How to Build a Marketing Plan with AI (5-Day Process)

2026 Update:

AI agents change the leverage in this game. Use them to speed up research, persona drafts, competitor teardowns, and first-pass copy.

But the market still decides. A prompt is a hypothesis. A campaign is the test.

This plan used to assume you were launching a “startup.” Same process if you run a local service shop or a one-person AI business. Narrow target. One offer. Two channels. Ship in five days.

You’ve got the business. Maybe you’ve even built the site.

Now what?

Most first-time operators skip this part. They go straight to “I need traffic” without knowing who they’re targeting or why those people would care.

Then they wonder why the ads don’t convert.

I’ve built marketing plans for dozens of businesses. The process used to take weeks of research, competitor analysis, and guesswork. Now I do the first pass in a day using Claude.

This guide gives you the exact prompts I use. Copy them, customize them, and you’ll have a real plan you can test.

One warning: AI gives you hypotheses, not answers. The prompts get you most of the way there. The market validates the rest when you run actual campaigns.

Research used to be the bottleneck. Finding market data, analyzing competitors, understanding customers. Weeks of work, most of it guesswork.

AI eliminates the bottleneck.

The catch: most people use AI wrong. They ask “help me with my marketing” and get generic garbage.

The fix: specific prompts with specific context.

Don’t Make This Mistake

When I launched my first business, I targeted “small business owners who need marketing help.”

That’s millions of people. I was competing with agencies, freelancers, and every marketing tool ever built.

I burned through $3,000 in ads before I figured out the problem: I was targeting everyone, which meant I was targeting no one.

The fix was counterintuitive. I narrowed to “solo consultants making $100-200K who want to productize their services.”

That’s a much smaller pond. Ads started converting.

Peter Thiel explains this in Zero to One. When PayPal launched, they didn’t target “online shoppers.” They targeted eBay PowerSellers: a tight group that desperately needed easier payments.

PayPal dominated that niche, then expanded.

This is your template.

Local shop version: not “anyone who needs a plumber in the metro.” Try “homeowners in these five zips with a 15+ year system, who search after 5pm.”

Solo AI version: not “companies that want AI.” Try “3-10 person trades businesses that miss calls and will pay for a missed-call setup.”

1. Pick the narrowest viable audience
2. Become the obvious choice for those people
3. Expand only after you’ve dominated

Every failed campaign I’ve run traces back to targeting too broadly.

Step 1: Market Research with AI

Before I spend money, I run market research. This used to take days. Now it takes 30 minutes.

You need to know:

• How big is this market, and is it growing?
• Who are the main players and how are they positioned?
• What do customers actually complain about?
• Where are the gaps?

AI pulls from training data, which can be stale. Use the output as a starting point, then validate with real conversations and your own search results.

Market Overview Prompt

Open Claude and paste this. Replace the brackets:

You are a market research analyst. Give me a comprehensive overview
of the [INDUSTRY/NICHE] market.

Include:
1. Estimated market size and growth trajectory
2. Key players and how they are positioned
3. Main customer segments
4. Current trends and disruptions
5. Common pain points customers face
6. Typical price points and business models
7. Barriers to entry
8. Regulatory or compliance considerations

Be specific. If you are not sure about a number, say so.
Do not invent statistics. Cite a source URL or omit the number.

Industry: [YOUR INDUSTRY]
Geographic focus: [Meridian ID / US / etc.]
Business type: [local service shop / solo AI offer]

Real example: When I was evaluating a productized SEO audit, I used “technical SEO services for SaaS companies.” The output pointed at a gap for one-time audits under $1,000 versus agencies on retainers.

That gap became the positioning.

Follow-up:

Based on this overview, what are the 3 most underserved
customer segments in this market? For each segment, explain:
- Why they're underserved
- What they're currently doing to solve the problem
- What would make them switch

Save both outputs. You’ll use them next.

Step 2: Building Buyer Personas with AI

Generic personas are useless. “35-year-old marketing manager who wants to grow” describes millions of people and helps you target none of them.

You need personas specific enough that you could find them on LinkedIn, in a Facebook group, or on a Google Business Profile search. Specific enough that you know the words they use.

Give AI your market research from Step 1, then ask for distinct personas to compare.

Buyer Persona Prompt

You are a customer research specialist. Based on the following
product/service, create 3 distinct buyer personas.

Product/Service: [DESCRIBE WHAT YOU'RE SELLING]
Price Point: [APPROXIMATE PRICE]
Main Benefit: [PRIMARY VALUE PROPOSITION]
Industry Context: [PASTE YOUR MARKET OVERVIEW FROM STEP 1]

For each persona include: demographics, where they hang out,
pain points, objections, buying triggers, and who influences
the decision (spouse, office manager, accountant).

Make each persona distinctly different. Give them names.

If your three personas all sound similar, you haven’t gone deep enough.

Persona Validation Prompt

Looking at these 3 personas, answer:

1. Which persona has the most urgent need? Why?
2. Which persona has the highest willingness to pay? Why?
3. Which persona would be easiest to reach? What platforms?
4. Which persona has the shortest sales cycle?
5. If I could only target ONE persona to start, which should it
   be and why?

