Documentation
DocumentationDeveloperAcademyCommunitySupportLogin

How to Guides for Answers Plugin

Suggest Edits

How To Configure the Answers Plugin for ServiceNow

Pre-Requisites

  • Please ensure the required ServiceNow Connector has been created with the necessary permissions. Please refer the ServiceNow Access Requirements Doc for details.
  • Please ensure the Service Account being used for connecting to ServiceNow has access to the Knowledge Bases users want to ingest articles from.

Configuration

Start by creating a new Ingestion under Answers > Ingestion > Internal Knowledge Settings

  • First, select the Connector created for the ingestion and then provide a name for the ingestion. under Ingestion Name.
  • Then, choose a Domain. The domain is the functional areas of employee service that is most related to the knowledge being ingested for this configuration.
    • The domain is the functional areas of employee service that is most related to the knowledge being ingested for this configuration. And choosing a domain helps the bot to serve relevant knowledge to the user.
    • Moveworks supports up to eight domains by default. You can click on Back to return to this page to change the selected domain during the knowledge configuration process, but the domain cannot be changed after you submit the configuration.

Setup Knowledge Bases - Wizard Mode

  • Moveworks will now make a live API call to your knowledge management system's instance and show you a list of all the knowledge bases or categories of knowledge articles available.
  • These categories can be different for different systems. For example, it can be knowledge bases for ServiceNow, or spaces for Confluence.

Select all the categories of articles that you want to ingest. For some systems like ServiceNow basic filtering options like selection of tables and default filtering options are provided. You can click on the edit icon on right side to have a look at these options.

Note: Basic filtering in wizard flow is only supported for some systems. You might not find edit icon for all the systems.

Note: For few systems like Zendesk, content needs to exist in the category else these categories might not show up in this view.

For example, in the case of ServiceNow the following options are available:

  • Moveworks supports the following default filters.
    Note: that these filters will be on by default.
    - Workflow status = Published (Ingest only published article. These filters allow you to exclude draft, archived articles to be ingested and served to your employees)
    - Active = True
    - Valid_to > BeginningOfToday
  • Moveworks supports the following Tables selections for each knowledge base. By default, the kb_knowlege table will be turned on for every base selected. You may choose other tables as required.
    • kb_template_how_to
    • kb_template_kcs_article
    • kb_template_faq
    • kb_template_what_is

Depending on your use case, you may choose to use Advance mode to ingest your knowledge base. You should use Advance mode if you need custom tables as part of the configuration, or if you require custom filtering of articles. To use Advance mode, click on the toggle next to Advance mode, and proceed to the Advance mode section of this guide to learn how to setup your knowledge in this mode.

Now that you’ve selected your KBs, click on Next: Sample URL to provide the sample article URL.

Provide a sample URL

In this step you will be asked to provide a sample URL, this is the end user facing article URL. Whenever your queries are answered by Moveworks, a user facing link to the article it referred to is also provided so that the user can be redirected to the complete article.

Here is how you get a sample URL for ServiceNow:

  1. Go to your ServiceNow instance.
  2. Go to any article that you want to ingest.
  3. Copy the URL in your browser’s address bar.
  4. Go back to Moveworks Setup, and paste this URL into the field under Paste a URL from an existing article.

Note: This step might not be present for systems where it is not possible for us to fetch sample URL automatically.

Now that you’ve provided a sample article URL, click on Next: Review Samples to go to the final step which is Validation.

Review Samples

Here you can confirm whether the configurations you made are correct. You can always click on Back and make changes.

This page also displays the article count is the total number of articles that will be ingested into Moveworks based on the configurations you just completed. This is not a sample count.

Setup Knowledge Bases - Advanced Mode

By using Advance mode you have greater control over which articles to ingest. For example, you can define who can access these articles, or you can use customize filters for various knowledge categories.

How to get to Advance mode?

You will find a toggle on the top right corner on the Setup Knowledge Bases step. Toggle this on and you will be taken to Advance mode. Please note that once you switch to Advance mode, all your current progress will be lost.

📘

Note : Some systems that do not support wizard flow will directly take you to Advance mode.

What can you do in Advance mode ?
There are multiple controls offered in Advance mode. You can look at the descriptions and make the configurations yourself. Apart from the multiple controls that you discover on this page, there is one major feature of Advance mode:

  • Select Ingestion System - Moveworks has a wide list of systems that support knowledge ingestion from which will be listed here. We will be selecting SNOW Config for this example.

  • Start URLs - In order to ingest the Articles from a Knowledge base, the user would need to explicitly mention the complete URL which will be used in the API call. They commonly follow the below structure :

    https://<instance-name>.service-now.com/api/now/v2/table/kb_knowledge?sysparm_limit=50&sysparm_display_value=all&sysparm_query=workflow_state=published^sys_class_name=kb_knowledge^kb_knowledge_base=<kb_sys_id>^active=true

  • Knowledge Article Filter Rule - This DSL field can be used to filter out Articles in the source system from being ingested. The steps of how to configure this can be followed here.

