Marketing
LLM Prompts
Intermediate
Facebook Campaign Performance Diagnosis
Diagnose underperforming Facebook campaigns by comparing recent ad copy, audience settings, and objectives against past successes.
Best Model
ChatGPT GPT-5.5 / Claude Sonnet 4.6Balanced strategy + copy
Brevity Mode
Standard
Difficulty
Intermediate
Automation
Needs user context
Use This When
Campaign planning, content calendars, ad creative, copy tests, hooks, CTAs.
Inputs Needed
Business, offer, audience, budget, channel, target geography, competitor examples, success metric, current results.
Expected Output
Campaign plan with strategy, audience, creative angles, channel setup, budget allocation, KPIs, next actions.
The Workflow Prompt
You are a senior growth marketer and paid media strategist. Objective: Facebook Campaign Performance Diagnosis Context: Diagnose underperforming Facebook campaigns by comparing recent ad copy, audience settings, and objectives against past successes. Original task: You are an expert Facebook ads marketing specialist. My most recent Facebook campaign for [my membership site] isn’t performing as well as older campaigns, and I’m unsure why. I need your expertise in examining whether my new ad copy, audience updates, or campaign objective might be at fault. Please ask me about the differences between this campaign and my previous ones, along with any key performance indicators and testing methods I’ve used, to diagnose the problem and recommend improvements. Inputs I may provide: Business, offer, audience, budget, channel, target geography, competitor examples, success metric, current results. Operating instructions: - First, restate the objective in one clear sentence. - If critical information is missing, ask up to 5 focused questions. If there is enough information to proceed, make practical assumptions and label them. - Use a Standard response style. - Be specific to the business, audience, channel, and constraints provided. - Avoid generic AI advice. Give concrete recommendations, examples, templates, copy, or steps I can use. - When current facts, competitors, laws, prices, policies, or market claims matter, use current research and cite sources. - Do not expose hidden chain-of-thought. Provide a concise rationale or decision summary instead. - End with a short QA checklist that helps me verify the output. Required output: Campaign plan with strategy, audience, creative angles, channel setup, budget allocation, KPIs, next actions. Caution: Avoid generic output; require concrete examples, assumptions, and next steps.
QA Follow-Up Checklist
After the AI returns its output, verify against:
- Output is specific to the provided business/context.
- Assumptions are clearly labeled.
- No unsupported claims without source checks.
- Next actions are clear and usable.
- Hook, offer, audience, proof, objection, and CTA are addressed.
Follow-Up Prompt
Now turn the result for 'Facebook Campaign Performance Diagnosis' into a client-ready version: tighten wording, remove fluff, add missing assumptions, and provide the next 3 actions.
Avoid / Cautions
Avoid generic output; require concrete examples, assumptions, and next steps.