The answer to question 5 is your primary target. Ignore the other two for now.

Trying to target all three means your messaging speaks to no one. Start with one, nail it, then expand.

Step 3: Competitive Analysis with AI

Your competitors have already spent money figuring out what works. Study them.

I analyze competitors before every campaign. Not to copy them. To find the gap they don’t own.

Method 1: Website Copy Analysis

1. Google your main keyword (including “[service] near me”)
2. Open the top 5 organic results and top 3 ads
3. Copy homepage and sales page text
4. Ask Claude for each: promise, positioning, objections handled, proof, CTA, and gaps.

Method 2: Ad Copy Analysis

If competitors are running ads, they’re telling you what they think works. Use Meta Ad Library for free, or a spy tool like AdPlexity.

Analyze these competitor advertisements. Identify:

1. ANGLES: What hooks are they using?
2. TARGETING SIGNALS: Who does the messaging assume?
3. FUNNEL STAGE: Cold, warm, or hot?
4. PATTERNS: What do multiple competitors do similarly?
5. GAPS: What angles is NO ONE using?

[PASTE AD COPY]

Competitive Gap Analysis Prompt

Based on this competitive analysis, identify:

1. POSITIONING GAPS: What positioning is no competitor owning?
2. AUDIENCE GAPS: What customer segments are underserved?
3. MESSAGING GAPS: What pain points are ignored?
4. CHANNEL GAPS: Search, Map Pack, Meta Ads, YouTube, email?
5. OFFER GAPS: What offers or guarantees could differentiate us?

For each gap, rate:
- Opportunity size (1-10)
- Difficulty to execute (1-10)
- Fit with our product (1-10)

You’re looking for high opportunity, low difficulty, good fit. That’s your positioning.

When I analyzed the SEO audit market, everyone was selling monthly retainers. The gap was a one-time audit with an implementation guide. That became the offer.

For a dentist, the gap might be “evening hours + transparent pricing” while every competitor leads with “family dentistry since 1998.”

Step 4: Opportunity Identification

You’ve done the research. Now pick a lane.

At this point you have:

• Market overview
• One primary persona
• Competitive analysis
• Gap analysis

Time to synthesize something you can test this week.

Opportunity Synthesis Prompt

Based on all the research below, identify the top 3 market
opportunities for [YOUR PRODUCT].

For each opportunity, provide:

1. TARGET: Which persona or segment
2. POSITIONING: How we'd position against competitors
3. ANGLE: The main hook
4. CHANNEL: Best traffic sources to reach them
5. OFFER: What we'd offer to get them to act
6. VALIDATION: How we'd test this before scaling

Rank by:
- Revenue potential (1-10)
- Speed to validate (1-10)
- Competitive defensibility (1-10)

[PASTE YOUR RESEARCH FROM STEPS 1-3]

Pick the opportunity with the highest “speed to validate” score. Not the biggest revenue potential.

You need to learn fast. Your first hypothesis is probably wrong. Find out quickly and iterate.

Revenue potential matters later, once you’ve validated that people actually want it.

Step 5: Funnel Strategy

You know who you’re targeting and how you’re positioned. Now you need a path from stranger to customer.

Most people overthink this.

The mistake new businesses make

They run ads saying “Buy Now” to people who’ve never heard of them.

That works for Amazon. It doesn’t work for your new shop or your new AI offer.

You’re competing with established players for the small slice of people ready to buy today. You’re losing, because they have more trust and bigger budgets.

The smarter play: Reach people who have the problem but aren’t ready yet. They’re cheaper. Then nurture.

Top-of-funnel vs bottom

Real example from a client selling project management software:

• Bottom ad: “Try [Software] Free”
• Top ad: “Why Your Projects Keep Going Over Budget (Free Audit Template)”

The bottom ad got a 0.8% CTR and a $12 CPL. The top ad got a 2.4% CTR and a $3 CPL.

The top-of-funnel leads took longer to convert. They converted at a higher rate because they’d been nurtured, and overall CAC was lower.

The trade-off is real: Top-of-funnel needs email, retargeting, content. More work up front.

For a new business without brand recognition, it’s often the only way to compete. For a plumber with emergency intent, bottom-of-funnel search still wins. Don’t force a lead magnet on a flooded basement.

Lead magnet and nurture

Ask AI for 5 lead magnet ideas (title, format, why they’d want it, how it leads to the paid offer). Pick the one they can use in under 10 minutes. Calculators and templates beat unread PDFs.

Don’t pitch on email 1. Have Claude draft a 5-email sequence over two weeks: deliver the magnet, expand the problem, introduce the category, show proof, then a soft offer.

Put this in Kit (formerly ConvertKit). Same product, shorter name. Don’t build a custom ESP.

Step 6: Traffic Source Planning

Don’t try to be everywhere. Pick one or two channels based on where the persona actually is.

For a dentist, HVAC, or plumber, I start with local SEO plus search ads. Map Pack is the unpaid version of “people who already want you.” Paid search fills the gaps while Google Business Profile compounds.

