Skip to main content

Teneo Copilot

The pages in this section provide information about the various aspects of generating content with Teneo Copilot:

Concept

Teneo Copilot allows you to Generate content automatically using Generative AI and Large Language Models (LLMs). Because the text generation is not done in run time, it is possible to benefit from the Generative AI model's creativity and flexibility in a safe way while controlling the content in your solution.

The Generate function is available for the following components:

For all of these components, it can be useful to add a lot of varied content. For example, it is good practice to add several User Intent examples to ensure greater coverage for the specific User Intent. It is also useful to have several answer texts to make your bot's communication more flexible and less repetitive.

Creating many similar texts for all of the mentioned components can turn into a tedious task, especially if just adding several slight variations of the same content. This is where the Generate function comes in handy; it can help you generate accurate data quickly and effortlessly.

note

The option to Generate content with Copilot is only available if LLM Settings are defined for the Account.

How To

Generate User Intent Examples

To automatically generate examples of User Intent, follow these steps:

  1. In the open Flow, first select the trigger or transition to open the left-side panel.
  2. In the panel, go to the User Intent section.
  3. Click Generate.
  4. In the pop-up, select if the examples should be generated from existing examples or a description and also how many examples should be generated.
  5. Click Generate; alternatively click Cancel to abort.
  6. When the data generation has finished, review the examples in the preview and click Apply to add them to the User Intent.
  7. Remember to Save the Flow to preserve the changes.

The new examples are highlighted with a yellow border for easy recognizability.

note

Due to the nature of Generative AI and the removal of duplicates, the actual number of generated results may vary.

Generate Class Examples

To Generate Training and/or Test Examples, follow these steps:

  1. Open the Class Manager.
  2. Next, open an existing class in edit mode either by double-clicking the class in the Class list or by selecting the class and clicking Edit.
  3. If needed, select the Test Examples tab, else leave the selection of the Training Examples and click the Generate button.
  4. In the pop-up, select if the data should be generated from the existing examples or a description and also how many examples should be generated.
  5. Click Generate. Alternatively, click Cancel to abort.
  6. When the data generation is finished, review the examples in the preview and click Apply to add them to the Class.
  7. Remember to Save the Class to preserve the changes.

The new examples are highlighted with a yellow border for easy recognizability.

Generate Output answers

To automatically generate answer variations, follow these steps:

  1. In the open Flow, first select the Output node.
  2. In the Output panel, below Answers, click Generate.
  3. In the pop-up, select if the answers should be generated from existing answers or from a description and also how many answers should be generated.
  4. Click Generate; alternatively click Cancel to abort.
  5. When the data generation has finished, review the answer variations in the preview and click Apply to add them to the Answers.
  6. Remember to Save the Flow to preserve the changes.

The new answers are highlighted with a yellow border for easy recognizability.

note

Due to the nature of Generative AI and the removal of duplicates, the actual number of generated results may vary.

Generate Entity Entries

To automatically generate entries, follow these steps:

  1. First, open the Entity in which entries should be generated.
  2. With the Entity open in edit mode, click Generate in the top ribbon.
  3. In the pop-up, select if the entries should be generated from existing entries or a description and also how many entries should be generated.
  4. Click Generate; alternatively click Cancel to abort.
  5. When the data generation is finished, review the examples in the preview and click Apply to add them to the Entity.
  6. Remember to Save the Entity to preserve the changes.

The new entries are highlighted with a yellow border for easy recognizability.

UI

Generate Icons

IconCommentRelated pages
generate desktopGenerates user intent examples in Teneo Studio Desktop.User Intent
generate answer desktopGenerates Class training and test examples and bot output answers in Teneo Studio Desktop.Class management
Outputs
generate entitiesGenerates Entity entries in Teneo Studio Desktop.Entries
generate class trainingGenerates Class training examples in Teneo Studio Desktop.Training data
generate class testGenerates Class test examples in Teneo Studio Desktop.Test data

Generate Window

generate window desktop

The user can choose to either:

  • Generate more answers or user intent examples from existing ones
  • Generate more answers or user intent examples from a description

The user can also choose the number of examples to generate.

note

Due to the nature of Generative AI and the removal of duplicates, the actual number of generated results may vary.

Tips and Tricks

Optimizing Descriptions

A good description is important for generating quality text; it works as an instruction that tell the LLM what to do and how to create the text. The following tips will help you follow good practices when creating a description:

  • Keep your description as concise as possible.
  • Be specific.
  • Avoid ambiguous language.
  • Avoid jargon.
  • Consider the style and tone of voice.
  • Ensure the level of detail is appropriate.
  • Instruct what to do, instead of what not to do.

If the results are not as desired, there are a couple of things you can do. Consider changing the description, clicking the Generate button again with a larger number of examples, or manually introducing a few examples and and generating more based on them.

note

Please keep in mind that Generative AI is a non-deterministic system, meaning that the text generated will most likely change every time you hit Generate.