ZyanDocs

Using the Ads Agent

The per-campaign Ads Agent and the cross-campaign Portfolio Agent — model and effort controls, playbooks, the research brief, and why every change still needs you.

Two chat assistants live inside GrowthAd Manager. The Ads Agent is scoped to one campaign and knows its metrics, ad groups and history. The Portfolio Agent reasons across the campaigns you select. Both analyse and propose. Neither executes anything against your spend.

Before you start

Both agents are owner-only and need the provider connected under SettingsIntegrations. The Portfolio Agent additionally needs at least one Google campaign selected — otherwise it says Select at least one Google campaign.

Which agent to open

Ads AgentPortfolio Agent
ScopeOne campaignThe campaigns you select
WhereThe floating panel on a campaign detail pageAd Manager → Portfolio Agent
Good atSearch terms, negatives, RSA copy, one campaign's CPABudget reallocation, comparing campaigns, pause candidates

The controls

SettingWhat it changesDefault
ModelWhich model answers. Models marked (analysis only) cannot propose campaign changes at all.Default
EffortHow much reasoning to spend: Low, Medium, High, X-High or Max. Higher takes longer.
Web researchWhether the agent may look things up. Auto, On or Off. Forced to Off for analysis-only models.Auto
PlaybookInserts a saved long-form prompt so you do not have to write the brief yourself.
Campaign scopePortfolio Agent only. Which campaigns the agent may read and reason about.

Analysis-only models cannot propose changes

Pick one of those and you will get good reading of the data and no actionable proposals. The panel says so — Analysis only — this model cannot propose campaign changes. If you wanted a recommendation you can approve, switch model first.

Playbooks and quick prompts

Six playbooks cover the recurring jobs: Full campaign buildout, Search terms & negatives, RSA and landing pages, Competitor gap, Bidding and budget, and Change audit & learning.

Quick prompts are one click each: Analyze performance, Find wasted spend, Ad group breakdown, Keyword analysis, Demographic insights, Campaign settings, Google recommendations, What changed recently? and Budget simulation. Condition-aware ones appear when they apply — Improve low CTR, Fix zero conversions, Reduce high CPA.

The Portfolio Agent has its own set: Portfolio overview, Budget reallocation, Find wasted spend, Compare top campaigns, Pause recommendations and Growth opportunities.

The campaign research brief

This is the highest-value thing on the page and the most frequently skipped. It is structured business context the agent reads before it answers anything, and the difference between a generic answer and a useful one.

Field groupWhat to put in it
ServicesWhat you actually sell — the placeholder suggests mobile detailing, tree service, vacation rentals
Service areasWhere you serve
CompetitorsWho you lose to
DifferentiatorsWhy someone picks you
Services not offeredSo the agent stops bidding on them
Poor-fit traffic to blockThe searches that waste money
Compliance-sensitive wordingWhat you may not say
Preferred and avoided landing pagesWhere traffic should and should not go
Positioning, ICP and audience detailWho you want
Proof pointsWhat you can claim
Price posturePremium, mid, value
Brand voiceHow ad copy should sound
SeasonalityWhen demand moves

Services not offered earns its keep immediately

Most wasted spend in a small account is traffic for something the business does not do. Filling that one field turns find wasted spend from a guess into a list.

Approval, always

The agent proposes. You approve. There is no path where a chat message moves money on its own.

No autonomous optimisation runs by default

Durable Google Ads optimisation tasks — the research, plan, approve, execute, verify loop — ship behind a flag that is off by default. With it off, chats behave like ordinary approvals and create no runnable tasks. On the Meta side, the auto-approve rules card stores rules that nothing evaluates: every action still requires a manual approval. Do not plan around unattended changes.

Approved changes go through the same staged review and the same frozen money guards as an edit you made by hand.

History

The panel keeps conversation history and a separate action history, so you can see what was proposed, what you approved, and when. Use the action history before asking what changed recently? — it is the record of your own decisions, not the provider's change log.

Troubleshooting

SymptomCauseFix
The agent explains but never proposes anything actionableAn analysis-only model is selectedSwitch model; web research is also forced off for those
The Portfolio Agent refuses to startNo campaigns selectedSelect at least one Google campaign in the scope picker
Answers are generic and miss your businessThe campaign research brief is emptyFill it in, especially services not offered and poor-fit traffic
An approved change did not reach the providerApproval and application are separate stepsCheck the staged-changes bar and press Apply
A proposal was rejected as too largeIt crossed a frozen money guardStep it up over smaller edits
A Meta approval stopped working overnightMeta approvals expire after 24 hoursAsk the agent to re-propose
You expected a rule to act while you were awayThe Meta auto-approve rules card is dormantEvery action needs a manual approval