Your writing assistant should learn each writer's voice

Writers have strong preferences about tone, structure, and style. pref0 learns these from corrections and ensures the writing assistant matches the writer's voice over time.

What pref0 learns

Real corrections pref0 extracts and compounds across conversations.

"Make it more casual, drop the corporate speak"

tone: casual0.70

"Use shorter paragraphs, max 2-3 sentences"

paragraph_length: short0.70

"No emojis in professional content"

emojis: never_professional0.70

"Active voice, always"

voice: active0.70

"Start with the conclusion, then explain"

structure: conclusion_first0.40

"Use Oxford commas"

punctuation: oxford_comma0.70

Example conversation

user

Write a blog intro about API design

assistant

In the ever-evolving landscape of modern software development, API design has emerged as a cornerstone of successful applications...

user

Way too formal. Make it casual and direct. Start with the point, not a preamble.

pref0 extracts the correction from this conversation and adds it to the user's preference profile. Next time, the agent gets it right.

Benefits

Voice consistency

The assistant learns the writer's tone, structure, and style preferences across all content types.

Fewer rewrites

When the first draft already matches the writer's voice, editing time drops dramatically.

Style guide as preferences

Team-wide writing conventions can be captured and enforced automatically through org preferences.

Per-writer profiles

Each writer gets their own preference profile. The assistant adapts to whoever is writing.

Other use cases

Stop re-correcting. Start learning.

Your users are already teaching your agent what they want. pref0 makes sure the lesson sticks.