Guideline Template

[Company Name] Brand Voice Guidelines

Generation Metadata

• Created: [date]
• Version: [N] (incremented from previous if updating)
• Replaces: [previous version date, if applicable]
• Sources: [list of documents and/or conversations analyzed]
• Documents processed: [N]
• Conversations analyzed: [N]
• Discovery report used: [Yes/No]
• Overall confidence: [High/Medium/Low]

Executive Summary

[2-3 paragraph overview of the brand voice. What makes this brand distinctive? What is the core personality? How should content feel to the reader?]

We Are / We Are Not

The foundational brand identity anchor. Voice is constant — it doesn’t change by channel or audience.

Voice Attributes Detail

For each “We Are” attribute:

[Attribute 1]: [Name]

• What it means: [detailed description]
• How it shows up: [specific behaviors in content]
• What to avoid: [the “We Are Not” counterpart, expanded]
• Evidence: [source quote or pattern, with citation]
• Confidence: [High/Medium/Low]

[Repeat for each attribute]

Brand Personality

• Archetype: [e.g., “The Expert Friend” — technically deep but never condescending]
• If our brand were a person: [brief personality sketch]
• Core values expressed in voice: [list]

Messaging Framework

Primary Value Proposition

[Core value statement — one sentence]

Variations observed:

• “[Variation 1]” (Source: [doc])
• “[Variation 2]” (Source: [doc])

Key Message Pillars

1. [Pillar Name]

   • Core idea: [one sentence]
   • When to use: [contexts]
   • Example phrasing: “[quote]”
   • Frequency in conversations: [X]% (if transcript data available)
   • Effectiveness: [High/Medium/Low] (if outcome data available)

2. [Pillar Name] [same format]

3. [Pillar Name] [same format]

Competitive Positioning

• vs. [Competitor A]: [how we differentiate]
• vs. [Competitor B]: [how we differentiate]
• vs. Status Quo: [why change is worth it]

Tone-by-Context Matrix

Voice is constant. Tone flexes by context. These three dimensions adjust:

Context-Specific Guidelines

Cold Outreach

• Overall tone: [description]
• Opening approach: [what works]
• Do’s: [list]
• Don’ts: [list]
• Example: “[sample opening line]”

Discovery Calls

[same structure]

Proposals & RFPs

[same structure]

Social Media

[same structure]

Terminology Guide

Must-Use Terms

Preferred Terms

Avoid These Terms

Never-Use Terms

Language That Works

Ranked by effectiveness (from conversation analysis, if available):

Top Phrases

1. “[Phrase]” — Context: [when to use], Why it works: [analysis]
2. “[Phrase]” — Context: [when to use], Why it works: [analysis]

Questions That Engage

1. “[Question]” — Leads to: [typical outcome]
2. “[Question]” — Leads to: [typical outcome]

Objection Handling Patterns

1. Objection: “[common objection]” Response pattern: “[how top performers respond]” Why it works: [analysis]

Language to Avoid

Anti-Patterns

1. “[Phrase/pattern]” — Problem: [what happens], Better: “[alternative]”
2. “[Phrase/pattern]” — Problem: [what happens], Better: “[alternative]”

Content Examples

Excellent Examples

[Full example with annotation explaining what makes it on-brand]

Examples to Avoid

[Full example with annotation explaining what’s off-brand and how to fix it]

Confidence Scores

Open Questions for Team Discussion

High Priority (blocks guideline completion)

1. [Question Title]
   • What was found: [description of ambiguity]
   • Agent recommendation: [suggested resolution]
   • Need from you: [specific decision]

Medium Priority (improves quality)

[same format]

Low Priority (nice to have)

[same format]

Data Gaps & Recommendations

[What’s missing and specific actions to fill gaps]

• Not done: [Gap 1]: [recommendation to fill it]
• Not done: [Gap 2]: [recommendation to fill it]

Appendix: Sources

Template Usage Notes

• Omit sections with no data rather than including empty placeholders
• If transcript data is unavailable, omit the “Language That Works” and “Language to Avoid” sections
• If only documents are available (no transcripts), note this in metadata
• “We Are / We Are Not” table should have minimum 4 rows, ideally 5-7
• Tone matrix should cover at minimum: cold outreach, proposals, social media
• All examples must have source attribution
• Every open question must include an agent recommendation

Nearby

• PreviousReference Confidence Scoring