  • Article Url Override - This is the similar field as the one in Wizard mode, This is where Moveworks will take up the new URL in order to generate this for all the ingested Articles. The field that controls this is the Article Url Override filed under Field Overrides and this is where you can provide the template.

Validation

  • Once you have submitted the Knowledge ingestion configuration, it will kick off the Ingestion pipeline in the background, the status of the same can be tracked on the Ingested Knowledge View
  • You can search for the Articles with their Title's here, and if they are listing on the Console that means they have been ingested successfully.

How To Configure the Answers Plugin for Confluence

Pre-Requisites

  • Please ensure the required Confluence Connector has been created with the necessary permissions. Please refer the Confluence Cloud Access Requirements Doc for details.
  • Please ensure the Service Account being used for connecting to Confluence has access to the Spaces users want to ingest from.

Configuration

Start by creating a new Ingestion under Answers > Ingestion > Internal Knowledge Settings

  • First, select the Connector created for the ingestion and then provide a name for the ingestion. under Ingestion Name.
  • Then, choose a Domain. The domain is the functional areas of employee service that is most related to the knowledge being ingested for this configuration.

Setup Knowledge Bases

  • Wizard Mode

    • Moveworks will now make a live API call to Confluence and provide the user with a list of spaces that have access to ingest Articles from.

    • Once the Spaces have been selected, you will be required to provide the URL of an existing article, Moveworks will leverage this URL to create the redirect links for all the Articles post ingestion.

    • On the final page you can review a Sample set of Articles fetched based on the config in a preview screen. You can validate the Article URL here.

  • Advanced Mode

    • In the Advanced mode, in order to ingest articles from a space, users are required to define the Start URL. They commonly follow the below structure :

      https://<instance-name>.atlassian.net/wiki/rest/api/content?limit=200&spaceKey=<space-key>


    • This is the similar field as the one in Wizard mode, This is where Moveworks will take up the new URL in order to generate this for all the ingested Articles. The field that controls this is the Article Url Override filed under Field Overrides and this is where you can provide the template.

Validation

  • Once you have submitted the Knowledge ingestion configuration, it will kick off the Ingestion pipeline in the background, the status of the same can be tracked on the Ingested Knowledge View
  • You can search for the Articles with their Title's here, and if they are listing on the Console that means they have been ingested successfully.

How To Configure the Answers Plugin for SharePoint

Pre-Requisites

  • Please ensure the required SharePoint Connector has been created with the necessary permissions. Please refer the SharePoint API Access Requirements Doc for details.
  • Please ensure the Service Account being used for connecting to SharePoint has access to the Sites we want to ingest from.

Configuration

Start by creating a new Ingestion under Answers > Ingestion > Internal Knowledge Settings

  • First, select the Connector which was created for the ingestion and then provide a name for the ingestion. under Ingestion Name.

  • Then, choose a Domain. The domain is the functional areas of employee service that is most related to the knowledge being ingested for this configuration.

  • In order to ingest articles from a SharePoint Site, users would need to define the Start URL. They commonly follow the below structure :

    • Site Pages 
      • https://<instance-name>.sharepoint.com/sites/<site-name>/_api/SitePages/Pages?$top=10&$skip=0

      • https://graph.microsoft.com/beta/sites/<instance-name>.sharepoint.com:/sites/<site-name>:/pages
    • Teams Site Pages 
      • https://graph.microsoft.com/beta/sites/<instance-name>.sharepoint.com:/teams/<teams-site-name>:/pages_

      • https://<instance-name>.sharepoint.com/teams/<teams-site-name>/_api/SitePages/Pages?$top=100&$skip=0

  • Users also need to provide the Article Url in order for us to generate this for all the ingested Articles. The field that controls this is the Article Url Override filed under Field Overrides.

Validation

  • Once you have submitted the Knowledge ingestion configuration, it will kick off the Ingestion pipeline in the background, the status of the same can be tracked on the Ingested Knowledge View
  • You can search for the Articles with their Title's here, and if they are listing on the Console that means they have been ingested successfully.

How To Mirror Permissions for Knowledge from ServiceNow

Pre-Requisites

In order to Mirror Permissions from ServiceNow for the associated Knowledge, Moveworks also needs to ingest the User Criteria linked to the Knowledge Articles. This is currently only supported for ServiceNow

  • To ingest the user criteria for knowledge, users need to install some update sets on the ServiceNow side which are defined in the Guide here.
    • Admins need to ensure the BASE and ACL update steps has been installed for the appropriate permissions to be set.
  • If you want to learn more about how this is setup, the steps are covered in the ServiceNow User Criteria Guide.

Configuration

Start by creating the User Criteria Ingestion Config which is under Core Platform > Resource Permissions > Mirror Permissions

  • Select Connector - Choose the ServiceNow Connector for ingesting User Criteria from.
  • Fetch Form Access Controls - Enabling this ingests user criteria associated with Catalog Items or Forms in ServiceNow.
  • Fetch Knowledge Base Access Controls - Enabling this ingests user criteria associated with Knowledge Articles in ServiceNow.
  • Evaluate User Criteria - Enabling this ensures, that once the user criteria has been ingested, it can then be evaluated on the Moveworks end before serving to the user.

