Running on Autopilot: Automating Recurring Marketing Work

This is Part 14 of a 16-part series on building your AI VP of Marketing with Claude Cowork. Previous: Measuring What Matters | Next: Expanding the Role

What Are Scheduled Tasks?

For thirteen articles, you have been walking into your VP's office and handing them work. You open Cowork, type a prompt or invoke a skill, review the output, and move on. The system works. But it only works when you show up.

Scheduled Tasks change that. A Scheduled Task is a prompt that runs on a schedule you define -- daily, weekly, monthly -- without you being present. Cowork opens the project, runs the task, and saves the output for you to review later. Your VP does the work whether you are at your desk or not.

Think of it this way. Until now, you have been managing your VP through drop-in meetings. You walk over, hand them something, wait for the result. Scheduled Tasks are standing meetings on their calendar. Monday at 8 AM, generate this week's content briefs. Friday at 5 PM, compile the weekly performance report. First of the month, run a competitive scan. The work happens on schedule because you put it on the calendar, not because you remembered to ask.

This is the payoff for the infrastructure you built across thirteen articles. Your CLAUDE.md gives your VP context. Your Rules constrain quality. Your Skills produce consistent outputs. Your Agents handle complex, multi-step work. Scheduled Tasks take all of that and put it on autopilot.

Here is how to create one.

Open your Cowork project. In the left sidebar, click Scheduled Tasks. You will see an empty list -- no tasks have been scheduled yet.

Click New Task. Cowork shows you a form with four fields:

Name. A label for the task. This is for you -- pick something you will recognize in a list. "Weekly Content Briefs" or "Friday Performance Report" works.

Schedule. How often the task runs. Cowork gives you presets -- daily, weekly, monthly -- and a custom option where you pick specific days and times. For most marketing tasks, weekly is the right starting point.

Prompt. The instructions your VP follows when the task fires. This is the same kind of prompt you have been writing all series. It can invoke Skills, reference Agents, or give direct instructions. Everything your VP can do in a conversation, it can do in a scheduled task.

Notifications. Whether Cowork notifies you when the task completes. Turn this on. You want to know when outputs are ready for review without checking manually.

Fill in those four fields and click Save. The task appears in your Scheduled Tasks list with its next run time displayed.

That is the entire mechanism. You write a prompt, set a schedule, and Cowork handles the rest. The complexity is not in the tool. It is in choosing what to automate and writing prompts that produce useful output without you in the loop.

Weekly Content Generation

Your content pipeline (Article 10) takes a topic and turns it into distribution-ready content across multiple channels. You built it to run manually -- you feed in a topic, the pipeline produces briefs, checks voice, builds a campaign plan, and repurposes the content. Every step is already wired together.

Now you put that pipeline on a schedule.

Create a new Scheduled Task with these settings:

Name: Weekly Content Pipeline

Schedule: Weekly, Monday, 7:00 AM

Prompt:

Run the weekly content production cycle.

Step 1: Review the marketing goals and content calendar in CLAUDE.md. Identify 
2-3 topics that align with this month's priorities and have not been covered in 
the last 60 days.

Step 2: For each topic, run the content-brief skill to produce a structured brief.

Step 3: Run the brand-voice-checker skill against each brief to verify tone and 
language alignment.

Step 4: Pass the approved briefs to the Campaign Strategist agent. Produce a 
campaign plan for each brief that includes channel selection, timing, and 
format recommendations.

Step 5: Compile everything into a single document with this structure:
- Executive summary (3-4 sentences on what was produced and why)
- Brief 1: topic, brief, voice check results, campaign plan
- Brief 2: topic, brief, voice check results, campaign plan
- Brief 3: topic, brief, voice check results, campaign plan (if applicable)
- Recommended priority order with rationale

Flag any brief where the voice checker found issues. Do not auto-correct -- 
leave the original and the checker's notes so I can decide.

Save the task. Monday morning, before you open your laptop, your VP has already selected topics, generated briefs, checked them for voice, and built campaign plans. The output sits in the task history waiting for you.

