Post from finished material
Insert an article, case or news - get a post for a specific platform: one thought, your own angle and the first line that works under the fold.
Retelling an article on a social network doesn’t work: it repeats the source and doesn’t give you a reason to read it. The tool takes the material, selects one thought from it for the selected area and adds an angle, and the first line is written with the expectation that the rest is hidden under the fold.
AI answers are free, but limited by the overall site limit. If the limit is reached, come back later: repeated clicks will not speed up the response.
Retelling does not give a reason to read you specifically
The most common way to make a post from an article is to compress it. The result is correct text that repeats the source and adds nothing. The reader who is interested in the topic will go to the original source, but the rest are uninterested and in a compressed form.
The reverse movement works: take one thought from the material and expand it with your own experience. Then the source becomes the reason, and the content is what is not in the source. This is precisely why they subscribe to a specific author.
The first line is written separately, because in the tape the rest is hidden under the fold. It should work in isolation from the text: not “today I want to tell you,” but immediately a statement or observation for the sake of which the post is being deployed.
And the last thing: several publications are published from one material, not just one. Therefore, the answer always contains two more abstract posts - so that a good source is not consumed at once.
What the tool intentionally doesn't do
Does not insert numbers, deadlines, benchmarks and names of companies that did not exist in your input. If the output requires a number that you did not provide, in the answer will be marked “to clarify” rather than a plausible number. This limitation is worth in the system prompt and works against the main property of language models: It’s difficult to complete what’s missing.
The request text is sent to the AI provider, and the response is returned to the browser. The site does not save these texts in the database. To limit expenses separately the number of requests and the anonymized connection identifier are taken into account. If the free limit is reached, the tool will offer to come back later.