Prompt Library

Prompt Library offers a central hub to store, organize, and share prompts across the team.

With TypingMind, you can easily access prompts within workflows to speed up development and creative tasks for your team.

Why build your prompt library on TypingMind?

TypingMind offers a flexible option to create your own prompt library where you can:

• Create exclusive built-in prompts for your team members so they can quickly access the resources without manually creating them from the chat interface.
• Control which groups of users can use the prompts

Step by step to build prompt library on TypingMind

1. Build your Prompt Library

• Go to Prompts Library
• Click “Add Prompt”

Your created prompts will be displayed on the end-user interface as follows:

2. Control user access to certain prompts

User access will be controlled using tags. Each user can be given a tag, and you can use these tags to set access permissions for each prompt.

Here’s how:

Step 1: Assign tags for users

Follow these steps to assign tags to your members:

1. Log into your chat instance's Admin Panel.
2. Navigate to the “Members” section.
3. Identify the member you wish to assign tags to and click on that member’s email
4. Enter the tag you want to assign them

Please note: You can assign multiple tags to each member. Learn more about Set tags for members

Step 2: Set tags for each prompt

Here’s how to set tags for each prompt:

1. Navigate the Prompts Library menu
2. Click “Add Promp" to add new prompt or “Edit” the existing prompt
3. Scroll down to the Visibility section and select “Visible only to users with tags” from the drop-down list
4. The User tags section shown up, enter tags that you have just set for specific members at step 1

Example: if you want only members with the "marketing" tag to access the Content Improver prompt, add the "marketing" tag to that prompt.

Here’s how the members with the “marketing” tag will see on the chat interface:

Best practices for creating an effective prompt

Here are some tips to help you craft a better prompt:

1. Be specific: the more specific your prompt, the better. If you want a story, specify the genre, characters, and setting. If you want information, specify the kind of information and its context.
2. Instruction: instruct the model on the format you want the output in. For instance, if you want a list, you can start your prompt with "List of...".
3. Temperature: this isn't part of the prompt, but it's a setting you can adjust. A higher temperature like 0.8 makes the output more random, while a lower temperature like 0.2 makes it more focused and deterministic.
4. Max tokens: another setting rather than a part of the prompt, but it's worth considering. This limits the length of the model's response. To ensure a smooth conversation, consider using the appropriate model if the prompt is too long.
5. Iterative refinement: don't expect to get the perfect response on your first try. Experiment with different prompts and settings, and iterate based on the outputs you get.