Wiring It Together: Your First Marketing Pipeline

This is Part 10 of a 16-part series on building your AI VP of Marketing with Claude Cowork. Previous: Agent: Content Repurposer | Next: Skill: Social Media Post Creator

The Pipeline

You have built four tools across five articles. Each one does a specific job. The Content Brief Generator produces structured briefs. The Brand Voice Checker audits content against your brand standards. The Campaign Strategist turns briefs into multi-channel campaign plans. The Content Repurposer takes one piece of content and transforms it into every format the campaign calls for.

Until now, you have used these tools one at a time. You ran a brief, reviewed it, started a separate conversation with the Campaign Strategist, and so on. That works, but it misses the point. These tools were designed to feed each other. The output of one is the input of the next.

Here is the complete flow:

TOPIC
  |
  v
[Content Brief Generator]  -- Skill: produces a structured brief
  |
  v
[Brand Voice Checker]      -- Skill: audits the brief for voice consistency
  |
  v
[Campaign Strategist]      -- Agent: turns the brief into a campaign plan
  |
  v
[Content Repurposer]       -- Agent: produces content for every channel in the plan
  |
  v
DISTRIBUTION-READY CONTENT

You start with a topic. You end with content ready to publish across multiple channels. Every step in between is handled by a tool you already built.

This is not a new tool. You are not building anything in this article. You are wiring together what already exists and running it as a single, connected workflow. The difference between four separate tools and a pipeline is that a pipeline has a defined sequence, quality gates between stages, and a predictable output every time you run it.

A marketing team does this with people. The strategist writes the brief, the brand manager reviews it, the campaign lead builds the plan, the content team produces the assets. Your pipeline replaces those handoffs with tools that pass work to each other -- and you stay in the loop at every checkpoint.

Wire It Together

You are going to run the full pipeline in a single Cowork session. One conversation, four stages, one topic all the way through. The example topic: a quarterly client update campaign for Tideway Bookkeeping.

Stage 1: Generate the Brief

Open your Cowork project and start a new conversation. Run the Content Brief Generator skill:

Run the content-brief skill for this topic:

Quarterly client update -- Q2 results and what is coming in Q3. Tideway
Bookkeeping wants to show existing clients what improvements shipped this
quarter (automated receipt matching, faster bank imports) and preview what
is coming next quarter (year-end tax prep automation). Goal is to reduce
churn by reminding clients of the value they are getting.

Your VP produces a structured brief with target audience, key messages, CTA, SEO keywords, content format, outline, competitor differentiation, and distribution notes. Read it. Does the brief capture the goal -- client retention, not acquisition? Are the key messages specific to the features you mentioned? Is the CTA appropriate for existing customers rather than prospects?

If the brief is off, correct it now. "The key messages are focused on attracting new clients. This is a retention piece -- the audience already uses Tideway. Rewrite the key messages to emphasize value delivered, not value promised." Fix it before moving to Stage 2. A bad brief produces a bad campaign plan, and a bad campaign plan produces bad content. Every error compounds downstream.

Once the brief looks right, move on.

Stage 2: Check Brand Voice

Take the brief output and run it through the Brand Voice Checker skill in the same conversation:

Run the brand-voice-checker skill on the content brief above. Check every
section -- key messages, CTA, outline descriptions -- against our brand
voice rules.

The Brand Voice Checker reviews the brief against your .claude/rules/brand-voice.md file. It flags language that does not match your voice standards. For Tideway, that might mean catching phrases like "we are excited to announce" (banned vocabulary) or "leverage our powerful platform" (jargon that contradicts the plain-spoken brand).

Review the flags. Some will be valid catches. Others might be false positives -- the checker being too strict on technical terms that your audience actually uses. Accept or reject each flag:

Good catches on "leverage" and "excited to announce" -- fix those. But
"automated receipt matching" is the actual feature name, not jargon.
Keep that. Apply the fixes and show me the updated brief.

The voice-checked brief is now your approved input for Stage 3. It has the right structure and the right voice.

Stage 3: Build the Campaign Plan

Feed the approved brief to the Campaign Strategist agent:

Run the Campaign Strategist agent on the voice-checked brief above.
This is a retention campaign for existing clients -- not acquisition.
The segments should reflect different types of current Tideway clients,
not prospects.

The agent produces audience segments, messaging angles, CTAs, a timeline, and channel allocation. For a retention campaign, the output should look different from the acquisition-focused example in Article 8. The segments might break down by client type (freelance designers versus freelance developers) or by engagement level (active users versus clients who have not logged in recently).

