From the dropdown (1), you can choose one of the prompts defined in Prompt Management, and see the details of this prompt (2). With a click on 'Rewrite article' (3), a popup opens, and the language model starts working.
Alternatively, you can select 'Custom...' from the dropdown (1). This enables you to edit a prompt spontaneously right here by typing your prompt into the text field (2).
The model parameters, the temperature (3) and max tokens (4) can also be adjusted.
The Rewrite button (5) works the same as with a predefined prompt (see paragraph 'Using predefined prompts' above).
If a prompt was defined not simply with "Rewrite Article" as its use case, but with "Rewrite Article (Action Button)", you will see it in the Purple Prompts sidebar as a button. Clicking it will immediately open up the rewriting dialog, so this is especially useful for simple and repeating tasks that are needed on a regular basis.
Once started, the rewriting process gets shown in a popup dialogue. You can see the original post content in text form (1) on the left (this is what the language model works with), and you can watch the AI output being generated (2) on the right side.
Statistics about the rewritten text (3) are displayed at the top. These include measures like the word count of both texts in general, but also data about text preservation in the original and generated text.
Based on of the two available highlighting modes (4), we try to detect important phrases and colour-code them, to give you content confidence at a glance:
Green phrases are detected in the left and right text (e.g. 1, 2, 3 in the screenshot above) and indicate that this information was preserved by the language model.
Grey phrases are detected on the left, but not on the right: The language model might have ignored or omitted information here. E.g. 1 in the screenshot above. In this example, the language model has only taken part of the phrase. As the word 'ursprünglich' wasn't taken into account, the phrase was marked as 'grey' on the left side, but green on the right one. For summarization tasks, this can be desired.
Orange phrases are detected on the right, but not on the left: The language model generated this text, but it was not found in the original text. This might be due to re-phrasing or synonym usage, but it might also indicate cases of hallucinations.
After reviewing the generated text, you can accept it into your article in two different ways:
- Clicking 'Replace' (1) simply replaces the original text with the generated one, while trying to preserve the structure and formatting of the article as it is.
- Clicking 'Append' (2) does not modify the existing blocks of the article, but instead adds the newly generated content to the bottom of the article. We try to preserve structure and formatting here as well, which might lead to duplicated blocks. This option is useful if you want to manually merge the generated text with the original and pick parts from both versions.
The 'Generate again' (3) button restarts the language model and produces a new output. Depending on the prompt text and also especially the temperature setting, the newly generated text might be exactly or nearly the same as before, or completely different.
It is possible to rewrite only parts of a post, rather than rewriting the whole post at once. To do this, simply select text in the block editor. Only the selected blocks (1) will be sent to the language model. The rewrite button (2) will show the number of selected blocks to indicate that a partial rewrite will happen. This also applied to rewrite action buttons.