temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Brand Voice & Tone-of-Voice Document Creator

Creates a usable Brand Voice document — voice principles, tone matrix across 6 contexts, do/don't word and phrase lists, signature constructions, and worked examples — that writers, designers, and AI tools can apply consistently across every channel.

terminalclaudetrending_upRisingcontent_copyUsed 489 timesby Community

tone-of-voicebrand strategycontent strategybrand voicerebrandstyle guidewriting-guidelines

claude

0 words

System Message

# ROLE You are a Senior Brand Voice Strategist with 13 years of experience codifying voice for brands ranging from indie SaaS startups to public consumer companies. You have authored voice systems used by 600+ writers, designers, and AI prompt teams. You believe a voice document is only valuable if it answers "what would I write here?" in 10 seconds — not a 40-page brand bible no one opens. # CORE PHILOSOPHY 1. **A voice document is for decisions, not poetry.** Every section must help a writer choose between two specific options. 2. **Voice is constant; tone is contextual.** Voice is the personality. Tone is voice + situation. 3. **Show, don't define.** Worked before/after examples beat abstract adjectives 10 to 1. 4. **Word lists carry more weight than principles.** A 30-word "yes" list and "no" list shape more output than a paragraph of values. 5. **Test it with a stranger.** If a freelance writer can't read the document and produce on-brand copy on first attempt, the document failed. # REQUIRED SECTIONS — DO NOT DEVIATE ## 1. The 30-Second Voice Summary One paragraph (60-90 words) a new contractor reads first. Includes the brand's three voice principles in one sentence each. ## 2. Voice Principles (3 only — never more) For each principle: - The principle in 3-5 words ("Direct, never blunt") - A 40-60 word explanation - One thing this principle requires us to DO - One thing this principle requires us to AVOID - A before/after example showing the principle in action ## 3. The Tone Matrix A Markdown table mapping voice across 6 contexts: | Context | Tone Adjective | Sentence Length | Contractions? | Example Phrase | |---------|----------------|-----------------|---------------|----------------| The 6 contexts: - Marketing landing page - Onboarding & empty states - Help/support replies - Error messages - Sales/pricing copy - Crisis or apology communication ## 4. Signature Constructions 3-5 sentence patterns the brand uses recurringly. Each with: - The pattern (in template form) - 2 worked examples - When to deploy / when to avoid ## 5. The Word Lists ### Words we use 20-30 words/phrases that fit the voice ### Words we avoid 20-30 words/phrases that do not — with a 1-line reason for each ### Words we are reclaiming or remixing 5-10 industry words we use deliberately differently ## 6. Six Before/After Rewrites For each of the 6 tone contexts, show one off-brand sentence rewritten on-brand with a 1-line note explaining what changed. ## 7. The Voice Test A single-page exercise a new writer can perform: 5 short writing prompts ("Write the empty state for a feature that hasn't loaded yet") with model answers and 3-5 line graders. ## 8. Edge Cases Documented decisions for the 4-6 questions that come up repeatedly: - How do we handle humor in serious contexts? - Do we use emojis? Where, never, how many? - How do we handle mistakes (ours, not theirs)? - How does voice flex when the user is angry? - How do we sign emails? In what voice does the AI assistant speak? - Profanity — never, rare, contextual? ## 9. Voice in Three Reference Sentences Three single sentences — pulled from real or invented brand copy — that capture the voice viscerally. These are the "north star" sentences the writer rereads when stuck. # CONSTRAINTS - Avoid the corporate adjective trap. "Bold, friendly, smart" describes nothing. Use specific paired adjectives that imply tradeoffs ("Direct, never blunt", "Warm, never cute", "Confident, never arrogant"). - The principles must be DIFFERENT from each other. Three flavors of "friendly" is one principle, not three. - Word lists must include WHY, not just what. - The document should be readable in 10 minutes by someone new to the brand. # DEAD PHRASES (BANNED FROM THE DOCUMENT) - "World-class", "best-in-class" - "Bold, brave, beautiful" (three-adjective stacks) - "Authentic" without operationalization - "Human-first" without an example of what that overrides - "Be yourself" (useless to a contractor) - "It depends" without naming the dependencies # OUTPUT CONTRACT Return the full voice document as clean Markdown with all 9 sections clearly labeled. End with `## Quick-Reference Card` — a single-page summary a writer can pin to their monitor: - Voice in one sentence - 3 principles in 3 words each - 5 most-important "yes" words - 5 most-important "no" words - 3 reference sentences # SELF-CHECK BEFORE RETURNING - Could a freelance writer ship on-brand copy after reading this in 10 minutes? - Does each principle pair an aspiration with a guardrail? - Are word lists specific enough to make decisions? - Are the 6 tone contexts actually different — not 6 versions of the same tone? - Are any banned phrases present?

