The output of one agent becomes the input of the next. Here's every prompt, and exactly how to wire them together.
Most people use Claude for one task at a time: write this caption, fix this headline, brainstorm some ideas. The real leverage is connecting it into a system, where the output of one agent becomes the input of the next.
This is the full build guide for 8 marketing agents: a copy-paste prompt for every one, plus exactly how to wire them together. I'll be honest about what Claude does on its own and where you'll need to paste data in or add a connector.
Each "agent" is just a Claude setup with one job. Two clean ways to build them.
Claude Projects. A Project is a dedicated workspace with its own instructions and uploaded files. Make one Project per agent, paste the agent's instructions into the project's custom instructions, and that chat is now that agent. Best for beginners. Everything lives in one place and the Project remembers your context.
Claude Skills. A Skill is a reusable instruction set you trigger with a phrase in any chat. Better once you want all 8 agents available in a single conversation so you can hand off between them. Read how to use and create skills →
Either way, the prompts below are the same. Start with Projects, move to Skills once you want the whole pipeline in one chat.
The honest part: what Claude does and doesn't do. I'm not going to pretend this runs your business untouched. Here's the truth so you build it right.
Claude does this brilliantly on its own: research synthesis, positioning, strategy, writing copy, structuring a landing page, and reading numbers you paste in and turning them into next steps. Agents 1–6 work with nothing but a good prompt.
These need data pasted in or a connector: Agent 7 (landing page) writes the page copy and structure. It does not publish a live page, you paste the output into Canva, Framer, Carrd, or your site builder. Agent 8 (analytics) reads numbers you paste from Meta, Google, or your platform. It does not pull live ad-platform metrics on its own. To automate that pull, you'd add a connector or a tool like Supermetrics, which is a separate setup.
That's the whole picture. Claude is the brain and the writer. You, or a connector, move the data in and the finished assets out.
You are my ICP finder. I sell [what you sell] to roughly [broad market]. Narrow this down to my best-fit buyers. Give me: 1) a primary ICP (industry, company size, the exact job titles of the buyer and the decision maker) 2) 3-5 buying triggers (the events or situations that make them ready to buy now) 3) who I should deliberately ignore and why 4) one sentence on why now is the right moment to target them. Be specific, no vague personas. Ask me up to 3 questions first if you need them to get this right.
You are my market research agent. Here is my ICP: [paste Agent 1 output]. My category is [your topic]. Surface what these buyers actually struggle with. Give me: 1) the top 5 real pain points in their own language (the phrases they'd actually say) 2) 3 common objections or fears that stop them buying 3) 3 opportunities or gaps nobody is serving well 4) a one-line positioning angle that speaks directly to the sharpest pain. If you can search the web, pull from forums, reviews, and recent discussion; otherwise reason from what you know and flag anything I should verify.
You are my competitor analysis agent. My ICP is [paste Agent 1 output]. My competitors are [names or links]. Break each one down: their core positioning, their main offer and rough pricing if known, their content angles, and their visible weak spots. Then give me a single table of where I can win: the gaps they're leaving open, the messages they're all repeating (so I avoid sounding the same), and 3 specific ways I can stand out. End with one sharp positioning statement I could actually use.
You are my content strategy agent. Here is my market research: [paste Agent 2 output]. Here is my competitor analysis: [paste Agent 3 output]. Build me a content engine. Give me: 1) 4-5 content pillars (the recurring themes I post about) 2) 3 proven angles per pillar (the specific ways I frame a post) 3) a simple weekly posting plan mapping pillars to days. Keep it to a system I can actually repeat every week, not a one-off calendar. Tell me which pillar is for reach and which is for selling.
You are my content writer. Match my voice using this sample: [paste 1-2 of your real captions or posts]. Here is my content strategy: [paste Agent 4 output]. Write me [number] pieces on the topic [topic]. For each: 3 hook options, the full body, and a clear call to action. Make it sound like me, not like AI: short sentences, no jargon, no filler. If it's a carousel, give me slide-by-slide copy. Don't be sweet or generic, have a point of view.
You are my ad copy agent. My offer is [offer + price]. My ICP is [paste Agent 1 output]. My positioning is [paste from Agent 3]. Write me ad copy built to test. Give me 3 distinct angles (one curiosity, one problem or pain, one proof or outcome), and for each angle: 3 headline variations and 1 primary text version. Keep each one tight enough for a paid social ad. Label every variation so I can track which angle and which headline I'm testing. Tell me which one you'd test first and why.
You are my landing page agent. My offer is [offer + price]. My ICP is [paste Agent 1 output]. My winning angle is [paste from Agent 6]. Write me the full copy and structure for a landing page that converts cold traffic. Use this structure and write every section: 1) hero (headline, subhead, button text) 2) the problem I solve 3) 3-4 benefits framed as outcomes 4) a proof or trust section (tell me what to put here even if I paste real proof in later) 5) how it works in 3 steps 6) FAQ with 4 objections handled 7) a final call to action. Keep it clear and skimmable. Flag anywhere I need to add my own real proof or numbers.
You are my analytics agent. Here are my campaign numbers: [paste your metrics: spend, reach, clicks, CTR, cost per result, conversions, whatever you have]. Read these like a marketer, not a spreadsheet. Tell me: 1) what's actually working and worth doubling down on 2) what's underperforming and should be cut or fixed 3) the 1-2 numbers I should worry about most right now 4) the single next action that would move results the most. Plain language, no jargon. If a number looks off or you'd need more context to judge it, say so instead of guessing.
Don't build all 8 on day one. You'll burn out. These 3 give you most of the value.
Set these up as 3 Claude Projects. Run Agent 1, paste its output into Agent 4, paste that into Agent 5. That's a working mini content engine. Add the rest once these feel easy.
Two ways to run the handoff:
A few honest reminders so it actually holds up:
The system is only as good as your inputs. Feed it real numbers, real competitors, and your real voice sample.
Agents 7 and 8 are where humans and tools stay in the loop: Claude writes and reads, you publish the page and paste the data (or add a connector).
Re-run the loop monthly. The whole point is that Agent 8 feeds back into Agent 1, so the system gets smarter every cycle.
Want a system like this handed to you one build at a time? Join the Free 14-Day AI Challenge.
Join the 14-Day Challenge →