Check the output against reality. Does the timeline fit your actual capacity? Are the channels ones you actually use? Is the email campaign realistic given your current list size? Adjust as needed:

We do not use LinkedIn for client communication -- remove that channel.
Replace it with an in-app notification for active users. Keep the email
campaign for all segments.

Once the campaign plan reflects what you will actually execute, move to the final stage.

Stage 4: Repurpose the Content

Hand the campaign plan to the Content Repurposer agent:

Run the Content Repurposer agent. Take the campaign plan above and
produce the actual content for each channel and format specified in
the timeline. Use the messaging angles from the campaign plan and
apply brand voice rules to every piece.

The Content Repurposer produces each content asset the campaign plan calls for. A client update email. A blog post summarizing Q2 improvements. An in-app notification draft. Each piece uses the messaging angle assigned to its segment and follows your brand voice rules.

You now have draft content for every channel in your campaign. Review each piece, approve or revise, and you are ready to publish.

End-to-End Test

Here is what the pipeline produces at each stage for the Tideway quarterly update campaign. These are condensed examples -- your actual outputs will be longer.

Stage 1 Output: Content Brief

## Content Brief: What Shipped in Q2 (and What is Next)

### Target Audience
Existing Tideway Bookkeeping clients -- freelancers and solo consultants
who already use the platform for monthly bookkeeping. They care about
whether their subscription is worth the monthly fee.

### Key Messages
1. Automated receipt matching went live in April -- clients using it save
   an average of 45 minutes per month on expense categorization.
2. Bank imports now process in under 60 seconds, down from 3-5 minutes
   last quarter.
3. Q3 will bring year-end tax prep automation -- a single click generates
   tax-ready reports for your accountant.
4. These improvements exist because clients asked for them. Feature
   requests from Q1 drove the Q2 roadmap.

### Call to Action
Try automated receipt matching this week -- open your dashboard, click
Receipts, and upload a photo of any receipt. See it categorized in
under 10 seconds.

### Content Format and Length
Client update email (300-500 words) as the primary format. Supporting
blog post (600-800 words) for the website.

Stage 2 Output: Voice Check

BRAND VOICE REVIEW

Checked against: .claude/rules/brand-voice.md

FLAGGED:
- Key message 4 uses "These improvements exist because clients asked
  for them." Passive construction. Rewrite: "You asked for these. Your
  feature requests from Q1 drove our Q2 roadmap."

- CTA says "See it categorized in under 10 seconds." Consider
  specifying what "it" refers to more concretely: "See the amount,
  vendor, and category filled in automatically."

PASSED:
- Tone is conversational and direct throughout.
- No banned vocabulary detected.
- Key messages lead with specific metrics (45 minutes, 60 seconds).
- CTA describes a concrete action with a measurable result.

2 items flagged. 0 critical issues.

After applying fixes, the brief moves to Stage 3 with tighter language and stronger voice alignment.

Stage 3 Output: Campaign Plan

### Audience Segments

| Segment | Description | Primary Channel |
|---------|-------------|----------------|
| Power Users | Clients who log in weekly and use most features. Already engaged. Want to know what is new. | In-app notification |
| Passive Clients | Clients who use Tideway but rarely log in. Their books get done, but they do not explore new features. At risk for churn. | Email |
| New Clients | Clients who joined in Q1 or Q2. Still learning the platform. Need to see value early. | Email (onboarding sequence) |

### Messaging Angles

**Power Users**: "You already use Tideway every week. Here is what changed
since last month -- automated receipt matching and faster imports. Try
receipt matching now and cut 45 minutes from your monthly routine."

**Passive Clients**: "Your books are current, your reports are on time,
and you did not have to think about it. Here is what else Tideway handles
that you might not have tried yet."

**New Clients**: "You joined Tideway to stop worrying about bookkeeping.
Here is proof it is working -- and here is what is coming next quarter
to make it even easier."

### Timeline

| Day | Channel | Action |
|-----|---------|--------|
| Day 1 | Blog | Publish Q2 update post on the website |
| Day 1 | In-app | Notify power users about receipt matching |
| Day 3 | Email | Send Q2 update to passive clients |
| Day 5 | Email | Send onboarding highlight to new clients |
| Day 7 | Email | Follow-up to passive clients who did not open Day 3 email |

Stage 4 Output: Content Assets

The Content Repurposer produces each asset. Here is one example -- the email for passive clients:

Subject: Your books are done. Here is what else Tideway does for you.

Hey [first name],

Your Q2 books are current. Reports are filed. Tax categories are up to
date. That happened automatically -- you did not have to chase receipts
or reconcile transactions.

