← All examples
Case

Every text in the right tone of voice

In 2021 the website of HAN University of Applied Sciences moved to a new brand style. It went fast, too fast to check whether every page matched the new tone of voice. That left us with this:

The problem

Why one editor couldn't keep up

The brand voice depended on one person's capacity. She had to find pages by hand and read each one, and a single text took 15 to 20 minutes to read, assess and rewrite. Meanwhile the other editors kept writing, and their texts were only corrected after the fact.

BeforeOne editor, checking by hand, page by page, 15 to 20 minutes per text
After80+ editors check their own text in 2 to 3 minutes, while they write
The result

What it delivered

Tone Tara is a custom GPT: a chatbot in ChatGPT that works with our own tone of voice knowledge. She checks a text against the brand voice and rewrites it. Editors paste their text and get it back in the right tone. She's been used thousands of times by more than 80 editors, and the editor who used to check every page now manages Tara.

Demo

See it work

Tone Tara's start screen in ChatGPT with four conversation starters: analyse my text, rewrite my text, how does the brand voice work, check my text for outdated words
Tara's start screen in ChatGPT, in Dutch. Four ways to begin.
Tara asks who the text is for and offers four audiences to choose from before she reviews the web page
Tara first asks who the text is for. The audience decides which parts of the brand voice get the most weight.
Tara's scores for the four directions of the brand voice: Curious 8 out of 10, Driven 6, Human 8, Reliable 7, each with one line of explanation
A score for each of the four directions of the brand voice, with the reason in one line.
The process

How Tara works

One of Tara's improvements: the original Dutch sentence, what the issue is, and her suggested rewrite
One of the improvements: the original sentence, what is wrong with it, and Tara's rewrite.
  1. Paste your text. A web page, a news item, anything you wrote.
  2. Say who it's for. Tara asks. She knows 12 audience types, each with its own accent on the brand voice.
  3. Tara scores it. An overall score out of 10 and one for each of the four directions of the brand voice: curious, driven, human and reliable. Plus specific suggestions for what to change.
  4. She rewrites it. In the right tone for that audience, with the word list applied.
  5. You review it. Paste, review, done.
Behind the scenes

How we built it

It started with a question: could we score all 20,000 pages automatically? I wrote a prompt that compared each page with our tone of voice guidelines and gave it a score from 0 (poor) to 10 (perfect) in a Google Sheet. Months of reading became a priority list.

That helped one editor, and it did nothing for the 80 others. So she and I turned the prompt into a chatbot, together. She brought the examples and judged the quality. I worked out how to teach it to the AI.

The first version was mediocre. It took five versions, over several months.

  1. The guidelines as a PDF. Tara followed the rules loosely, like a new hire who read the manual once.
  2. The same guidelines as a structured text file. More precise output.
  3. Good examples. Tara now had a reference for what right looks like.
  4. Bad examples with the editor's rewrites. The biggest jump in quality: Tara could see the gap between wrong and right, and how to close it.
  5. A word list. The words we don't use, each paired with the word we prefer.

The AI platform stayed the same through all five. Every improvement came from better knowledge. We're now rebuilding Tara so she also works with other AI models, next to ChatGPT. Tara follows the five steps of my BUILD framework.

Three choices made the difference.

The human side

What stays with people

Tara checks the tone. Every editor still reviews what comes back. What good brand voice looks like came from the responsible editor, and she manages Tara now: seven knowledge files, kept up to date, with the feedback from editors going back in.

Which check in your team still depends on one person's time?

← See all examples
A check that waits for one person?

Let's build the helper for it

In a workshop you pick one task from your own work and leave with a working AI helper for it. No technical background needed.

Get in touch