5 AI Prompts Your Marketing Team Should Be Using Today

Audit paid media accounts, research keywords, analyse your CRM and create marketing assets — with ready-to-use prompts for Claude, ChatGPT or any LLM.

By Pau Ferrer Ponseti · ferrerponseti.com · Growth Consulting & Paid Media

Why This Matters Now

Artificial intelligence gets discussed a lot in abstract terms: productivity, automation, transformation. But in the day-to-day work of marketing, its real value shows up when it eliminates repetitive analysis, accelerates research and structures decisions faster.

Many teams still spend hours every week on tasks that AI can already assist with: reviewing competitor ads, analysing CRM performance, researching SEO topics or creating campaign assets. Time that could be invested in strategy instead.

In this guide you will find five practical prompts — tested in real workflows — that you can use with Claude, ChatGPT or any advanced LLM to automate critical parts of your marketing workflow.

What you need to get started
These prompts assume you can export data from tools such as:
· your CRM · Google Ads / Meta Ads · Google Search Console · Google Analytics
No advanced technical knowledge required. Just the ability to export, structure and paste data.

How to Build More Powerful Prompts

Before diving into the prompts, three principles that make the difference between mediocre results and genuinely useful outputs. Apply them every time you design or adapt a prompt.

1. Ask the AI to ask you questions first

When you are about to create a complex prompt, start by asking the AI to ask you questions. Tell it: "Before writing the prompt, ask me everything you need to know to do this well." The answers you give will feed a much richer context — and the final output will be more precise and actionable.

2. Build and refine the prompt in a separate session

Do not build the prompt in the same chat where you are going to run it. Use a separate conversation — or even a different AI model — to design, improve and clean it up. This lets you iterate on the prompt without contaminating the working session with noise. A well-crafted prompt prepared in advance produces consistent results from the very first attempt.

3. Give the AI the same context that will run the prompt

The AI running the prompt needs to understand who you are, what you do, who your audience is and what the specific goal is. The more relevant context you include at the start — company, vertical, tone, constraints — the less you will need to correct afterwards. Context is not noise: it is the difference between a generic answer and a useful one.

4. For large projects, ask the AI to generate separate prompts for each phase

The most common mistake when working with AI is asking for too many things at once. Solutions like AI Agents exist for this — they work on one very specific task. If you do not have AI agents, do not worry: you can achieve the same result simply by having a conversation. You just need to break all the tasks in the prompt into smaller, more manageable pieces for the AI.

General rule:
A well-constructed prompt with good context always beats a quick prompt with no context. Invest time in preparing it — it will save you iterations and errors.

Prompt 1: Generate Landing Pages for SEO and Paid Media

The problem

Creating landing pages for long-tail keywords or paid media experiments requires copywriting time and structure. Most teams leave these opportunities untapped because the production cost is high. With a good prompt, you can generate structured drafts in minutes.

Step-by-step workflow

1. Identify keyword clusters you want to target (Search Console, Ahrefs, Semrush) — or ask the AI to build them for you ;).
2. Create a landing strategy spreadsheet with: primary keywords, search intent, target audience, product or service description.
3. Add context about your differential value proposition.
4. Provide all of this information to the prompt.

The prompt

You are an SEO strategist and conversion copywriter.

I will provide you with a keyword cluster we want to target with a landing page.

Your task is:
1. Design the complete landing page structure optimised for SEO and conversion.
2. Write a main H1 and the key headings (H2, H3).
3. Include sections that address the search intent and the main objections.
4. Suggest internal linking opportunities with existing pages on the site.
5. Ensure the content also works for paid media traffic
   (clarity, strong CTA, no friction).

Tone: professional, clear and conversion-oriented, maintaining SEO relevance.

What you will get

Expected output:
A complete landing page structure with H1, headings, objection sections, CTA and internal linking suggestions — ready to send to design or publish directly.

Prompt 2: Create Lead Magnet Drafts

The problem

Lead magnets are one of the most effective assets for capturing demand in paid media campaigns and organic traffic. The problem is that creating them well — with logical structure and real value — takes time. AI can generate a complete draft of several lead magnets in a single session.

