Utilizing ChatGPT Effectively: How to Specify Information and Tasks Efficiently

The ChatGPT web interface solely features input fields for submitting queries. As such, it does not provide a dedicated input field for executing actions based on specific text (information).

So how should it be specified?


How to specify informations and tasks

Since the ChatGPT input field doesn’t permit line breaks, utilize a text editor or notepad to craft text in the subsequent format.

Write information to be given to ChatGPT, etc.
It can be multiple lines.

Based on the above content, ________.

After creating the text, paste it into the ChatGPT chat field and request it.

ChatGPT recognizes the information in “Content:”, and executes tasks written in “Task:”.


Introduce some examples.

Create the blog title

To create a title for a blog post using ChatGPT, give the blog body and headings as content and instruct the task to create the title.

For example, I had ChatGPT create the title for the following blog post.

Given the character limit in ChatGPT, it is unfeasible to provide the full text of a lengthy article.

The above article used GPT-4 to give the text of the opening section and the main heading as bullets. The following text was specified as a question to ChatGPT.

This article is written in Japanese, so I wrote them in Japanese.





- 有料版と無料版
- 情報の正確性と付き合い方
- 言語モデルの選択について
- AIに手伝ってもらう


ChatGPT’s response to this was as follows.

ChatGPT体験記: AIとの対話で学ぶ新たな可能性

My ChatGPT Experience: Exploring New Possibilities Through AI Conversations

Both Japanese and English titles were created. Since I had instructed another task in the same thread to create Japanese and English titles, the Japanese-English titles were created without specifying them again here.

ChatGPT demonstrates the provision of contextual responses within the same thread.

Ask for interpretation of the document

This article contains ChatGPT’s response. This is not an issue, as it is a citation abiding by copyright regulations. Still, I checked the terms and conditions just to be sure. I asked if it is allowed to use the content in a blog, giving the relevant part in ChatGPT’s Terms of Use as of April 24, 2023 as the content.

(a) Your Content. You may provide input to the Services (“Input”), and receive output generated and returned by the Services based on the Input (“Output”). Input and Output are collectively “Content.” As between the parties and to the extent permitted by applicable law, you own all Input. Subject to your compliance with these Terms, OpenAI hereby assigns to you all its right, title and interest in and to Output. This means you can use Content for any purpose, including commercial purposes such as sale or publication, if you comply with these Terms. OpenAI may use Content to provide and maintain the Services, comply with applicable law, and enforce our policies. You are responsible for Content, including for ensuring that it does not violate any applicable law or these Terms.

Answer whether this content allows users to use the output for blogging or other purposes.

GPT-3.5 was used at this time. The following response was received.

Yes, according to the content, users are allowed to use the output generated by the Services for any purpose, including commercial purposes such as blogging or publication, as long as they comply with the terms of service. However, users are responsible for ensuring that the content does not violate any applicable law or the terms of service.

I interpreted it as fine myself, but to be sure, I asked ChatGPT to interpret it as well, and they confirmed that it was fine.


Structuring even straightforward text in this manner ensure that ChatGPT comprehends it. You can apply this to convey the information you want to give and what you want it to do. This way of writing can be applied in many ways.

Also, ChatGPT itself only has information through September 2021 at the time of this writing. However, by specifying the content this way, it is possible to give the latest information after that date and ask for interpretation.


Authored Books

  • URLをコピーしました!
  • URLをコピーしました!


Akira Hayashi (林 晃)のアバター Akira Hayashi (林 晃) Representative(代表), Software Engineer(ソフトウェアエンジニア)

アールケー開発代表。Appleプラットフォーム向けの開発を専門としているソフトウェアエンジニア。ソフトウェアの受託開発、技術書執筆、技術指導・セミナー講師。note, Medium, LinkedIn
Representative of RK Kaihatsu. Software Engineer Specializing in Development for the Apple Platform. Specializing in contract software development, technical writing, and serving as a tech workshop lecturer. note, Medium, LinkedIn