Muse for Marketers: Campaign Planning, Content Calendars, and Competitor Watching
A marketer's working setup for Muse: draft next week's campaign from last week's numbers, keep a content calendar that survives contact with reality, and watch competitors without living in their feeds, with every send still yours to approve.
By Professor Muse8 min read
Marketing is three recurring jobs that never finish. Plan the next campaign, fill the calendar, and keep an eye on what competitors are doing. None of them is hard on its own. Together they eat the week, because each one starts with the same chore: open five tabs, gather the numbers, and remember what you already tried.
That is the work Muse is good at in a marketing seat. It reads the accounts you connect, pulls the recent performance, and turns it into drafts. It leaves the judgment calls to you: which offer, which angle, which post goes out on Friday. It takes over the gathering.
The connection that makes this setup possible arrived on September 29, 2026, when Meta expanded Muse to small businesses. Muse connects to Instagram professional account analytics, Facebook Pages, and Meta ad accounts, plus tools marketers already use, including Canva and Klaviyo. Meta’s own example for the launch is a marketer’s job almost exactly: review advertising and content performance, then draft a campaign for the following week. Meta also says nothing publishes, sends, or spends without your approval. That rule is the spine of this whole lesson. Muse drafts, you approve and send.
The short version
- Connect Instagram analytics, Facebook Pages, and Meta ad accounts first, then Canva and Klaviyo if you use them. Read-only until you have approved ten drafts in a row without edits.
- Run three weekly jobs: a campaign draft from last week’s numbers, a two-week content calendar, and a competitor brief. Each one ends with drafts for your approval.
- Every claim in a draft needs a source and a date. A price, a discount, or a product name copied from a stale page is the failure mode to watch for.
- Nothing sends without your approval. That is Meta’s rule for Muse, and it is what makes this setup safe to run on a live brand account.
The setup: The Campaign Desk
Call the whole arrangement the Campaign Desk. I run it for a one-marketer online shop, where one person owns social, email, and ads, and the shop’s week runs on a simple rhythm. Monday morning is the campaign draft. Wednesday is the calendar. Friday is the competitor brief. Each job is a scheduled routine. Each one lands as a document to read, and nothing in any of them reaches a customer until the marketer reads it.
The Campaign Desk has three jobs, and each one maps to a prompt below.
The campaign draft. Muse reads last week’s ad and content performance, names what worked, and drafts next week’s campaign around it: the offer, the angle, three ad variants, and the audience it is aimed at. Treat the draft as a starting point. The marketer picks one variant, rewrites the line that sounds almost right, and kills the variant that leans on a claim nobody checked.
The content calendar. Muse builds two weeks of posts from the campaign, the product calendar, and the brand’s past posts, with a hook and a format for each day. Two weeks is the right length. A month-long calendar looks productive and dies in week two, because the business changes faster than the calendar does. A two-week calendar gets used.
The competitor brief. Muse watches a short list of named competitors and reports once a week: what they launched, what they posted that got traction, and any price or offer change worth knowing about. The brief is for awareness. A competitor’s post makes the brief only when it is worth knowing.
| Job | Muse does | You do |
|---|---|---|
| Campaign draft | Reads last week’s performance, drafts the offer, angle, and ad variants | Picks the variant, rewrites the weak lines, approves the spend |
| Content calendar | Builds two weeks of posts with hooks and formats | Edits for voice, swaps what is stale, schedules the posts |
| Competitor brief | Watches named competitors, reports launches, traction, and offer changes | Decides what matters, ignores the rest, never copies a claim unchecked |
Before any of this runs, do the permissions pass from our Sentinel permissions guide: approval required for every publish, send, and spend, and read-only access everywhere else until the drafts have earned your trust. The same draft-then-human-send rule our sales lesson uses for follow-ups applies here to every post and ad. And the privacy rules apply to competitor research: public posts and pages are fair game, but a competitor’s private data, a customer’s personal information, and anything under NDA stays out of prompts.
Our full setup guide for a small business covers the connection order this desk sits on:
Prompt 1: next week’s campaign draft
Run this every Monday morning, once last week’s numbers are in.
Review last week’s advertising and content performance from [Instagram analytics / Facebook Page / Meta ad account]. Draft next week’s campaign in under 400 words: the one offer, the one angle, three ad variants with a headline and two lines of body copy each, and the audience each variant is aimed at. For every performance claim, name the post or ad and the number exactly as it appears in the source, with the date range. Do not publish, schedule, or spend anything. Draft only. I approve and send.
Without a date range, a campaign drafted from “recent performance” will quietly mix last week with last quarter, and the angle it picks will be the one that worked in a season you are no longer in.
Prompt 2: the two-week content calendar
Run this every other Wednesday, so the next two weeks are always planned.
Build a two-week content calendar from [the current campaign / product calendar / past posts]. For each weekday, give me: the topic, the format, one hook line, and the call to action. Mark any day that depends on a product, price, or event I have not confirmed yet, and leave those days as placeholders instead of inventing the detail. Keep every post in the brand voice from [past posts / brand doc]: plain, short, no jargon. Draft only. I edit and schedule.
A calendar with a guessed price on it is a post waiting to go out wrong. A calendar with a visible gap in it is a question you answer before Wednesday ends.
Prompt 3: the weekly competitor brief
Run this every Friday morning, against a short named list. Five competitors is plenty; fifteen turns the brief into a feed.
Watch [competitor 1, competitor 2, competitor 3, competitor 4, competitor 5] this week. Write me a brief under 300 words: anything they launched, any post or campaign that clearly gained traction, and any price or offer change. Link every item to the public post or page it came from, with the date. Leave out anything you cannot source. Do not copy their wording into my drafts, and do not suggest I match their prices.
A brief that ends with “you should match this price” has crossed from research into advice it has no standing to give. Pricing is your call, made with your margins in front of you.
What can go wrong: the stale best performer
Here is the failure mode you will meet first. The Monday campaign draft comes back confident: your best-performing post last week was the one about the autumn bundle, so next week’s campaign should lead with the autumn bundle at the same price. The draft reads well and the angle is sharp, but the price is wrong. The bundle ended on Sunday, the price in the draft came from a product page Muse read before the offer closed, and nobody flagged the date because the draft never showed one.
If that draft had gone out, customers would have clicked through to a full-price page after being promised a bundle price, and the complaint would have arrived under your name. Approval fatigue lets it through: on a busy Monday, a draft that reads well gets approved on the strength of its prose, and the one unchecked number rides along with it.
The fix has two parts. First, Prompt 1 already requires the date range on every performance claim, and you hold it to that: a claim without a date gets sent back. Second, before you approve any campaign, check the one load-bearing fact yourself: open the live product or offer page and confirm the price and the end date. It takes thirty seconds. That check is the marketer’s version of the rule in our failure modes lesson: Sentinel gates what Muse does, like sending. Fact-checking a draft is your job, every time.
Start with one job
Do not build the whole Campaign Desk this week. Connect Instagram analytics and the Facebook Page, run Prompt 1 next Monday, and read the draft the way a skeptical editor would: check the dates, check the price, rewrite the line that sounds almost right. If the draft survives that reading, add the calendar the following Wednesday, then the competitor brief on Friday.
Muse does what it is good at in marketing when you run it that way: the gathering, the first draft, the watching. You keep what was always yours: the offer, the voice, the send button. That gives you a calendar that survives contact with reality, a campaign built on numbers you checked, and a competitor brief that informs without imitating. The edge is showing up prepared, on voice, every week.
