Teneo Developers

Detailed information

Try Out chat details

Input

In the Input section of the advanced Try Out window, the user is able to see information related to the tested input; the provided details - related to the input - are divided into different sections:

  • The top of the section displays the given input

  • Classifications details information about the top predicted Class Intents
    Teneo Learn trains a machine learning model in the solution when Classes and training data are added in the Class Manager; the machine learning model is used at runtime and in Try Out in the Teneo Predict Input Processor to determine to which of the Classes a user input is most likely related.
    For each input, Teneo Predict generates a top-rated annotation that is tagged as the top intent (i.e. with the suffix TOP_INTENT) and also creates annotations for the most important Classes for the particular input (with the scheme <CLASS_NAME.INTENT). Teneo Predict generates a maximum of 5 top Intent Classes. For more information about the creation of classification annotations, please see here.

Although the classification is displayed in the Input section, the triggered Flow Trigger might not contain the displayed Class as a Match Requirement, the information related to the actually triggered Trigger is displayed under thePath.

  • Annotations details the produced annotations
    Linked together with the above bullet point, here the user finds information about the created annotations for the given user input, i.e. the annotations created by Teneo Predict as well as annotations by other Input Processors or by the Teneo Engine (such as System and Standard annotations).
    Hoovering over a displayed annotation provides the user with more information about the confidence score, order, and if it is a Standard annotation.

  • Processing details information about, for example, initialized Variables and changed session variables, Input Processor results, as well as information related to Global Scripts present in the solution.

Path

The Path section provides information about the different items that crossed Engine's path while processing a request.

Path section view

The Path can contain one or more of the below information types or events, depending on the path taken from the user input is given and to the final output is provided, furthermore, these are expandable (clicking the arrow icon in the far right side) and allows the user to navigate directly to the location in the solution by clicking the ID.

  • Blue colored edge: Trigger Match Requirements and Trigger elements
    • Match (Requirements)
      Specifies which Match Requirement(s) were matched by the given user input, e.g. Class, Context, Condition, Language Object, etc.
      Read more about the different Match Requirement types here
    • Trigger
      Displays details related to the triggered Intent Trigger
  • Yellow colored edge: Transition Match Requirements and Transition elements
    • Match (Requirements)
      Specifies which Match Requirement(s) were matched by the given user input
      Read more about the different Match Requirement types here
    • Transition
      Details information related to the Transition such as the Name and vertex ID, or if the Transition is input consuming
  • Green colored edge: Other elements that occur within the Flow context
    • Raise Flow
      Provides details of the Flow the triggered Intent Trigger belongs to
    • Junction
      Provides details of Junction's ID
    • Output
      Specifies details related to the Output node, such as Revisits, Emotion, Answer ID, URL, and Answer Text
    • Drop Flow
      Specifies details related to the Flow being dropped, including if the Flow was aborted or stuck

The data available in the Path section can be accessed by scripting in order to send/receive messages from the Teneo Engine; for more details please click here.

Output

The Output section gives information related to the Output, such as the answer text, emotion, and when applicable, the URL and/or Output parameters.

State

Information related to the state of Global Variables is displayed here. In this view the user will find any Watched Variables in the top of the list for easier control of these selected variables.

To add a Global Variable to the list of Watched Variables, simply click the Eye icon next to the name of the Variable in the list.

Messages

The Messages section provides different information related to the Engine status which depends upon which interaction in the Dialog view is currently selected; selecting an Online message will, for example, display information related to:

  • Solution parsing
  • Engine initialization
  • the solution's machine learning model (model status: update in progress, update completed, update failed)
  • Statistics, such as, number of Flows, Language Objects, and Entities in the solution and any assigned lexical resource
  • Available script engines (such as Groovy Scripting Engine) and the default scripting language
  • Error and warning messages

While a user is working in the solution, information about created and updated Flows, Language Objects, and Entities is also displayed as well as any errors detected during development; and selecting a tested input/output will present the user with information related to the response time, input text and, if available, any input parameters.

Error and warning messages

The Dialog view of both the simple and the advanced Try Out displays information related to errors and warnings detected in the solution to quickly draw the user's attention to these, and more extended information is available in the Messages section of the advanced Try Out window.

Error messages displayed in the Try Out includes:

  • Errors when starting the Try Out Engine (i.e. HTTP errors when communicating with the server or failing initialization of the Engine)
  • Missing/Incorrect Language Object/Entity references
  • Disabled Language Object/Entity used in conditions or entry values
  • Undeclared Variables being set
  • Script errors in Flows

Learn more about error detection in solutions here.

Solution Suggestions
Information about Errors