For a solo AI offer, I start with either Google Search (if people search the problem) or Meta Ads (if they don’t). Google is higher intent and more competitive. Meta is cheaper and needs better creative plus nurture.

Traffic Source Selection Prompt

Based on this buyer persona and marketing strategy, recommend
the top 2 traffic sources to test first.

Persona: [PASTE YOUR PRIMARY PERSONA]
Product: [YOUR PRODUCT]
Price point: [PRICE]
Funnel strategy: [TOP/MIDDLE/BOTTOM FOCUS]
Budget for testing: [MONTHLY BUDGET]

For each traffic source:
1. Why it fits this persona
2. Targeting strategy
3. Ad format recommendations
4. Minimum test budget
5. What "success" looks like for a 14-day test

Rank by: Likelihood of a useful read within 30 days

Important: I said “top 2” not “top 5.” You don’t have the budget or attention to test five channels well.

Keyword Research Prompt

If you’re running search, you need keywords:

Generate keyword ideas for [PRODUCT/SERVICE] in [CITY/REGION if local].

Include:
1. HIGH INTENT: People ready to book or buy
2. COMPARISON: People evaluating options
3. PROBLEM-AWARE: People searching the problem
4. INFORMATIONAL: People researching the topic

For each keyword, estimate:
- Search volume (high/medium/low)
- Competition (high/medium/low)
- Buyer intent (1-10)
- Recommended landing page type

Focus on long-tail terms bigger competitors might skip.
Do not invent exact monthly volumes. Use high/medium/low.

Start with high-intent keywords. People searching “emergency AC repair [city]” are ready. Lower-intent keywords need more nurture.

Full Google Ads setup guide

The Complete AI Marketing Plan Workflow

Here’s my 5-day process from zero to first test.

Day 1: Research Foundation

1. Run the market overview prompt. Save the output.
2. Generate 3 buyer personas.
3. Pick your primary persona with the validation prompt.
4. Write down: “I’m targeting [specific persona] because [reason].”

Day 2: Competitive Intelligence

1. Google your main keyword. Open the top 8 results.
2. Copy competitor website text and ads.
3. Run competitive analysis prompts.
4. Identify your positioning gap.
5. Write down: “I’m positioned as [X] because competitors ignore [Y].”

Day 3: Funnel and Offer

1. Decide: lead magnet or direct offer (emergency local search is usually direct).
2. If lead magnet: generate ideas, pick one, create it with AI, then edit.
3. Map the email sequence.
4. Select 2 traffic sources.

Day 4: Campaign Assets

1. Write landing page copy with AI, then edit heavily.
2. Generate 10+ ad variations per angle.
3. Build the email sequence in Kit.
4. Create simple retargeting for visitors who don’t convert.

Day 5: Launch

1. Review everything. AI output needs a human.
2. Set up tracking: pixels, conversion events, call tracking, UTMs.
3. Build campaigns.
4. Launch with $20-50/day per paid channel.
5. Calendar reminder to review in 7 days.

Full tracking setup guide

What AI Can and Can’t Do

AI is excellent at:

• Compressing research from weeks to hours
• Generating hypotheses and angles
• First drafts of copy
• Spotting patterns in competitor pages
• Structuring your thinking

AI cannot:

• Tell you if people will actually buy
• Validate your price
• Guarantee ads convert
• Replace tests with real traffic and real money

The market decides. AI helps you build better hypotheses faster.

Your real advantage: While competitors spend weeks on the deck, you’ve launched and gathered data. You’re on iteration 3 while they’re still planning iteration 1.

Your Marketing Plan Template

One page. Nothing fancy.

MARKETING PLAN: [PRODUCT/BUSINESS NAME]
Date: [TODAY]

WHO I'M TARGETING
- Primary Persona: [Name, role, specific situation]
- Main Pain Point: [The problem]
- Why They'd Care: [Why this offer is relevant]

MY POSITIONING
- Gap I'm Filling: [What no one else is doing]
- Angle: [How I'm different]
- Price Position: [Premium/Mid/Budget]

MY FUNNEL
- Traffic Source 1: [Platform + targeting]
- Traffic Source 2: [Platform + targeting]
- Lead Magnet (if any): [What they get]
- Primary Offer: [What I'm selling]
- Price: [$]

SUCCESS METRICS (30-day)
- Cost Per Lead: $[X]
- Lead to Customer Rate: [X]%
- Customer Acquisition Cost: $[X]
- Revenue or booked jobs goal: [X]

FIRST 3 TESTS (This week)
1. [Specific test]
2. [Specific test]
3. [Specific test]

Print it. Update it after every test.

Your Next Step

Option 1: Do it yourself

1. Block 2 hours tomorrow morning
2. Open Claude
3. Run the prompts in this guide
4. Fill out the one-page plan
5. Launch a test within 7 days

Don’t spend weeks perfecting. Spend days building, then let data tell you what to fix.

Option 2: Do it with me

Book a strategy call and we’ll build the plan in 90 minutes. You’ll leave with a completed plan, first ad variations, and a path to launch.

Related Guides

• Niche Research with AI
• Campaign Optimization
• AI Tools for Marketing