Finally, navigate to Resource Permissions > Permissions Rules under the Core Platform section in the left navbar. Here you will create a new Permission Rule for allowing Serving of Knowledge, ingested from an integration.

The permissions configuration requires the below details in order to serve up the respective Resource, the Rule associates with.

📘

Always create the initial Permission Strategy to use ABAC with the Rule set to TRUE so the serving can be tested.

You can also write a DSL Rule here utilising user attributes to enable it for subset of users. Example here.

ABAC - Simple DSL Rule Evaluation

This strategy evaluates the permission rules written in Moveworks DSL Language. You can learn more about the DSL Syntax in the Guide here .

  • Resource Rule

    • In this drop down users are required to select the Resource Type, on which the rule will apply.
      Ex. KB Rule

  • KB Rule - This is where users will write the DSL rules in the MWDSL Syntax

    • Boolean Rule

      • Ex. TRUE or FALSE

      • ⚠️ This acts as the master control here where it enables or disables the serving of content for this integration completely

    • Attribute Rule

      • Allowing Knowledge to be served for a subset of user. Ex. user.email_addr IN ["[email protected]"]

      • Allowing only certain Articles to be served within the Bot. Ex. resource.article_id IN ["12345","5678"]

      • Allowing users who have a specific user-tag associated with their Record, access to the Articles in the Bot. Ex. (("HAS_ACCESS_TO_BOT" IN user.user_tags) OR ("MOVEWORKS_INTERNAL_USER" IN user.user_tags))

  • Integration ID - The connector which is being used to ingest the knowledge content.

  • Resource Type - Resource Type for which the Rule will apply. Ex. kb, file etc.

  • Action - ACTION_VIEW

❗️

Please ensure to validate the Syntax before moving forward.

Ignoring to do this can result in a syntactically wrong rule being saved which could cause issues in serving knowledge

Validation

Once you have submitted the Resource Permissions ingestion configuration, it will kick off the Ingestion pipeline in the background, the details of the Ingestion times is present in the Moveworks Ingestion Schedule. It is recommended to wait a day before testing this out.

In order to validate the Permissions users would need to change the Permission Rules which were set to ABAC earlier to now use the Mirroring Strategy which is ReBac.

ReBac- Mirroring External System Permissions - This strategy mirrors the permission rules on the External Knowledge source by ingesting them on the Moveworks end. This is currently only supported for ServiceNow

  • Additional Access

    • In this drop down, Moveworks requires the user to select the Resource Type, on which the rule will apply.
      Ex. KB Rule

    • KB Rule - There are is where the user will write the DSL rules in the MWDSL Syntax. If the Rule is left empty it will default to TRUE.


  • Additional Restrictions

    • In this drop down Moveworks requires the user to select the Resource Type, on which the rule will apply.
      Ex. KB Rule

    • KB Rule - There are is where users will write the DSL rules in the MWDSL Syntax. If the Rule is left empty it will default to TRUE. You can also write rules utilising internal Attributes which allow knowledge from a specific knowledge base to be served and not others.

    • Integration ID - The connector which is being used to ingest the knowledge content.

    • Resource Type - Resource Type for which the Rule will apply. Ex. kb, file etc.

    • Action - ACTION_VIEW

You should now be good to start testing the serving of Knowledge which permissions are being mirrored from the external system.

How To Serve Knowledge to users based on their Geo Location

Pre-Requisites

  • Please ensure the required Confluence Connector has been created with the necessary permissions. Please refer the Confluence Cloud Access Requirements Doc for details.
  • Please ensure the Service Account being used for connecting to Confluence has access to the Spaces users want to ingest from.

Configuration

  1. Click on Answers > Plugin Settings under Enterprise Search in the Moveworks Setup sidebar.
  2. Click on the Geocode boost Preference dropdown and select one of the types.
    1. Hard - Your bot will answer queries with respect to your geolocation every time, if the bot is not confident in the response, it won't provide you an answer.
    2. Soft - Your bot will respond to your queries with respect to your geolocation, but if it does not find out an appropriate article for your location, it might respond to you with whatever source is available.
    3. Disabled - This disables the Geocode Boost option for your bot.
  3. Click on the checkbox next to Positive Geocode Boost.

Validation

The users can now request for knowledge in the AI Assistant, and based on their Geo location the responses would include Articles which are mapped to that location.

This is especially common in case of Articles where the Title includes the name of the location. Here is a guide to learn more about this

How To Filter out Articles from being Ingested

Pre-Requisites

  • Please ensure the required Connector has been created with the necessary permissions. Also ensure the appropriate access has been provided to view the Article ID for the articles to be filtered out.

Configuration

  1. In order to filter out the articles from ingestion, users need to enter the Advanced Mode during the Knowledge Configuration flow.
  2. Please find the Knowledge Article Filter Rule where users can use the below attribute to filter out the Article based on its sys_id which is written in the Moveworks DSL Language. 
    NOT(article.article_id IN ["<article sys_id>"])

Validation

  • Once the ingestion has completed running. Users can validate if the article was filtered out by searching for the title in the Ingested Articles View Page.

Updated 1 day ago