Step-by-step workflow

1. Identify the most recurring problem of your target audience — or ask the AI to build it for you ;).
2. Define the most useful format: checklist, guide, template or framework.
3. Prepare: audience description, main problem and chosen format.
4. Provide those inputs to the prompt.

The prompt

You are a B2B marketing strategist with experience in demand generation.

We want to create a downloadable lead magnet for our audience.

Target audience: [describe audience]
Main problem: [describe problem]
Format: [checklist / framework / guide / template]

Your job is:
1. Propose a clear and compelling title for the lead magnet.
2. Design the complete structure of the document.
3. Write a brief draft for each main section.
4. Suggest how the content can naturally lead towards our product or service
   without feeling like an advertisement.

The output should be usable as a downloadable marketing resource.

What you will get

Expected output:
A complete lead magnet draft — title, structure and content per section — with a natural transition towards your service or product offer.

Prompt 3: Detect Patterns in CRM and Sales Pipelines

The problem

Marketing performance is usually measured only at lead volume level. However, the most valuable insights appear when you analyse how those leads evolve inside the pipeline: which channels generate real deals, which sources stall at early stages, where commercial velocity is lost.

Step-by-step workflow

1. Export CRM data with fields such as: lead source, attribution campaign, pipeline stages, timestamps and deal outcome.
2. Remove personally identifiable data before pasting.
3. Organise the data in a clean spreadsheet.
4. Paste a representative sample (50–200 rows) into the prompt.

The prompt

You are a revenue operations analyst with experience in B2B SaaS.

I will provide you with CRM pipeline data including: lead source,
campaign attribution, timestamps per stage and deal outcome.

Your job is:
1. Identify patterns that positively or negatively affect pipeline performance.
2. Detect delays or inefficiencies in the commercial process by stage.
3. Compare the performance of different acquisition channels (quality vs. volume).
4. Suggest concrete improvements in lead management or campaign segmentation.
5. Propose 3–5 key metrics that should be monitored regularly.

Focus on practical insights that improve alignment between marketing and sales.

What you will get

Expected output:
A pipeline analysis by channel and stage, identification of bottlenecks and concrete optimisation recommendations to improve lead quality and closing velocity.

Prompt 4: Automate Topic Research and SEO Planning

The problem

SEO topic research involves reviewing multiple sources, identifying search intents, organising clusters and prioritising. It is a process that can consume days of work when done manually. AI can structure a complete topic cluster — with priorities — in a matter of minutes.

Step-by-step workflow

1. Choose a central topic related to your business or a service line.
2. Gather context about your audience, competition and current positioning.
3. Provide that information to the prompt along with the main topic.
4. Use the output as the basis for your content roadmap.

The prompt

You are an SEO strategist with experience in B2B content marketing.

Our website wants to build authority around the following topic: [insert topic].

Your task is:
1. Generate a complete topic cluster around this topic (pillar page + cluster posts).
2. Identify informational, transactional and comparative searches by subtopic.
3. Propose concrete article ideas for each cluster with an editorial angle.
4. Detect internal linking opportunities between the proposed content pieces.
5. Recommend which topics should be published first for the fastest SEO impact.

Structure the output so it can be used directly as an editorial content roadmap.

What you will get

Expected output:
A structured topic cluster with pillar page, cluster articles, mapped search intents, internal linking opportunities and a publication order prioritised by SEO impact.

Prompt 5: Audit Paid Media Accounts

The problem

Ad accounts grow in complexity over time: duplicated campaigns, poorly distributed budgets, outdated segmentations. Auditing them objectively and systematically requires time and experience. With the right data, AI can detect structural problems and optimisation opportunities in minutes.

Step-by-step workflow

1. Export performance data from Google Ads or Meta Ads.
2. Include key metrics: impressions, clicks, CTR, CPC, CPA, conversions and total spend.
3. Organise the data by campaign and ad group in a spreadsheet.
4. Paste the data into the prompt with context about the business objective.

The prompt

You are a senior paid media consultant with experience in B2B and e-commerce accounts.

I will provide you with performance data from Google Ads or Meta Ads campaigns.

