AI Ticket Sentiment Analysis Crate
What does the AI Ticket Sentiment Analysis Crate do?
Our AI Ticket Sentiment Analysis Crate uses AI to analyze a customer ticket's details to determine its impact, urgency, priority, and sentiment. It automates the process by updating these fields in your PSA system, handling ticket escalations, and adding a note with the analysis results.
Customize and configure the following for this Crate:
Choose the AI model to use for ticket analysis, as this Crate works with both OpenAI and Anthropic.
Customize AI's maximum tokens used using organization variables.
Choose which fields to update in the PSA system: impact, urgency, and sentiment.
Define impact, urgency, and sentiment thresholds for automatic priority updates and escalations.
Assign tickets to specific PSA members when thresholds are exceeded.
This Crate doesn't manually resolve tickets or perform actions outside of analyzing and updating specific fields. Further ticket management actions will need to be handled separately.
How the Crate works
The Crate workflow is triggered by a webhook whenever a new ticket is created in the PSA system.
Workflow breakdown
The workflow begins with the START task using the noop action to initiate the process.
The set_model task uses the noop action to configure AI model settings and determines which AI model to use based on organization variables.
The is_model_set task uses the noop action to check if an AI model is properly configured and routes to the failure path if no model is detected.
The get_max_tokens task uses the noop action to retrieve the maximum token limit for the AI model from organization variables or model defaults.
The is_max_tokens_set task uses the noop action to validate token configuration and routes to a warning task if tokens are not properly set.
The max_tokens_not_set task uses the noop action to log a warning message about missing token configuration before continuing.
The get_ticket_variables task uses the AI:Format PSA Ticket Variables action to extract and format ticket information from the PSA system.
The get_note_information task uses the PSA:Get Note Information action to retrieve additional ticket notes and user messages from the PSA.
The check_psa task uses the noop action to determine which PSA system is being used and branches the workflow accordingly.
If Halo PSA is detected, the get_halo_psa_impacts task uses the HaloPSA API Request action to retrieve available impact options from the system.
If ConnectWise Manage is detected, the get_cwm_impacts task uses the CW PSA API Request action to retrieve impact data from ConnectWise.
If no specific PSA is detected, the static_impacts task uses the noop action to provide default Low, Medium, and High impact options.
For Halo PSA systems, the get_halo_psa_urgencies task uses the HaloPSA API Request action to retrieve urgency level options.
For ConnectWise systems or when using static data, the static_urgencies task uses the noop action to provide default Low, Medium, and High urgency options.
The get_ticket_priorities task uses the PSA: Get Ticket Priorities action to retrieve available priority levels from the PSA system.
The get_openai_information task uses the Select AI Prompt Provider action to send ticket content to the AI service for analysis of impact, urgency, and sentiment.
If the AI analysis succeeds, the set_inital_note task uses the noop action to format the AI analysis results into a readable ticket note with priority, impact, urgency, and frustration ratings.
The update_impact_urgency_sentiment task uses the PSA: Update Impact, Urgency, Sentiment action to apply the AI-determined values to the PSA ticket.
If any step fails during execution, the failed task uses the noop action to handle the error condition and route to error processing.
The list_errors_in_ticket task uses the noop action to determine whether error information should be added to the ticket based on configuration settings.
If error reporting is enabled, the update_ticket task uses the PSA: Update Ticket action to add failure details as an internal note to the ticket.
If error reporting is disabled, the ticket_error_updating_disabled task uses the noop action to bypass ticket error updates.
The END task uses the noop action to compile all logging information and publishes the final automation log with status codes, errors, warnings, and execution details.
Crate prerequisites
Before unpacking the Crate, you'll need to have the integration for one of the following PSAs set up:
If you're using a PSA that isn't on this list, please let us know and we'll look at whether it has the ability to trigger an automation based on a ticket being created.
Remember, you can also set up an Azure instance of OpenAI, and use that with this Crate. If you want to use an Azure instance of OpenAI with this Crate, you'll need to follow the Azure OpenAI Integration Setup steps to have this completed before unpacking.
Unpack the AI Ticket Sentiment Crate
Navigate to Crates > Crate Marketplace in the left side menu of the Rewst platform.
Search for
AI Ticket Sentiment Analysis.
Click on the Crate tile to begin unpacking.
Click Unpack Crate.
Choose your desired PSA from the drop-down selector. This is especially important for customers using multiple PSAs.
Choose either OpenAI or Anthropic as your AI integration.
Choose your detection category from the drop-down selector.
Choose the number threshold for impact, urgency, and sentiment of tickets.
Impact Threshold:
This is the threshold that you want to set for the impact of the ticket. If the impact is below this threshold, the ticket will be considered low impact. If the impact is above this threshold, the ticket will be considered high impact, and update the ticket accordingly.
Urgency Threshold:
This is the threshold that you want to set for the urgency of the ticket. If the urgency is below this threshold, the ticket will be considered low urgency. If the urgency is above this threshold, the ticket will be considered high urgency, and update the ticket accordingly.
Sentiment Threshold:
This is the threshold that you want to set for the sentiment of the ticket. If the sentiment is below this threshold, the ticket will be considered a positive sentiment. If the sentiment is above this threshold, the ticket will be considered negative sentiment, and update the ticket accordingly.
Enter the email address of the PSA member that the ticket will be assigned to for sentiment.
Choose the AI Provider that you wish to use from the drop-down selector.
Choose the AI Model that you wish to use.
Choose if you would like to Report errors in ticket when unable to utilize AI.
Click Continue.
Triggers for all possible PSAs are included in this Crate. By default, they're disabled, and only the PSA indicated by your choice in the drop-down selector used in the previous step will be enabled. The trigger that will kick off the automation when a ticket is created is the one left enabled.
Click Unpack.
Use the AI Ticket Sentiment Crate
Create a ticket in your PSA with a typical description and summary. Set your impact, urgency, and sentiment to be above the threshold that you chose in the Crate's configuration. This will kick off the workflow's webhook trigger.
Organization variables associated with this Crate
These organization variables give you more control over the functionality of this workflow.
ORG.VARIABLES.ticket_sent_max_tokens- Allows you to manually set the max tokensORG.VARIABLES.ai_model_ticket_sent- Allows you to manually set the model
Last updated
Was this helpful?