--- title: "Split brand, audience, and campaign files so AI drafts on-brand copy" description: "Keep brand voice, segments, channel rules, and campaign results in separate files so AI drafts copy for the right audience without a daily re-brief." canonical: "https://scalewithsearch.com/articles/ai-for-marketing-managers" date: "2026-01-28" modified: "2026-09-25" --- ## Site navigation - [Scale With Search](https://scalewithsearch.com/) - Real estate - Real estate - [Real estate](https://scalewithsearch.com/for/real-estate) - Work - Start here - [Send your brief](https://scalewithsearch.com/work#send-your-brief) - [Prepare your six-question brief](https://scalewithsearch.com/work#prepare-your-six-question-brief) - Build - [Site build, content library with SEO, signal desk](https://scalewithsearch.com/work) - For your business - Trades and home services - [Auto body and collision shops](https://scalewithsearch.com/for/auto-body-and-collision-shops) - [Foundation and home repair contractors](https://scalewithsearch.com/for/foundation-and-home-repair) - [Garage door and fencing contractors](https://scalewithsearch.com/for/garage-door-and-fencing-contractors) - [HVAC contractors](https://scalewithsearch.com/for/hvac-contractors) - [Janitorial and commercial cleaning companies](https://scalewithsearch.com/for/janitorial-and-commercial-cleaning) - [Locksmiths](https://scalewithsearch.com/for/locksmiths) - [Moving companies](https://scalewithsearch.com/for/moving-companies) - [Pest control companies](https://scalewithsearch.com/for/pest-control-companies) - [Plumbing and electrical contractors](https://scalewithsearch.com/for/plumbing-and-electrical-contractors) - [Restoration and water or fire damage companies](https://scalewithsearch.com/for/restoration-and-water-fire-damage) - [Roofing companies](https://scalewithsearch.com/for/roofing-companies) - [Towing companies](https://scalewithsearch.com/for/towing-companies) - [Tree services and landscaping companies](https://scalewithsearch.com/for/tree-services-and-landscaping) - [Solar installers](https://scalewithsearch.com/for/solar-installation) - [General contractors](https://scalewithsearch.com/for/general-contractors-and-construction) - [Paving, concrete, and flooring contractors](https://scalewithsearch.com/for/paving) - Practices and professional services - [Bookkeeping and tax practices](https://scalewithsearch.com/for/bookkeeping-and-tax-practices) - [Dental practices](https://scalewithsearch.com/for/dental-practices) - [Family and criminal defense law firms](https://scalewithsearch.com/for/family-and-criminal-defense-law-firms) - [Med spas and aesthetics practices](https://scalewithsearch.com/for/med-spas-and-aesthetics) - [Personal injury law firms](https://scalewithsearch.com/for/personal-injury-law-firms) - [Veterinary clinics](https://scalewithsearch.com/for/veterinary-clinics) - [Gyms and fitness studios](https://scalewithsearch.com/for/fitness) - [Therapy and outpatient health practices](https://scalewithsearch.com/for/therapy-and-outpatient-health) - [Medical billing companies](https://scalewithsearch.com/for/medical-billing) - [Insurance agencies](https://scalewithsearch.com/for/insurance-agencies) - [Financial advisors](https://scalewithsearch.com/for/financial-advisors) - [Property management companies](https://scalewithsearch.com/for/property-management) - [Recruiting and staffing agencies](https://scalewithsearch.com/for/recruiting-and-staffing) - [Architects and interior designers](https://scalewithsearch.com/for/architects-and-interior-designers) - [Logistics and supply chain companies](https://scalewithsearch.com/for/logistics-and-supply-chain) - Agencies, MSPs, and manufacturing - [IT and managed service providers](https://scalewithsearch.com/for/it-and-managed-service-providers) - [Machine shops and precision manufacturers](https://scalewithsearch.com/for/machine-shops-and-precision-manufacturing) - [Marketing agencies and freelancers](https://scalewithsearch.com/for/marketing-agencies-and-freelancers) - [SEO agencies and consultants](https://scalewithsearch.com/for/seo-agencies-and-consultants) - [Small manufacturers and fabricators](https://scalewithsearch.com/for/small-manufacturers-and-fabricators) - Restaurants, shops, studios, and nonprofits - [Restaurants and hospitality businesses](https://scalewithsearch.com/for/restaurants-and-hospitality) - [Retail stores and ecommerce sellers](https://scalewithsearch.com/for/retail-and-ecommerce) - [Photographers, event