Q&A Intents
Last updated
Last updated
Q&A intents are deprecated, and will be phased out.
You can upgrade your existing Q&A intents to LLM intents via the "Build - AI" section in the Studio.
Click the "Upgrade to LLM" button in the "Build - AI" section to use the new LLM intents.
They will use the latest GPT models to use intent classification. Not only will this yield better results, it also removes the need to train the app for any new intents, making your publish cycle much shorter.
If you want to know more on LLM intents, visit the AI page in the manuals. The documentation on the legacy Q&A intents can be found below.
Only the Producer and the Developer roles are allowed to manage intents.
When automating human conversation, understanding of the user's intent is key. Giving the right answer to the wrong question is biggest mistake made by bots today, hence identifying the intention of the user message is the biggest challenge.
The DialoX platform offers a special section to manage all the intents that are relevant for your bot. Intents can be organized in multiple files. However, most bots only offer one file called "Intents".
The system differentiates between global and local intents. The local intents can be recognized by the circle icon in front of the row, see billing, sales and support in the above example. However, local intents are currently only available to selected customers by means of a feature flag.
Local intents are introduced to make their recognition within a specific context much better while needing less training phrases. This is possible due to the use of the LLM AI technology called chat GPT.
You can add a new intent by clicking on the Add intent button. Now you can specify the label and description of the intent and start adding training phrases.
Enable 'only use locally' when you are using the intent only to trigger the next link in an Ask or Prompt node.
Disable 'only use locally' when you are using the intent to trigger outside an ASK or PROMPT node. These only make sense for usage in Intent triggers. Because these intents can be triggered without knowing the exact context upfront, these intents need more careful training. The following hints can give some guidance:
Using complete sentences works better than single words (unless intents are only used for topic classification, as in the example above)
Try to have roughly the same amount of phrases per intent
The optimum amount of phrases per intent is roughly 20
Try to reuse important words in multiple sentences
Toggle Only use locally when you need to recognize a user intent within the context of a specific dialog or flow. If you want this intent to be able to be triggered anywhere in your bot you need to keep it global (so toggled off).
When you make sure the description is clear, you will only need a couple of training phrases (examples). For clear intents one might already be enough, like in the example above.
Local intents are introduced to make their recognition within a specific context much better while needing less training phrases. This is possible due to the use of the LLM AI technology called chat GPT.
Intent training can be quite a tedious process. The AI will use its algorithm to calculate which intent to classify for any given user utterance. The way that is done by the AI remains a black box. This often requires quite some tweaking of training sentences before the required behaviour is achieved.
It is possible to test the classification of intents by running your bot and see if it behaves as expected. Another, quicker way is to test the intent classification within the training section of the platform.
By typing a sentence (user utterance) in the Sentence field in the top of the side panel on the right, the system will automatically run it against the AI.
In the above example we are testing the global intent for opening hours.
For local intents, you need to specify the context by adding the intents you want to test the utterance against in the Context field below. This field is however only available behind a feature flag so it can be tested by a selected group of customers first.
Title: The title of an intent is a concise and clear label that defines the purpose of the intent. It should be easily understandable and descriptive of the user action or goal it represents. For example, a title like "Book a Meeting" or "Check Order Status" should clearly reflect the user’s intended action.
Description: The description provides additional context or details about the intent's purpose. It serves as a brief explanation of what the intent is designed to accomplish and helps maintain clarity when managing multiple intents. A good description outlines the specific scenario or use case that the intent addresses, ensuring that the intent's functionality is easily understood by others working on the project.
This means you will be able to instruct and automate via your Intents using only a comprehensive title & description which allows you to store your Intents in a more efficient way.
This description highlights the importance of the title and description in effectively organizing and managing intents within the NLP Intent UI.
