How-To
Set up a Meta Lead Generation campaign with AI
One task, a few steps. Run the prompts in your approved AI workspace.
Where to run this
Your approved ChatGPT, Claude or Gemini workspace, files uploaded first.
Upload first
- Approved campaign brief and target CPL
- Markets, languages, budget
- CRM details and sales process
- Lead qualification criteria and lead form requirements
- Landing pages and approved offers
- Pixel and Conversions API status
- Historical performance and creative assets, if reusing or cloning a campaign
Steps
- 01
Pick your starting point before you build a blueprint
Do this
New advertiser, new market, new lead-generation initiative, no suitable historical campaign: build fresh. An existing lead 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: clone and adapt it.
- 1a
New campaign: generate the blueprint
AI prompt You are designing a complete Meta Lead Generation campaign. Using only the approved materials provided, generate: a campaign blueprint, recommended campaign structure, audience framework, lead capture framework (Instant Forms vs. website forms), creative framework, and measurement framework. Use only information supplied. Do not invent audiences, products, offers, claims or budgets. Finish with READY TO BUILD or NOT READY.
- 1b
Existing winning campaign: audit it, don't just redesign it
AI prompt Review the attached Meta Lead Generation 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, checking specifically whether reported lead volume reflects qualified leads or raw form fills, a high lead count with poor CRM sync or weak qualification criteria can look like success and not be one. Then identify scaling, audience expansion, and creative opportunities. Use only: KEEP, TEST, EXPAND, REMOVE, HUMAN REVIEW, NOT EVIDENCED. Do not redesign a successful structure without evidence. Do not invent performance results. Do not approve the campaign. Finish with STRUCTURE CAN BE REUSED or STRUCTURE REQUIRES REVISION.
- 1c
Cloning into a new market: adapt, don't rebuild
AI prompt Use the attached high-performing Meta Lead Generation campaign as the source blueprint. Preserve: campaign structure, audience framework, lead form framework, and measurement framework. Review whether changes are required for: market, language, local CRM/sales-process differences, local lead-qualification criteria, and creative availability. 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 approve the campaign. Finish with READY TO CREATE LOCAL BLUEPRINT or LOCAL EVIDENCE REQUIRED.
- 02
Build tracking and lead infrastructure before anything else
AI prompt Review my Meta Lead Generation tracking setup against the attached blueprint. Validate: Meta Pixel, Conversions API, CRM integration, offline conversion tracking, lead sync integration, domain verification, and event prioritisation. Use only: MATCH, MISMATCH, MISSING, NOT EVIDENCED. Do not infer missing settings. Do not approve setup.
Do this
Confirm the CRM lead sync is actually pushing qualified-lead status back to Meta, not just capturing the raw form submission, if Meta only ever sees "lead submitted" and never "lead qualified" or "lead converted," it will optimise toward volume over quality.
- 03
Build campaign and audience structure
AI prompt Review this Meta Lead Generation campaign and audience structure against the attached blueprint. Review: campaigns, ad sets, prospecting audiences, lookalikes, retargeting audiences, customer lists, and audience exclusions. Use only: MATCH, MISMATCH, MISSING, CONFLICT. Do not infer missing information. Do not invent audience sizes. Do not approve setup.
- 04
Build lead forms and creative assets
AI prompt Review these Meta Lead Generation forms and creative against the approved guidelines. Check: Instant Forms, website forms, primary text, headlines, descriptions, images, videos, lead magnets, and thank-you screens. 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
A shorter Instant Form usually produces more, lower-intent leads; a longer one produces fewer, better-qualified leads. Match form length to what the sales team can actually follow up on, not to whichever produces the lowest cost-per-lead in isolation.
- 05
Reconcile the build against the blueprint
AI prompt Compare the approved blueprint against the completed campaign build. 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.
- 06
Final launch readiness review
AI prompt Review the final Meta Lead Generation campaign evidence pack. Verify: Pixel implementation, CAPI implementation, CRM integration, lead capture readiness, form readiness, prospecting coverage, retargeting coverage, creative coverage, landing-page readiness, and policy status. Use only: PASS, BLOCKER, HIGH RISK, NOT EVIDENCED, CONDITION ACCEPTED. Missing evidence is not a pass. Do not approve launch. Do not recommend optimisation actions.
Do this
Have a second person check the campaign before it goes live, and confirm the sales team actually knows leads are about to start arriving, a technically perfect campaign that leads go cold on because nobody follows up isn't a win.
Practitioner notes
Notes from other practitioners
What actually happened when you ran this. Gotchas, better prompts, platform quirks. Notes post immediately and are visible to everyone.
No notes yet.