Best for
- Teams refreshing messaging from real buyer language
- Marketers with scattered customer research
- Sales and content teams that need shared language evidence
Turn approved language from interviews, calls, reviews, and support into a source-linked phrasebook organized by problem, outcome, objection, trigger, and buying stage.
A reusable voice-of-customer phrasebook with source context, recurrence notes, segment, stage, approved use cases, and language that should not be overgeneralized.
Quick view
Check the audience, core tools, and access before you start the detailed steps.
Best for
Core tools
1 tool used across the workflow.
Access
Preview the open steps, then unlock the remaining implementation details and prompts.
Why this works
Customer language is powerful because it reveals how people frame a problem before marketing cleans it up. A phrasebook becomes useful only when every phrase keeps enough source context to show who said it, in what situation, and whether it recurs.
Expected results
Source context
Every phrase retains segment, stage, and source ID
The team can tell where language came from before reusing it.
Recurrence clarity
Themes show independent source support
Anecdotes are not presented as universal buyer language.
Reusable guidance
Phrases map to specific messaging uses
Research becomes operational without becoming copy-paste marketing.
Step-by-step workflow
The first 2 steps are open. Pro unlocks the remaining steps, copy-paste prompts, pro tips, tool-by-tool setup guidance, and implementation details.
30 min
30 min
List the customer evidence sources you are allowed to use and the fields that must be removed or generalized. Define segments, stages, product areas, and the research questions the phrasebook should answer. Review whether public reviews and private conversations need different attribution or usage treatment.
A source and privacy protocol for the phrasebook.
Useful language does not require storing unnecessary personal details.
45 min
45 min
Provide Claude with approved excerpts and enough context to distinguish buyer, seller, support agent, and internal speaker. Ask it to remove duplicative filler while preserving the original meaning and source identifier. Manually check a sample before large-scale coding. Record the evidence, rationale, and any unresolved issue in the working notes so another operator can review the decision later.
A clean source corpus with speaker and context preserved.
Speaker mistakes can turn company language into fake customer language.
ROLE
You are a voice-of-customer research analyst.
OBJECTIVE
Normalize approved source excerpts for later coding.
INPUTS
{{approved_source_material}}
{{segment_definitions}}
{{privacy_rules}}
OUTPUT
Return source ID, speaker type, segment, stage, cleaned excerpt, and any ambiguity or redaction note.
GUARDRAILS
Do not attribute a phrase to a customer unless the speaker is verified.
Do not invent facts, metrics, quotes, identities, or source access.
UNCERTAINTY
Label missing evidence, weak samples, and conflicts instead of guessing.
HUMAN REVIEW
A named human must approve public claims, outreach, spend changes, customer-facing copy, or system-of-record updates.Pro workflow preview
Previewing 2 of 6 steps
Get the remaining 4 steps, copy-paste prompts, pro tips, tool-by-tool setup guidance, and ongoing workflow and prompt releases.
$9/month
Related workflows
Continue with workflows that share a similar GTM motion, category, or tool stack.
A messaging drift report with source excerpts, severity, intentional versus accidental variation, correction recommendations, owners, and approved exceptions.
A source-linked messaging evidence library with recurring themes, representative language, confidence, recommended uses, and review ownership.
A claim-evidence register with source copy, claim type, proof, evidence age, risk, required qualifier, owner, and correction priority.