet.” Agents run on their schedule once they’re switched on, or when someone clicks Run now, so check under Switched on that the agent is there, and that its brand has the right module switched on.
What each outcome means
| Outcome | What happened | Cost |
|---|---|---|
| 3 findings (any number) | The agent read the data, called the model, and posted findings to the brand’s feed. | Billed |
| 0 findings | The agent called the model and found nothing worth flagging. A valid result. | Billed |
| report written | A report agent stored a new report. | Billed |
| nothing changed | The data was the same as on the previous pass, so the model call was skipped. | Free, except reads of a connected system |
| no data to read | The brand had no data for this agent yet, so the run ended before any model call. | Free, except reads of a connected system |
| failed | The run stopped. The reason is shown when you open it. | Free when it stopped before the model call, as most failures do |
A custom agent that reads a connected system pays for reading it on every run, because the reading itself is done by the model. When such a run ends on nothing changed or no data to read, it still shows its cost, with the line “Reading the connection was charged.” Report agents are another exception: they don’t skip on unchanged data, so as long as there’s something to read, you get a report.
How the schedule works
Every scheduled agent has an interval, set in Runs every (hours) on the Schedule and budget tab of its form. It’s the shortest gap allowed between two runs on the same brand. Once that much time has passed since the agent last completed a run there, it’s due again. The Next run: date in the Agents Command Room is the first daily pass after that.
Note: Due runs are picked up by a daily check. In practice an agent runs at most once a day, even with an interval under 24 hours, and a due run can start a little later than its interval suggests.
Only switched-on agents are scheduled. Organization agents run on every brand whose module is on, unless a brand switched them off for itself; a brand can also switch one on just for itself, or change its interval there. Personal agents run on a schedule too: each member’s agents that are switched on run on the organization’s brands as their owner, billed to that person.
An agent set to read several brands together, or the organization’s own data, runs once over them all. That run is filed under the No brand workspace. See AI agents.
Starting a run yourself
In the Agents Command Room, Run now on an agent’s card runs that one agent right away (see Switched on above).
On a findings feed, such as the one on the Google Ads Reporting page, editors see a Run watchers now button. It runs every agent switched on for that brand right away, not only the one shown on the page. The button then reads Done: 3 new findings (with the real count) or Done: nothing new, the total cost of the run (every agent added up) shows next to it, and the feed refreshes. An agent over its budget is skipped, and the others still run. Your own personal agents are included when you belong to the brand’s organization.
Runs started either way are listed under Previous runs with Started by and your name.
You can also test one agent from its card with Run on real data. That test isn’t listed in the Agents Command Room. See organization and personal agents.
Run emails
If you’re an admin, this is the part that lands in your inbox.
A scheduled run that produced something is followed by an email. Runs that found no data or nothing changed stay quiet. Starting a run with Run now also sends the email for report and custom agents that include the full results; test runs never send one.
Who receives it is set per agent on the Notifications tab of its form, under Email the results to:
| Setting | Recipients |
|---|---|
| The organization’s administrators (default) | Every admin of the organization. On an account without an organization, its owner. On a personal agent the choice reads The agent’s owner. |
| These people only | The addresses you list, up to 20. Colleagues are suggested as you type. |
| Nobody | No email. The run is still listed in the Agents Command Room. |
The subject reads like “[Brand] Agent name: 2 findings”, or “[Brand] New report from Agent name” for a report agent. When the run has findings, the email opens on a summary: how many are critical, warnings or info, then one line per finding, the most severe first. Below it, a short table names the agent and the brand, when it ran and what it read, what it found or wrote, and what it cost: the tokens, and the price your organization was charged, in US dollars. Its Open the run button opens that run in the Agents Command Room, already unfolded, and the All runs link opens the page itself. Set Email content to Full results to get the findings, or the report, in the email itself.
Dates in the email follow the recipient’s own settings when it goes to one person. Sent to several, it gives the time in UTC, with the zone written out. Each recipient gets the email in their own language. An address with no account behind it gets your organization’s interface language when it offers exactly one language besides English, and English otherwise.
Listen to this report
When the email goes to one person who has their audio briefing switched on, it also carries Listen to this report (MP3): the briefing episode that speaks about this run. If that person’s briefing is due that day and not made yet, it’s made right then, so the email of the run that brought the news carries it. An email to several people never carries one: a briefing is private.
Reports
Each run of a report agent stores one report. You can open it from the run under Previous runs, or from the agent’s card under Recent reports, where the six most recent per brand are kept at hand. The Agents Command Room can only open recent reports; an older run shows a note instead and points you to the agent’s card.
A report over several brands is open to the same people as a report over one: every member works on every brand of the organization.
Why a run fails
Several of these are safety checks: the run is stopped because a budget or a setting says so.
A run can stop before it starts or partway through. Open the row under Previous runs to see why. The usual reasons:
- Budget used. The agent has used its monthly or weekly budget. The message gives the amount spent against the budget and ends with “Raise its budget under AI Agents, or wait for next month” (or, for the weekly budget, wait for it to clear).
- Switched off. The agent was switched off after the run was queued: “Skipped: this agent is switched off for this brand.”
- Brand choice changed. “Skipped: this agent now runs once over the brands picked for it”, or the reverse, “Skipped: this agent now runs on each brand separately.”
- Brand moved. The brand changed organization since the run was queued: “Skipped: the brand changed organization since this run was queued.”
- Agent removed. The BearingBridge team removed the agent from the app: “This agent was removed from the app.”
- An error while reading data or calling the model.
A failed run doesn’t count as completed, so the agent comes up again at the next check. Fix the cause, or it’ll fail the same way.
What it costs
Any run that reaches the model is billed as AI usage. Its cost is printed on the run and repeated in the email, and it’s always the price your organization was charged. Some agents also pay for reads: the AI visibility data call, Assets Library downloads, and reads of connected systems all count in the run’s cost.
There’s no flat price per run: it depends on the model and on how much the agent reads. Open a few of an agent’s runs under Previous runs to see what it typically costs, then size its budgets from that. Two budgets per agent, monthly and weekly, cap its spending. The agent’s card shows what it spent this month and in the last seven days. A run that starts under budget finishes, even if it crosses the line; the next one is blocked. Agent spending is recorded in the usage log like any other AI action: scheduled and manual runs as Agent run, tests as Agent test run, and the drafts made from a finding as Agent finding · response draft and Agent finding · post draft. See credits and costs.