planners, and travel agents](https://scalewithsearch.com/for/photographers) - [Churches and nonprofits](https://scalewithsearch.com/for/churches-and-nonprofits) - [All industries](https://scalewithsearch.com/for/) - Learn - For your office - [Office job guides](https://scalewithsearch.com/guides/) - [Browser calculators](https://scalewithsearch.com/tools/) - Start here - [How it works](https://scalewithsearch.com/how-it-works) - [Free Starter Kit](https://scalewithsearch.com/kit/business-memory-starter-kit.zip) - [Synthetic specimen](https://scalewithsearch.com/specimen/working-session-specimen.zip) - Guides - [The Complete Guide to Business Memory for AI Agents](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [The Complete Small-Business Guide to AI Agent Governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [The Complete Guide to Leaving Vendor AI Memory](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - Articles by cluster - [Business memory](https://scalewithsearch.com/articles/business-memory-for-ai-agents-guide) - [Agent governance](https://scalewithsearch.com/articles/ai-agent-governance-guide-small-business) - [Migration and ownership](https://scalewithsearch.com/articles/leaving-vendor-ai-memory-guide) - For machines - [llms.txt](https://scalewithsearch.com/llms.txt) - [llms-full.txt](https://scalewithsearch.com/llms-full.txt) - [Machine view](https://scalewithsearch.com/?view=machine) - Company - Evidence - [Proof](https://scalewithsearch.com/proof) - Company - [About](https://scalewithsearch.com/about) # Split brand, audience, and campaign files so AI drafts on-brand copy. A marketing manager runs three campaigns at once: one for enterprise buyers, one for small businesses, and one for a product launch. Each has different messages, pain points, and calls to action. The manager asks an AI assistant for LinkedIn copy for the enterprise campaign. The draft is generic thought leadership that could belong to any company. The manager pastes the campaign brief, and the draft improves. The manager pastes last quarter's best post, then the brand voice guide. The context is now 400 words long before the actual request. The next day, on the same campaign, the manager starts over. The fix is a small set of context files that the assistant reads before it writes. The manager keeps them current. The assistant drafts from them. ## What the assistant needs and does not have Built-in chat memory stores some preferences. It does not hold your brand guide, segment research, channel rules, and campaign results as a maintained record. A marketing manager works with all of these: - brand voice guidelines that took months to settle; - audience segments with different pain points and vocabulary; - campaign objectives that change each quarter; - channel format rules, because LinkedIn, Instagram, and email differ; - results from past campaigns that should shape the next one; - stakeholder preferences, such as a CEO who dislikes exclamation marks or a VP who likes metaphors. Without these, each request needs a re-brief. The writing ability is not the gap. The missing record is. ## What each file holds Split the context by what changes at different speeds. The voice changes rarely. Campaigns change each quarter. | File | Contents | Changes | |---|---|---| | `brand-voice.md` | Sentence length targets, banned words, preferred metaphors, tone by channel, good and bad examples, stakeholder preferences | Rarely | | `audience-enterprise.md` | Job titles, pain points, their words, objections, proof points that convert | When research changes | | `audience-smb.md` | The same fields for small business buyers | When research changes | | `campaigns-active.md` | Objective, target KPIs, message pillars, offers, calls to action, legal no-go claims, what works, what failed and why | Weekly during a campaign | | `channel-rules.md` | Format and voice rules per platform | When a platform rule changes | A `product-features.md` file helps when you launch features often. It holds each feature's approved description and the claims that legal cleared. ## Inspect two of the files These are synthetic examples. ```markdown # channel-rules.md updated:: 2026.09.25 ## LinkedIn - 150 words at most. Hook in the first line. No hashtags. ## Instagram - Casual. Emojis allowed. Call to action in stories, not captions. ## Email - House rule: no "free" in subject lines. - Standard close: one call to action, one link. ``` ```markdown # campaigns-active.md ## Q1 enterprise: SSO launch objective:: demo requests from IT directors pillars:: security review time, admin control, audit trail cta:: "See the admin console" legal_no_go:: no "unhackable"; no compliance guarantees ## Results so far - Email with a question subject line: best open and click rate this quarter. - Webinar promo underperformed: value proposition sat in paragraph three. ``` The results section is where the next campaign learns from the last one. Record clicks and replies next to opens. Since Apple Mail Privacy Protection arrived with iOS 15 in September 2021, open rates overstate real opens. ## Load the files at the start of each session Claude Code reads a file named `CLAUDE.md` from the working folder when a session starts ([Claude Code memory documentation](https://code.claude.com/docs/en/memory), checked 2026.09.25). Keep `CLAUDE.md` short. List the five files and say which ones to read for which job. For example: for LinkedIn copy, read `brand-voice.md`, the audience file, `campaigns-active.md`, and the LinkedIn section of `channel-rules.md`. A request then carries only the job. That split is the difference between a brief and a prompt, which [a brief is not a prompt](/articles/brief-vs-prompt) explains in more detail. ## Before and after the files Before: "Draft a LinkedIn post about our new feature." The draft is a generic announcement. You paste the voice guide (200 words), the feature brief (150 words), and last week's best post (100 words). You clarify that the audience is enterprise IT directors, not small business owners. The draft gets closer, and you edit for 10 minutes. The next day, for a different angle on the same feature, you start over. After: "Draft a LinkedIn post about the new SSO feature for enterprise IT directors." The assistant reads the voice file, the enterprise audience file, and the feature file. The first draft needs one sentence changed. The next day: "Draft an email version of that post." The assistant applies the email rules, shifts the voice for the channel, and uses the standard call-to-action structure. No context gets pasted. ## A working setup A marketing manager at a business software company sets up the five files in the table. Then: 1. For each copy request, the manager names the audience, the campaign, and the channel. 2. When a campaign ends, the manager updates `campaigns-active.md` with what worked and what failed. 3. When positioning shifts, the manager updates `brand-voice.md` once, and every later draft reflects it. 4. When a draft breaks a rule, the manager adds the rule to the right file, not only to the chat. Step 4 is how the files improve. The guide on [how corrections become part of the system](/articles/corrections-become-system-memory) shows how to record each fix so it holds. The files also become the source of truth for people. Freelancers, new hires, and the assistant read the same files, so one update reaches all three. ## Retire a campaign without losing what it taught When a campaign ends, move its block out of `campaigns-active.md` and into `campaigns-archive.md`. Keep the objective, the pillars, and the results section. Drop the offers and calls to action that no longer run, so the assistant does not reuse an expired offer in a new draft. Add one line at the top of the archived block: the single lesson you want the next campaign to inherit. For the SSO launch above, that line might read: "Question subject lines won; lead with the value proposition in the first paragraph." When you plan the next campaign, ask the assistant to read the archive's lesson lines first. That keeps the results in reach without loading every old campaign into every session. ## Keep voice without freezing claims A voice file can go stale in a quiet way. An approved example from last year may state a feature, a number, or a customer claim that is no longer true. Label old examples as voice only. Keep current claims in the product and campaign files, with dates. The guide to [AI brand memory for content creation](/articles/ai-brand-memory-content-creation) covers this in depth. For research that feeds campaigns, the guide to [AI memory for content research](/articles/ai-memory-content-research) shows how to keep sources and rejected angles between sessions. ## Set the approval boundary The assistant drafts. You publish. It does not post to a social account, send an email campaign, or change ad spend. Every claim in a draft must trace to a product, campaign, or research file. When a draft makes a claim that the files do not support, the assistant must flag it, and you remove it or add the source. The files stay on your computer. The text Claude Code reads goes to Anthropic for processing. Retention and training terms depend on your plan. Keep customer lists and unreleased financial results out of the files. ## Test the files on one campaign Run one test before you rely on the files. 