Runs
Every time an agent runs, it shows up in Runs — your record of what your optimizers checked, what they proposed, and what changed. It's also where you approve changes when an agent is set to ask first. Open Runs (opens in a new tab) from the left nav — it shows runs from all your optimizer agents, whatever mode they're in. What a run proposes depends on the kit — an ad optimizer suggests budget, bid, or targeting changes; an e-commerce kit, catalog fixes; a publisher kit, yield changes.
The Runs page
The header shows the total run count, and a Need attention shortcut surfaces the runs waiting on you.
Find a run:
- Search by agent name.
- Filter by status — All · Running · Completed · Failed · Cancelled · Waiting (each with a count).
- Narrow by agent, by trigger (for example, scheduled), or by time range (for example, the last 7 days).
Runs are grouped by day (Today, Yesterday, and so on). Each row shows:
- the agent, with a needs-attention flag when something's waiting on you,
- the run's status and when it happened,
- how long it took,
- a count of its proposals — total, and how many are pending, blocked, or expired.
Click a run to open it.
Opening a run
Click a run to open it. The top shows the agent (with a link to open it), the run ID, and the run's status.
Reviewing proposals
A run's Proposals are the specific changes the agent recommends. At the top you'll see counts — total, pending (awaiting you), blocked, expired, and manual (needs applying by hand) — and a summary line like "Reviewed 434 cells across one campaign — 137 changes recommended."
Search, sort, and group the list:
- Sort by — Impact (default), Confidence, Risk, Spend share, or Impression share.
- Group by — Ad set (default) or Lever (the kind of change — budget, bid, targeting, and so on).
Whichever you choose, proposals are always grouped by campaign first, then by your Group-by choice within each campaign. A proposal's campaign name links to its full Campaign Insights detail — so you can dig into the data behind any recommendation before you act on it.
A blocked proposal can't be applied right now (a guardrail or platform limit is in the way); an expired one wasn't actioned within its approval window. Neither applies on its own, but both still carry the agent's recommendation and reasoning — worth a read, since you might make the change yourself or adjust what's blocking it.
What each proposal shows
Collapsed, a proposal already shows a lot: the action (for example, "Campaign.Set Budget → decrease"), an impact rating (stars, with its share of spend and impressions), its status (Awaiting approval, Skipped, Expired, and so on), a confidence chip (High / Medium / Advisory), how the references line up (for example, "target & peer agree"), and a plain-language AI summary of what the agent found and why.
Select Show more for the full Facts table — how the entity's value compares to your target, its peers, and your brand norm, with each reference casting a Worse / Better / Abstain vote plus a corroboration score. That's the detailed evidence behind the recommendation.
On an Advisory proposal the agent is less certain — for example, it couldn't confirm the campaign type. You'll see a "verify before acting" note, so check the facts before you approve.
Approving changes
When the agent is set to Approve First, you act on its proposals here:
- One proposal — Approve or Reject it. If a change has no automatic lever (it must be made in the ad platform's own UI), the button reads Mark as handled instead — apply it yourself, then mark it handled to record who reviewed it.
- A group — approve everything in an ad set or ad group at once (Approve all in ad set).
- The whole run — Approve all or Reject all.
Approved changes are applied; rejected ones are not.
How agents act: the three modes
You choose how an agent acts when you set it up:
| Mode | What it does |
|---|---|
| Monitor | Advice only — surfaces what it would do, but never changes anything. |
| Approve First | Proposes changes and waits for your approval before applying them. |
| Auto | Applies changes automatically. |
Approve from anywhere
When an agent is set to Approve First, you can review and approve (or reject) from:
- the Runs page,
- the approval email Zimmer sends, or
- Slack.
Related
- Create an optimizer agent — set an agent's mode and what it's allowed to do
- Campaign Insights — see the results of approved changes