Here is what the output looks like when you open it:

The executive summary tells you what your VP produced and why it chose those topics. Below that, each brief appears in full -- the same structured format you have seen since Article 5 -- followed by the voice checker's notes and the campaign plan. At the bottom, a priority order with reasoning: "Brief 1 targets a keyword gap identified in last month's metrics. Brief 2 supports the product launch timeline in CLAUDE.md. Brief 3 is evergreen and can be pushed to next week if needed."

Your review takes fifteen minutes. You scan the topics, check that they align with what you know about the business right now, read the voice checker's flags if any exist, and approve or adjust the priority order. Then you hand the approved briefs to the Content Repurposer -- either manually or through another scheduled task later in the week.

Competitive Monitoring

In Article 7, you watched your VP run a competitor analysis -- researching rivals, comparing positioning, and identifying gaps. That was a one-time exercise. Markets do not stay still. Competitors change their pricing, launch new products, shift their messaging. A positioning matrix from two months ago is a historical document, not a strategic tool.

Scheduled Tasks turn that one-time analysis into ongoing surveillance.

Create a new Scheduled Task:

Name: Monthly Competitive Scan

Schedule: Monthly, 1st of the month, 8:00 AM

Prompt:

Run a competitive monitoring scan.

Using the competitor list in CLAUDE.md (or the most recent competitive analysis 
in this project's history), research each competitor for changes in the last 30 days:

1. Pricing changes -- new tiers, price increases or decreases, new free offerings
2. Messaging shifts -- new taglines, repositioned value propositions, new claims
3. Product updates -- new features, discontinued products, major releases
4. Channel activity -- new marketing channels, increased activity on existing 
   channels, notable campaigns
5. Content themes -- what topics they are publishing about, any patterns or 
   shifts in focus

For each competitor, produce:
- A 2-3 sentence summary of what changed (or "No significant changes detected")
- A relevance rating: HIGH (requires a response from us), MEDIUM (worth noting), 
  or LOW (informational only)

End with:
- A "Competitive Landscape Summary" paragraph (5-6 sentences) covering the 
  overall direction of the market
- Any positioning opportunities that opened up since the last scan
- Recommended actions, if any, with specific next steps

If a competitor made a HIGH-relevance change, flag it at the top of the report 
before the detailed breakdown.

The output arrives on the first of every month. Most months, it is routine -- minor changes, a few MEDIUM flags, no action required. You scan it in five minutes and file it. That is fine. The value of competitive monitoring is not in any single report. It is in the pattern that emerges over three, six, twelve months. You spot a competitor gradually shifting upmarket. You notice another one doubling down on a channel you abandoned. You catch a pricing change before your customers ask you about it.

When a HIGH flag appears, you pay attention. A competitor just launched a product that overlaps with your core offering. A rival dropped their price by 30%. Someone is running a campaign directly targeting your audience segment. These are the moments where the automated scan earns its keep. You did not have to remember to check. Your VP checked for you.

Automated Reporting

You built a measurement framework in Article 13. It tracks the metrics that matter for your marketing -- traffic, engagement, conversions, whatever you defined as your key indicators. Until now, you have been running those reports manually. You open Cowork, ask your VP to pull the numbers, and review the results.

That is a Friday afternoon task. It happens when you remember, and it does not happen when you are busy. Which means it does not happen on the weeks you need it most -- the weeks where something changed and you should have caught it.

Create a new Scheduled Task:

Name: Weekly Performance Report

Schedule: Weekly, Friday, 4:00 PM

Prompt:

Compile the weekly marketing performance report.

Using the metrics framework from our measurement setup, produce a report 
covering this week's performance:

1. HEADLINE METRICS
   Report each key metric defined in CLAUDE.md with:
   - This week's value
   - Last week's value
   - Week-over-week change (percentage and direction)
   - Flag any metric that moved more than 15% in either direction

2. CHANNEL PERFORMANCE
   For each active marketing channel:
   - Activity this week (posts published, emails sent, ads running)
   - Engagement metrics (opens, clicks, shares, comments)
   - Conversion metrics (leads, signups, purchases attributed to this channel)

3. CONTENT PERFORMANCE
   For content published this week or last:
   - Traffic to each piece
   - Engagement on each piece
   - Best-performing piece and why

4. FLAGS AND RECOMMENDATIONS
   - Any metric that moved significantly (positive or negative) with a 
     one-sentence explanation of the likely cause
   - One specific recommendation for next week based on this week's data
   - Anything that should change in our scheduled content pipeline based 
     on what the numbers show

Keep the report under 500 words. Lead with what changed, not with what 
stayed the same. If nothing significant moved, say so in two sentences 
and skip the detailed breakdown.