1. Pick a live campaign and one channel. 2. Ask for one draft for each audience file. 3. Check each draft against the voice file, the audience file, and the channel rules. 4. Count your edits, and note each rule that a draft broke. 5. Add each broken rule to the right file, then ask again. The files pass when the second round needs fewer edits than the first and breaks no recorded rule. If a draft still misses, the rule is probably vague. Rewrite it as something a reviewer can check, such as "150 words at most", not "keep it short". You already maintain brand guidelines, campaign briefs, and personas. The test shows whether they exist in a form that the assistant can follow. ---- ```text .|########||. .|########||. .|########||. |##||. .||##|. |##||. .||##|. |##||. .||##|. |#|. .|#|. |#|. .|#|. |#|. .|#|. |#| |#| |#| |#| |#| |#| .#| |#. .#| |#. .#| |#. .#. .#| .#. .#| .#. .#| |#. .#| |#. .#| |#. .#| |# ...... #| |# ...... #| |# ...... #| .# ||#########| #| .# ||#########| #| .# ||#########| #| .#. |######||######|. .#. .#. |######||######|. .#. .#. |######||######|. .#. #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# #. .##|###|##|#|######| .# || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || || |##|#||||||||||||#||#| || # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. # |#||||||||||||||||||||#| #. || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # # .#||||||||||||||||||||||||#| # || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || || ....|||#||||||##|#|||#|#||##||||....|. || #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# #. . ....|# ....#||| ||| .#||| ....#. .# # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. # . ||||#| .#####|| . .#| .#||| ||||# #. .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || .| ||||| #. |#|||||. || #. |#||. .||||| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || || |.... #. ....|#. |. ...|. ....|| || #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# #. .||||||##||||||##||####|||||||#||||||#| .# # .||####|###########################|. # # .||####|###########################|. # # .||####|###########################|. # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#||||||.#.|| # |. ..# #| #|||||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||||| .. |# ## |#| ...#|#|||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#|||#|# .# .#| #| ##|.#..#|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # .#||||||############|######|||||#| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # # |...||#||||||#||||#|#||||||#|||||#||| |.| # #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# #. .. ||||# .|||##|. |#| .|| || .|||#. #| # .# || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || | ...|| ...##| | #| .|. |. ##### .. .| || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || || ||||| || ||||#| . |. |. |#. ||||| |#| || || .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. .# |.....#|....|#.||||.|||##.|#|....||.#||.#. #. #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# #.|||||||#############################| ||| .# || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || || ##||#||#||||||#||#||#||#||##. || # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # # .#|||||||||#||#|||||||||||#| # || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || || |#||||||||||||||||||||||#| || .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. .# |#||||||||||||||||||||#| #. || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || || |#||||||||||||||||||#| || #. .######|#|#########| .# #. .######|#|#########| .# #. .######|#|#########| .# .#. |#####||||#####| .#. .#. |#####||||#####| .#. .#. |#####||||#####| .#. |# ||########|| #. |# ||########|| #. |# ||########|| #. |# ...... #| |# ...... #| |# ...... #| |#. .#| |#. .#| |#. .#| |#. .#. |#. .#. |#. .#. .#| |#. .#| |#. .#| |#. |#| |#| |#| |#| |#| |#| .|#|. .|#|. .|#|. .|#|. .|#|. .|#|. |##||. .||##| |##||. .||##| |##||. .||##| .||########||. .||########||. .||########||. Scale With Search 2026 [scalewithsearch.com](https://scalewithsearch.com) ```