# How to diagnose Performance Max campaigns with an AI agent

> Tier: deep. Full contract: quantified decision rules and evidence requirements.

Where PMax spend actually goes, whether asset groups are healthy, and which campaigns spend without the ad strength to justify it.

**Intent.** Make an opaque campaign type inspectable: placements, asset health and spend, in one ranked view.

## When to use

- PMax holds meaningful spend and nobody can say where it goes.
- Before feeding PMax more budget.
- Shopping accounts where PMax and standard Shopping coexist.

## When not to use

- PMax campaigns younger than 6 weeks: the learning phase makes every diagnostic read as unhealthy.
- Accounts where PMax spend is trivial; the pass costs more attention than it frees.

## Sources

Required: Google Ads

## Preconditions

- At least one PMax campaign with 30+ days of spend.
- For product questions, the Shopping feed reachable via the account.

## Inputs

- `window`: Analysis window. Default: last 30 days.

## Procedure

1. Read asset group diagnostics: ad strength, coverage, action items. — tools: `google_ads_get_pmax_asset_diagnostics`
2. Read the assets themselves, to name what is missing or weak. — tools: `google_ads_get_pmax_assets`
3. Read placement distribution: how much serves on Search-like, Shopping, Display, YouTube. — tools: `google_ads_get_pmax_placements`
4. For Shopping-heavy accounts, read product-level performance and the products behind it. — tools: `google_ads_get_shopping_performance`, `google_ads_get_shopping_products`
5. Rank campaigns by spend over asset health, and list the top concrete fixes.

## Decision rules

- **When** A campaign spends above the account median with ad strength below Good → **conclude** Rank it first: it buys reach with weak ammunition, and the fix is asset work, not bidding.
- **When** Coverage action items name missing asset types (video, long headlines) → **conclude** List them verbatim as the work order.
- **When** A high share of conversions comes from brand-like placements → **conclude** Flag possible brand cannibalisation; PMax may be buying conversions search would have caught. **Unless** Brand is explicitly excluded elsewhere and this is the intended catcher.
- **When** Products with spend and zero conversions concentrate in one feed segment → **conclude** The problem is the feed segment, not the campaign; name the segment.

## Evidence requirements

- Every ranked campaign shows spend, ad strength, and its named action items.
- Placement claims cite the placement report, not inference.

## Human approval boundary

- Asset replacement and feed fixes are human work; the skill delivers the ordered list.
- Budget or status changes proposed here go through Safe Writes.

## Failure modes

- Learning-phase campaigns read as broken; check campaign age first.
- Placement reporting for PMax is partial by design; treat distributions as indicative, and say so.
- Ad strength is Google's own heuristic; treat it as a ranking signal, not a verdict.

## Output

- **Campaigns ranked**: Spend over asset health, worst first.
- **Work order**: Missing or weak assets, verbatim from diagnostics.
- **Spend map**: Where PMax money actually serves, with the caveat stated.

## Related

- Skill: [account-audit](https://www.getmcpads.com/skills/account-audit.md)
- Skill: [budget-reallocation](https://www.getmcpads.com/skills/budget-reallocation.md)
- Guide: [campaign-audit](https://www.getmcpads.com/guides/campaign-audit.md)