Your task is:
1. Identify campaigns or ad groups with low performance and possible causes.
2. Detect structural problems in segmentation or campaign architecture.
3. Highlight clear budget redistribution opportunities.
4. Propose 3–5 concrete experiments that could improve performance.
5. Present a prioritised action list — ordered from highest to lowest expected impact.

The goal is to produce a practical audit that guides immediate account optimisation.

What you will get

Expected output:
A structured audit with campaign diagnostics, budget redistribution opportunities and a prioritised action list ready to execute.

Bonus Tip: How I Created This Article

1. Using ChatGPT to generate an initial prompt:

   I want to create a new article with a title like this:
   5 prompts to automate tasks: Use AI in your business
   
   The tasks I think can be either automated or made more efficient are:
   
   - create and push to the github project of your site new, optimised landings
     to amplify organic reach and paid media testing.
   
   - create drafts for new lead magnets that can be uploaded on your site and
     used as downloadable resources on your ad campaigns.
   
   - feed the AI with CRM data (pipeline evolution, call recordings, source and
     campaign attribution...) and let it help you find patterns of improvement:
     leads are being called too late, a specific campaign shows much better CRM
     performance than the rest...
   
   - reduce drastically the active research you need to make for a topic you want
     to position on Google with your site. Then let AI write and correct the
     content produced.
   
   - audit paid media accounts. Feed the AI with account data including campaign
     names, dates, history changes and relevant metrics and explain that you want
     it to analyse the performance of the accounts and come up with quick
     technical wins.
   
   Please ask any questions you consider important. Any feedback for improvement
   is more than welcome — feel free to improve on the ideas.
   
   Once you have all the information, create a prompt I can copy into Claude
   to create a relevant and appealing article for my blog.

2. ChatGPT then asks questions such as:

   • Who is the target audience for the article?
   • Which AI tools should the prompts be oriented towards?
   • Do you want it to include exact prompts the reader can copy?
   • Approximately how many words should it be?

3. ChatGPT generates the prompt, which I then copy and paste into Claude.

4. Claude generates a first draft of the article, usually in docx format.

5. At this point it is my job to make sure the article content truly delivers what I want — and I personalise it with sections like this bonus tip.

6. Once you have the final content, you can write the following prompt to Claude Code. But first:

   • It is important to have it connected to your website's GitHub environment so it can push the content it writes
   • This is the prompt I used for my Freelancer vs Agency article
   • I recommend uploading the article as a PDF to GitHub so Claude can read it correctly
   • It is also worth noting that this prompt was created by ChatGPT based on a set of rules I have predefined for code generation. The goal is to be able to publish the article without breaking anything.

   Here it is:

   Important operating rules:
   - Make the smallest possible set of changes needed.
   - Do not refactor unrelated files.
   - Do not change layouts, templates, routing, sitemap generation, or blog architecture.
   - Do not rename folders or move existing articles.
   - Do not modify the Spanish blog.
   - Only create or update the English article using the content provided.
   - Preserve the site's current static architecture (Astro + static build).
   
   Goal:
   - Create an English blog article using the document located at: freelancer-vs-agency.docx.pdf
   - This document is the source of truth for the article content.
   
   Steps to follow:
   - Open and read the file freelancer-vs-agency.docx.pdf. You can find it in the
     main branch with the same path.
   - Extract the text, tables, headings, and structured sections from the document.
   - Reconstruct the article content faithfully.

Conclusion: AI Doesn't Replace Strategy — It Accelerates It

Tools like Claude or ChatGPT do not replace strategic thinking. They do not know what positioning makes sense for your business, which audience is most profitable, or how to structure a differential proposition. That remains human work.

But they can eliminate the repetitive analytical work that consumes time without generating value: reviewing data, structuring documents, synthesising scattered information, generating first drafts. And that frees up capacity for what really matters: business decisions, experimentation and growth strategy.

The five prompts in this guide are designed for marketers and consultants who already have good judgement and want to multiply their execution capacity. Use them as a starting point, iterate on them and adjust them to your specific business context.

Implementation tip
Start with the prompt most relevant to your current pain point. Do not try to implement all five at once. One well-executed workflow is worth more than five half-finished ones.