Please contact a Glean representative if you are interested in partnering with Glean and building tools on Glean’s platform.

Frequently Asked Questions (FAQs)

Which fields are interpreted by LLM?

The "Unique Identifier" and "Trigger Condition (including Example Queries)" fields are used by the LLM to identify which tool it should invoke/use for a user's query.

Make sure to give a detailed trigger condition and example queries, to ensure LLM knows exactly what user queries should this tool be used for.

How to authenticate Tools built using Glean's Jira template?

Please follow these steps to setup authentication for Jira:

Set up the integration user

  • Select a user whose Jira account will be used to set up the integration between Glean and Jira. This account must have Modify Reporter permissions in Jira.
  • To grant this account Modify Reporter permissions, do the following:
  • Log into Jira as an Administrator.
  • In Jira’s settings page, click the Issues menu.
  • Scroll down and select the “Permission schemes” menu and select the permission scheme corresponding to your project
  • Add the user to ‘Modify Reporter’ permissions by clicking ‘Update’ > ‘Single user’ > Select the integration user > Update
  • Add the user to ‘Create Issues’ permissions by clicking ‘Update’ > ‘Single user’ > Select the integration user > Update
  • Add the user to ‘Assign Issues’ permissions by clicking ‘Update’ > ‘Single user’ > Select the integration user > Update

Create the Jira OAuth app

  • Navigate to the Atlassian Developer Console at this link and create a new app of type: OAuth2.0 Integration.
  • Follow the prompts to set up the app. Make note of details like the app name, description, and logo.

Configure the callback URL


Go to the Authorization tab of your app configuration.

Using the unique Tool identifier in Glean’s Tool creation page, set the callback URL to the following: https://{domain}{uniqueToolIdentifier}.

Set permissions

In the Atlassian Developer Console, navigate to the Permissions tab

Add the following scopes:

Jira API - write:jira-work, read:jira-user

Configure the app on Glean

Fill the following fields in the Authentication section of the Glean Tool setup page:

Complete authentication

  • Save the tool's settings to confirm the configuration
  • Click on the authorization link provided to complete the OAuth flow. Once authorization is complete, you should see a message “Authorized
What are type hints?

Type hints are like instructions that help the Glean AI understand and work with different tools better. They're clues that tell the AI what each part of a tool does, making it easier for the AI to get the right information or do the right thing with those tools.

Benefits of Implementing Type Hints

  • Simplified Tool Creation: Type hints make it easier for developers to describe their tools' capabilities and requirements.
  • Better at Getting Information and Doing Tasks:
  • Type hints give clear instructions on gathering data or performing actions, leading to more accurate and relevant results from the AI.

How to Use Type Hints To use type-hints, consider the following steps:

  • Identify Relevant Type Hints: Review the list of supported type hints to determine which ones align with your tool's functionality.
  • Incorporate Type Hints into Your API Specs:
  • Add the selected type hints as structured details in your tool's API specifications.

Supported Type Hints

Below are the type hints currently supported by Glean:

  • EmailAddress

This type hint is used for fields that are intended to capture the email address of the user. Example usage:

  x-glean-typehint: 'EmailAddress'
  type: string
  description: User to which the issue is assigned.
  • Content

This hint is applied to fields that deal with large amounts of text or content. It's ideal for tools that generate, modify, or display content, ensuring that the information is handled appropriately. Example usage:

  x-glean-typehint: 'Content'
  type: string
  description: Rich description.
  • JiraProjectId

This type hint is for fields that require a JIRA project ID. It's used in contexts where actions or information are specific to a particular JIRA project, helping to ensure that operations are correctly scoped. Example usage:

  x-glean-typehint: 'JiraProjectID'
  type: string
  description: Project ID where the ticket is created.
  • JiraComponentId

This hint is designated for fields that involve a JIRA component ID. It's useful for tools that need to interact with specific components within a JIRA project, facilitating precise and relevant operations. Example usage:

  x-glean-typehint: 'JiraComponentId'
  type: string
  description: Component Id where the ticket should be filed.

By incorporating these type hints into your tool's API specifications, you can enhance the Glean AI assistant's understanding and handling of your tool, leading to a more seamless integration and a better overall user experience. If you have any further questions or require assistance, our developer support team is here to help.

Do Tools work for endpoints behind VPN?

Yes, please contact our team for information on how to do this.

How much data can my service return (for retrieval tools)?

The response from the service you're connecting to retrieve content using your retrieval tool will be sent to the LLM to create the final response. Hence, please ensure that the data returned is not larger than ~8000 characters. Depending on the LLM model being used, larger responses will be truncated from the end.