Summarize Closed Help Scout Conversations and Send to Asana

When any conversation's status changes in Help Scout—opened, pending, closed, or spam—this trigger captures the status update and conversation details. It watches your Help Scout account continuously and passes the conversation data to the next step for status verification. The trigger automatically connects to your Help Scout account once you authorize MESA, with no manual configuration needed.

The filter compares the conversation status from the trigger against the value "closed." If the status matches exactly, the workflow continues to retrieve the conversation threads; if not, the workflow stops here and no task is created. This is a hard-coded filter checking specifically for "closed" status, so you don't need to configure anything—it works automatically to catch only resolved conversations.

The step fetches every thread (message) in the closed conversation using the conversation ID from the trigger. This includes the initial customer message, all agent replies, and any additional back-and-forth communication. Each thread's body text gets extracted and prepared for the next step to combine into a single summarizable format. The API call automatically uses the conversation ID to pull the correct thread data from Help Scout.

The Map step iterates through all the thread bodies retrieved in the previous step and combines them into a comma-separated text string. For example, if there were 5 messages in the conversation, this step extracts each message body and joins them together with commas, creating a single text field that contains the entire conversation from start to finish. This formatted text gets passed to both AI steps for summary and title generation.

The AI receives the comma-separated conversation text from the Map step and analyzes it to create a concise summary that focuses on the customer's issue and resolution. The prompt specifically instructs the AI to exclude technical details and focus on the narrative, making the summary accessible for team members who weren't involved in the original conversation. The summary gets included in the Asana task notes for reference.

The AI analyzes the same conversation text and generates a clear title that captures the essence of the support issue. The prompt instructs the AI not to preface the title with "Title:" so it outputs clean text ready to use as the Asana task name. For example, instead of "Help Scout ticket," you might get "Customer requested refund for damaged product during shipping."

You'll configure two fields: the Asana workspace and the specific project where tasks should be created. The workspace is your overall Asana account (like "Marketing Team" or "Customer Success"), and the project is where these support summaries will live (like "Support Insights" or "Customer Feedback"). The task name uses the AI-generated title, and the notes section includes the AI summary, original Help Scout ticket number, customer email, and the date the conversation was closed for complete reference.