Proto-Persona
Create a lightweight, hypothesis-driven persona in hours from existing research, market signals, and team knowledge — a working customer profile before deeper validation.
Your stakeholder deck has "Manager Mike, 30-45, lives in SF, has a dog" — and that demographic snapshot tells you nothing about whether he'd use your product. A proto-persona is a hypothesis: behavioral, quote-driven, with explicit "assumption — validate" tags. Good enough to align the team in a day. Not so polished you forget to validate it.
Who it's for: PMs aligning teams pre-research, UX leads kicking off design, founders without deep customer knowledge yet, product teams identifying research gaps
Example
"Create a proto-persona for our analytics tool's primary user" → Manager Mike (Director, mid-sized SaaS) + quotes + pains (10 hrs/week in meetings) + trying to (deliver 2 weeks ahead) + decision authority ($10k budget, exec approval above) + [ASSUMPTION—VALIDATE] tags
CLAUDE.md Template
New here? 3-minute setup guide → | Already set up? Copy the template below.
npx ccplaybooks add proto-persona# Proto-Persona
Create a lightweight, hypothesis-driven persona from current research, market signals, and team knowledge. A working customer profile that prevents design-by-committee while acknowledging you don't have all the answers yet.
Not a validated persona. Not demographic data alone. Not permanent.
## Proto vs. Validated
| Proto-Persona | Validated Persona |
|---------------|-------------------|
| Hours/days | Weeks/months |
| Assumptions + limited research | Extensive user research |Get new playbooks like this one
One email a week with new Claude Code workflows. Free, like everything here.
No spam. Unsubscribe anytime.
What This Does
Walks through name → bio → quotes → pains → trying-to-accomplish → goals → decision authority → influencers → beliefs, with [ASSUMPTION—VALIDATE] tags for everything not backed by research. Outputs a hypothesis-driven persona that aligns teams quickly without pretending to be validated research.
Pairs with problem-statement, jobs-to-be-done, positioning-statement, and user-story.
Quick Start
mkdir -p ~/Documents/ProtoPersona
mv ~/Downloads/CLAUDE.md ~/Documents/ProtoPersona/
cd ~/Documents/ProtoPersona
claude
Provide whatever context you have — interview snippets, support tickets, sales call notes, market reports. Claude drafts the persona and tags assumptions for validation.
The Sections
| Section | Purpose |
|---|---|
| Name | Alliterative, memorable |
| Bio & Demographics | Only behavior-relevant details |
| Quotes | Reveal mindset (real or [PLACEHOLDER]) |
| Pains | Specific, related to your product space |
| Trying to accomplish | Observable outcomes |
| Goals | Short + long term, personal + professional |
| Decision Authority | Buying power + approval levels |
| Influencers | Who shapes their decisions |
| Beliefs & Attitudes | Affect adoption |
Tips & Best Practices
- Behavior over demographics. "Active in 5 Slack communities" beats "lives in NYC."
- Tag assumptions.
[ASSUMPTION—VALIDATE]keeps the team honest about what's a guess. - Start with 1-2. Primary + secondary. Adding more before validating creates analysis paralysis.
- Real quotes only. Or mark placeholder. Fake quotes ("I love delight!") create fake empathy.
- Plan to graduate. A proto-persona that's never updated is a fossil. Validate, evolve, or replace.
Common Pitfalls
- Demographic snapshot with no behavioral context
- Treating proto-persona as validated fact
- Building 10 personas before validating any
- Fabricated quotes that sound like marketing copy
- Never updating the persona as research comes in