Use with careMake content

A practical method for your work

Taste Calibration Pattern

Teach the model your taste with examples before asking it to create.

Start with this template →View original source ↗
Original sourceAnthropic: use examplesChecked 2026-07-07
Use this whenWriting style · Design feedback · Brand voice
You will getA reusable way to start the work

Core idea

Taste is hard to describe as rules. Showing liked and disliked examples gives the model a target distribution for style, density, rhythm, and visual preference.

Why it works

Examples are often stronger than adjectives like premium or clean. They reduce ambiguity and make subjective work more repeatable.

Weak

Write it in a premium tone.

Better

Here are 3 examples I like and 2 I dislike. Extract the style rules first, ask one question if needed, then rewrite using those rules.

Customize it

Liked examplesDisliked examplesExtracted rulesTolerance for deviation

Working template

Goal: [what I am trying to accomplish] Context: [background, audience, constraints] Use this pattern: Taste Calibration Pattern Variables: Liked examples, Disliked examples, Extracted rules, Tolerance for deviation Return: [exact output format] Before finalizing: state limits and one improvement

Operating recipe

  1. Start with the weak version so you know what problem you are fixing.
  2. Add the missing variables instead of making the instruction longer randomly.
  3. Ask the model to follow the output contract exactly once.
  4. Review the first answer against the checklist below.
  5. Save the improved version as your reusable pattern.

Quality checklist

  • Did I give the model the real goal, not just the task?
  • Did I define the output shape before asking for the answer?
  • Did I include examples, constraints, or a quality bar?
  • Did I ask for limits, uncertainty, or failure cases?
  • Can I reuse this as a pattern next time?

Model notes

Claude

Strong for long context, critique, and structured writing. Give it clear sections and examples.

ChatGPT

Strong for fast iteration and everyday templates. Be explicit about output format and assumptions.

Gemini

Useful for broad synthesis and Google-adjacent research. Keep source requirements explicit.

Limits

Examples can overfit. Refresh them when the brand or task changes.

Read next

Context Pack PatternGive AI the work environment before asking for serious output.Role + Rubric PatternGet better critique by defining the judge and the scoring criteria.Ask Before Answer PatternUse clarification only when missing context changes the answer.
Free downloads

Turn this into a reusable workflow.

Get the Prompt Debugging Checklist and Solo Builder AI Setup Pack as language-specific .md files.

Open free downloadsBack to library →