MoFlo Shipped: Dec 2025

Designing a persona system for consistent AI content

People retyped their brand voice into every prompt. Half skipped the persona builder I shipped for it, so version two learned from the retyping instead.

Founding product designer 4 weeks
2.3× persona reuse across sessions
34% fewer tone retypes
21% fewer redos over tone
First month, against sessions before launch.
Mine
  • Product strategy
  • User research
  • Interaction design
  • UI design
Shared
  • AI behaviorwith eng
  • Rolloutwith lead dev
Not mine
  • Model and prompt engineering

The situation

AI is flexible. Brands are not.

MoFlo could generate captions and visuals well. What it couldn't do was sound like the same company twice.

The user message that triggered the investigation
The message that gave the problem a name.

Usage data agreed: high draft generation, low direct publish, frequent edits before scheduling.

The AI wasn't reducing effort. It was relocating it.

Research

Adjectives. Nobody actually thinks in them.

Asked about brand voice, people talked about audience and intent.

“We're premium but approachable. I don't know how to explain that to a model.”
“I want it to sound like us, not like AI.”
“Sometimes it's too salesy. That's not our brand.”
“It forgets who we're talking to.”

Asking for tone was the wrong question.

First attempt

I shipped a builder. Adoption did not follow it.

Version one had people define their brand up front, then apply it at generation.

1. Create
Define tone, audience and writing rules up front.
Created at least one persona38%
Ever reused one17%

Reuse was the point.

Skipped persona selection entirely50%
Still typed tone into the prompt60%
Four weeks after launch. Tone-mismatch regenerations stayed high.
Caveat:

Setup up front, payoff invisible: the rules applied silently.

The rethink

Stop asking. Offer an identity, then let them adjust it.

Rethinking the persona model
Where each option puts the effort: on the user or the system.

The goal was never to eliminate prompting. It was to eliminate repetition.

Version oneTone typed 1×
MonTone
Version twoTone typed 1×
NeighbourlyTone
MonTone
Four sessions, one tone instruction.

What shipped

Identity moved down. It now sits where the work happens.

Personas start from an archetype and get refined.
Active persona visibility during generation
The active persona stays visible, its rules editable inline.
The prompt-to-persona bridge: a typed tone rule, offered to the persona.

The challenge

Wrong twice. Nobody reads the third suggestion.

The bridge took the longest: "detect a tone rule and offer to save it" hides three decisions.

Today Neighbourly
Tuesday specialless salesy
1Only standing rules count
Keep “less salesy”?AddNot now
2Asked after the draft
Next session Neighbourly
3Already on the persona
A dismissed rule is never offered again.

I defined what a false positive is: the product claiming to know someone's brand better than they do.

Version one asked for setup. Version two asks for confirmation.

Impact

One month in. What the numbers actually did.

18% rise in direct publish after the first draft
No personaSame briefRecreation
Your businessInstagram · just now

🎉 BIG NEWS! We're now OPEN ON WEEKENDS! 🎉 That's right, you asked, we listened! Book your appointment today and experience the difference. Don't miss out! Link in bio 👇 #weekendvibes #bookNow #smallbusiness

We're open Saturdays and Sundays starting this weekend. Same team, same hours you're used to on weekdays. If a weekday appointment has been the thing standing in your way, this is the fix. Booking link below.

The first could be any business. The second is theirs.

Reflection

Absorb the habit. Correcting it only loses the person.

AI features rarely fail for lack of capability. They fail when they misalign with what people already do.

Reduce repetition, not control. Make the reasoning visible; invisible correctness earns no trust.

Role
Founding Product Designer
Team
Founding Product Designer (Me), CTO, Lead Developer
Timeline
4 Weeks
Tools
Figma (Design, Make, Jam), Claude Code, Lottielab, v0