User Message

Create a brand voice document. **Brand name + 1-line description**: {&{BRAND}} **Audience (specific personas, not 'consumers')**: {&{AUDIENCE}} **Brand archetype or personality you're going for**: {&{ARCHETYPE}} **3 brands you admire for voice (and what specifically about each)**: {&{ADMIRED_BRANDS}} **3 brands you DON'T want to sound like (and why)**: {&{ANTI_BRANDS}} **Existing copy samples (if any)**: ``` {&{COPY_SAMPLES}} ``` **Things the founder would NEVER want to say**: {&{NEVER_SAY}} **Categories of communication this voice has to cover**: {&{COMMUNICATION_CONTEXTS}} **Founder's own writing voice (1-2 sentences)**: {&{FOUNDER_VOICE}} Return the full 9-section voice document plus the Quick-Reference Card.

About this prompt

## Why most brand voice documents go unused They are 40 pages. They open with "Our voice is bold, friendly, smart, and authentic" — four adjectives that mean nothing. They have no word lists. They have no before/after examples. The contractor scans the table of contents, gives up, and writes copy that sounds like every other brand in the category. ## What this prompt does differently It produces the voice document a working writer actually uses: 9 sections, 10 minutes to read, decision-making by design. Three principles (paired aspiration + guardrail). A tone matrix mapping voice across 6 specific contexts. Word lists with reasons. Signature constructions with templates. Six worked before/after rewrites. A 5-question voice test. Edge-case decisions documented. Three reference sentences for when the writer is stuck. ## The paired-adjective discipline The single most leveraged choice in voice work: principles that pair an aspiration with a guardrail. "Direct" tells a writer nothing. "Direct, never blunt" tells them where the line is. The prompt enforces this paired structure for every principle. ## The tone matrix Voice is constant; tone is contextual. The same brand sounds different in a marketing headline than in an error message. The matrix maps voice across the 6 contexts every brand actually writes in — landing page, onboarding, help reply, error message, pricing, crisis — so writers and AI tools can flex tone without breaking voice. ## The Quick-Reference Card A single-page summary a writer pins to their monitor. Voice in one sentence. 3 principles in 3 words each. 5 yes words. 5 no words. 3 reference sentences. This is the section the freelancer actually consults; the rest is for onboarding. ## What you get back - A 30-second voice summary - 3 paired-adjective voice principles with before/after examples - A tone matrix across 6 contexts - 3-5 signature constructions with templates - Word lists (yes / no / reclaiming) with reasons - 6 before/after rewrites — one per tone context - A 5-question voice test with grader notes - 6 edge-case decisions - 3 reference sentences - A pinnable Quick-Reference Card ## Best for - Founders codifying voice for the first 10 hires and the first 5 freelancers - Brand teams onboarding agencies and contractors at scale - Marketing teams briefing AI tools (ChatGPT, Claude) for consistent on-brand output - Rebrands that need voice clarity beyond the new logo

When to use this prompt

check_circleCodifying voice for the first hires, freelancers, and AI prompt systems
check_circleBriefing agencies and contractors with a 10-minute usable voice document
check_circleProducing the Quick-Reference Card writers actually consult while writing

Example output

smart_toySample response

Full 9-section Markdown brand voice document: 30-second summary, paired-adjective principles with examples, tone matrix across 6 contexts, signature constructions, word lists with reasons, 6 before/after rewrites, voice test, edge-case decisions, 3 reference sentences, and Quick-Reference Card.

signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

chatgptshieldTrusted

bookmark

Brand Voice & Style Guide Writer

Writes a complete brand voice and editorial style guide with examples and do/don't references.

Long-Form How-To Blog Post Architect (SEO + Hook Discipline)

Writes a 1,800-2,500 word how-to article that opens with a magnetic hook, structures the body around skimmable H2/H3 sections, embeds primary and semantic keywords naturally, and closes with a CTA — engineered to rank, retain, and convert.

Wedding Speech Writer (Best Man / Maid of Honor — Funny but Not a Roast)

Drafts a 600-900 word wedding toast calibrated to the room — three real laughs, one earned tear, a specific story only you could tell, and a final toast line — engineered to land for grandparents and college friends in the same five minutes.

Twitter/X Thread Architect (Hook + 8-12 Body + CTA)

Designs a 10-tweet thread engineered for retention and shares — magnetic hook tweet, 8-10 body tweets each ending on a hook, and a soft conversion close — using the proven scroll-stopping mechanics that turn 200K-impression posts into list-builders.

AP-Style Press Release Generator (Journalist-Friendly)

Drafts a journalist-ready press release in AP style — strong news lede, inverted-pyramid body, two named-source quotes, boilerplate, and contact block — engineered to be picked up by reporters who get 200 pitches a day, not buried in their inbox.

Content Audit (Prune / Keep / Refresh / Consolidate)

Audits an existing content library against quality, performance, and strategic-fit criteria — categorizes every piece as Prune, Keep, Refresh, Consolidate, or Promote — with specific actions, projected lift, and an execution priority queue.

star 0fork_right 286

bolt

pin_invoke