Set up a Google App campaign with AI

Where to run this

Your approved ChatGPT, Claude or Gemini workspace, files uploaded first.

Upload first

• ☐Approved campaign brief and primary KPI
• ☐Budget, target markets, languages
• ☐App Store and Google Play URLs
• ☐Firebase and App Attribution Partner setup status
• ☐Conversion events and approved claims
• ☐Creative assets
• ☐Historical performance, if reusing or cloning a campaign

Steps

1. 01

   Pick your starting point before you build a blueprint

   Do this

   New app, new market, no suitable historical campaign: build fresh. An existing app campaign with credible performance history: audit it, don't redesign a winner without evidence. A proven campaign that needs to launch in a new market or language: clone and adapt it.

2. 1a

   New campaign: generate the blueprint

   You are designing a complete Google App Campaign. Using only the approved materials provided, generate: a campaign blueprint, recommended campaign structure (name, objective, campaign type, conversion goal, recommended bid strategy per campaign), a measurement framework (primary conversion, secondary conversions, event hierarchy, Firebase requirements, App Attribution Partner requirements), an audience framework (user acquisition, existing user, high-value user, retargeting strategy), a creative framework (text, image, landscape image, video, HTML5 asset requirements), and app readiness requirements (App Store readiness, Play Store readiness, deep-link requirements, attribution requirements). Use only information supplied. Do not invent products, audiences, events, offers, claims or budgets. Finish with READY TO BUILD or NOT READY.

   Do this

   Don't select more than one conversion action to optimise toward, that creates a blended target across actions with potentially different real values, which confuses the bid strategy rather than sharpening it.

3. 1b

   Existing winning campaign: audit it, don't just redesign it

   Review the attached App Campaign and the supplied performance evidence. First identify what appears to be working, what should remain unchanged, and what is not supported by sufficient evidence. Then identify: measurement opportunities, creative opportunities, asset opportunities, user quality opportunities, event opportunities, and scaling opportunities. Use only: KEEP, TEST, EXPAND, REMOVE, HUMAN REVIEW, NOT EVIDENCED. Do not redesign a successful structure without evidence. Do not recommend changes purely based on best practice. Do not invent performance results. Do not approve the campaign. Finish with STRUCTURE CAN BE REUSED or STRUCTURE REQUIRES REVISION.

4. 1c

   Cloning into a new market: adapt, don't rebuild

   Use the attached high-performing App Campaign as the source blueprint. Preserve: campaign structure, measurement framework, event framework, and creative framework. Review whether changes are required for: market, language, app localisation, event availability, attribution setup, conversion tracking, and regulatory restrictions. Classify every recommendation as: KEEP, LOCALISE, REMOVE, ADD, HUMAN REVIEW, NOT EVIDENCED. Do not redesign the campaign unless the supplied local-market evidence requires it. Do not invent events, audiences or budgets. Do not approve the campaign. Finish with READY TO CREATE LOCAL BLUEPRINT or LOCAL EVIDENCE REQUIRED.

5. 02

   Build measurement and attribution before anything else

   Review the app measurement setup against the approved App Blueprint. Review: Firebase setup, attribution setup, conversion imports, event tracking, deep links, app store links, and conversion hierarchy. Use only: MATCH, MISMATCH, MISSING, NOT EVIDENCED. Do not infer missing settings. Do not approve setup. Finish with BLOCKERS, REQUIRED CHANGES, READY FOR CAMPAIGN BUILD, or RETURN TO TRADER.

6. 03

   Build campaign structure

   Review the App Campaign structure against the approved App Blueprint. Review: campaign objective, app selection, conversion goal, budget, bidding, locations, languages, event optimisation, and campaign duplication. Use only: MATCH, MISMATCH, MISSING, CONFLICT. Do not infer missing information. Do not approve setup. Finish with BLOCKERS, DUPLICATIONS, CONFLICTS, READY FOR ASSET BUILD, or RETURN TO TRADER.

   Do this

   Open: Google Ads → New Campaign → App Promotion. Set tCPA high enough to drive more than 100 conversions early on, Google's own guidance is to review the actual CPA once real data has been collected and then set the target roughly 20% above that observed number, not guess at a target upfront. For iOS specifically, bids around 1.5x higher than Android are the standard recommendation given the platform's measurement constraints.

7. 04

   Build creative assets

   Review the App Campaign assets against the approved App Blueprint. Check: text asset quality, message relevance, image quality, landscape image coverage, video coverage, HTML5 asset coverage, CTA suitability, app-store alignment, audience relevance, unsupported claims or offers, duplicate assets, and missing assets. Use only: PASS, EDIT, REMOVE, HUMAN REVIEW, NOT EVIDENCED. Do not invent offers, claims or promotions. Do not assume policy approval. Do not approve the campaign.

   Do this

   App Campaigns use platform-generated ad combinations, you supply the raw assets (text, images, landscape images, video, HTML5 where available) and Google assembles them, you don't build individual finished ads by hand.

8. 05

   Reconcile the build against the blueprint

   Compare the approved App Blueprint with the completed App Campaign build. Review: campaign structure, campaign objectives, conversion goals, event mapping, Firebase setup, attribution setup, bidding, budgets, locations, languages, and assets. For every setting provide: SETTING, APPROVED VALUE, ACTUAL VALUE, STATUS, EVIDENCE, REQUIRED ACTION. Use only: MATCH, MISMATCH, MISSING, NOT EVIDENCED, NOT APPLICABLE. Do not infer missing settings. Do not modify the campaign. Do not approve launch. Finish with BLOCKERS, ITEMS REQUIRING REVIEW, and an overall status of READY FOR LAUNCH CHECK or RETURN TO TRADER.

9. 06

   Final launch readiness review

   Review the final App Campaign evidence pack. Verify: approved objective, KPI and budget, campaign structure, Firebase implementation, attribution implementation, event mapping, install tracking, in-app action tracking, deep link readiness, asset coverage, store listing readiness, conversion test evidence, policy status, and unresolved blockers. Use only: PASS, BLOCKER, HIGH RISK, NOT EVIDENCED, CONDITION ACCEPTED. Missing evidence is not a pass. Do not infer approval. Do not approve launch. Do not recommend optimisation actions. Finish with Launch Blockers, Accepted Conditions, Evidence Gaps, Items Requiring Review, and an overall status of READY FOR LAUNCH or NOT READY.

   Do this

   Have a second person check the campaign before it goes live.