Friday afternoon, the report appears. You read it in five minutes. Most weeks, the summary is short: numbers held steady, nothing needs attention, here is what we published. That five-minute read replaces a thirty-minute dashboard session where you try to remember what the numbers were last week and whether this week is better or worse.

The value shows up on the weeks something moves. Traffic spiked because a post got shared. Email open rates dropped because the subject line format changed. A channel that was performing well went quiet. Your VP does not just show you the numbers -- it flags the change, offers a likely explanation, and recommends a specific action. You still make the decision. But you make it with the analysis already done.

Create a second reporting task for monthly summaries:

Name: Monthly Performance Summary

Schedule: Monthly, last Friday of the month, 4:00 PM

Prompt:

Compile the monthly marketing performance summary.

Aggregate weekly reports from this month into a monthly view:

1. Month-over-month trends for each headline metric
2. Best-performing channel this month with supporting data
3. Best-performing content piece this month with traffic and engagement numbers
4. Content topics that resonated vs. topics that underperformed
5. Progress toward quarterly marketing goals (from CLAUDE.md)
6. Three specific recommendations for next month's content and channel strategy

This report informs monthly planning. Be direct about what worked, what 
did not, and what should change.

The monthly summary rolls up your weekly reports into a strategic view. It connects individual week performance to your quarterly goals. It tells you whether you are on track, falling behind, or ahead of plan. And it recommends adjustments -- not vague "try harder" advice, but specific changes tied to data.

Review Cadence

You now have three scheduled tasks running: weekly content generation, monthly competitive monitoring, and weekly performance reporting. Your VP handles the work. But automation does not mean abdication.

This is the same principle from Article 3. You are still the boss. Your VP runs the tasks, compiles the analysis, and makes recommendations. You own the decisions. A scheduled task that nobody reviews is not automation -- it is waste.

Here is the review cadence that keeps you in control without pulling you back into the weeds.

Weekly review -- 15 minutes, Monday or Tuesday.

Open the content pipeline output from Monday morning. Scan the topics your VP selected. Check that they still make sense given anything that changed over the weekend -- a customer conversation, a product update, an industry event. Read the voice checker flags if there are any. Approve the priority order or adjust it. This is your chance to steer before content gets produced, not after.

Then check Friday's performance report. Read the flags. If something moved, decide whether it needs a response this week. If nothing moved, you are done.

Monthly review -- 30 minutes, first week of the month.

Read the competitive scan. Note any HIGH flags and decide on responses. Read the monthly performance summary. Compare progress against your quarterly goals. Adjust your CLAUDE.md if priorities have shifted -- new goals, new audience segments, new channels. Any changes you make to CLAUDE.md automatically flow into every scheduled task on its next run.

Quarterly review -- 60 minutes, once per quarter.

Step back and evaluate the entire automation setup. Are the scheduled tasks producing useful output? Are you actually reading the reports? Has your business changed enough that the prompts need updating? This is when you rewrite prompts, add new tasks, retire old ones, or adjust schedules.

The quarterly review is also when you check for drift. Automation runs the same prompt every time. Your business does not stay the same. A content pipeline prompt written in January might miss a product line you launched in March. A competitive scan might still track a competitor that went out of business. Scheduled tasks need maintenance the same way any process does.

What Is Next

Your marketing pipeline now runs on its own schedule. Content briefs appear Monday morning. Performance reports land Friday afternoon. Competitive intelligence arrives on the first of every month. You review, approve, and steer -- but you do not drive every step.

That pattern -- context, constraints, tools, automation -- works for marketing. It also works for other parts of your business.

In Article 15, you apply the same pattern to sales support. Your VP already knows your product, your audience, and your competitive positioning. You extend that knowledge into sales collateral, proposal generation, and lead qualification. You are not starting over. You are expanding the role -- the same way you would with a human VP who proved themselves on marketing and earned a seat at the sales table.

This is Part 14 of 16 in the Your AI VP of Marketing series. Next: Expanding the Role: Adding Sales Support