Two things shipped this quarter that make your account even more hands-off:

1. Automated receipt matching. Snap a photo of a receipt, and Tideway
   fills in the vendor, amount, and category. No manual entry.

2. Faster bank imports. Transactions now sync in under 60 seconds.
   If you noticed fewer loading screens lately, that is why.

Coming in Q3: one-click tax prep. A single button generates every
report your accountant needs for year-end filing.

You are already getting your money's worth. These updates just make
the math even more lopsided in your favor.

[Try receipt matching now -- takes 10 seconds]

-- The Tideway team

Each asset follows the messaging angle assigned in the campaign plan, hits the key messages from the brief, and passes the brand voice check. One topic, four stages, distribution-ready content.

Troubleshooting and Guardrails

The Voice Checker flags too much content

Problem: Every run produces a wall of flags. You spend more time reviewing voice issues than writing content.

Fix: Your brand voice rules are too strict. Open .claude/rules/brand-voice.md and loosen the constraints. If you banned all adjectives, allow industry-specific ones. If you required every sentence to be under 15 words, raise the limit to 20. The voice checker enforces whatever rules you wrote -- if it is flagging too much, the rules need adjustment, not the checker.

The Campaign Strategist produces generic plans

Problem: The campaign plan looks like it could belong to any company. Segments are vague ("young professionals"), messaging angles are bland ("our solution helps you save time"), and CTAs are interchangeable.

Fix: The agent is pulling from your CLAUDE.md, and your CLAUDE.md does not have enough specifics. Add your actual product features, your real customer pain points, and your competitor positioning. The agent cannot be specific about your business if your briefing document is generic. Go back to CLAUDE.md and add a section on your top products or services with concrete details -- pricing, features, what makes each one different.

The Content Repurposer loses brand voice

Problem: The repurposed content drifts from your voice. The blog post sounds right, but the email version sounds like a press release.

Fix: Strengthen your brand voice rules with format-specific guidance. Add lines like "In emails, write as if you are talking to one person. No corporate 'we are pleased to announce.' Use 'you' and 'your' more than 'we' and 'our.'" The Repurposer follows voice rules, but if those rules do not cover format-specific pitfalls, it defaults to generic conventions for each format.

The brief is fine but the campaign plan contradicts it

Problem: The brief targets existing clients, but the campaign plan includes acquisition segments. Or the brief specifies email as the primary format, but the campaign plan puts most effort into social media.

Fix: Add explicit constraints when you hand work to the Campaign Strategist. "This is a retention campaign -- all segments must be existing clients" or "The primary channel is email -- allocate at least 60% of effort there." The agent follows the brief, but it also draws from your CLAUDE.md, which may list channels and goals that pull in a different direction.

When to stop and fix before proceeding

Not every problem needs to cascade through the full pipeline. Here are the gates:

After Stage 1 (Brief): If the brief targets the wrong audience or misses the campaign goal, stop. Do not voice-check a brief that is pointed in the wrong direction.

After Stage 2 (Voice Check): If the voice checker finds more than three critical issues, the brief needs a rewrite, not a patch. Rewrite the flagged sections, then run the check again.

After Stage 3 (Campaign Plan): If the segments do not match real groups you can reach, the plan is theoretical. Fix the segments before producing content. Content written for a fictional audience is wasted effort.

After Stage 4 (Content): If the content does not match the messaging angles from the campaign plan, the Repurposer's instructions need tightening. Go back to the agent definition, not the individual content pieces.

Off-Ramp: What You Have Built

With the pipeline, you type a topic and walk through four stages. Each stage has defined inputs, defined outputs, and a quality gate before the next one starts. The output is consistent because the process is consistent. Your fifth campaign goes through the same pipeline as your first.

You can stop here. This pipeline handles content strategy, brand consistency, campaign planning, and multi-format content production. For a small business without a marketing team, that is a serious operation. If all you ever do is run this pipeline once or twice a month, you are producing more structured, more consistent marketing than most businesses your size.

What is Next

The pipeline produces content for every channel in your campaign plan. But "produce content for LinkedIn" and "write a LinkedIn post that follows platform conventions, uses the right length, and includes appropriate hashtags" are different things. Right now, the Repurposer creates content in the right voice with the right message -- but it does not format that content for the specific conventions of each social platform.

In Article 11, you build a Social Media Post Creator skill that takes repurposed content and formats it for specific platforms -- character limits, hashtag strategies, image specifications, and posting conventions that vary from LinkedIn to Instagram to Twitter.

Part 10 of 16 -- Your AI VP of Marketing series. Next: Skill: Social Media Post Creator