TICKET MANAGEMENT
Real-time duplicate detection on new Front conversations
When a new Front conversation arrives, it embeds the message, searches a vector store of recent tickets for near-matches.
How it runs
The automated pipeline, trigger to output.
- TriggerNew Front conversation createdFront
- ActionEmbed subject + body with OpenAIOpenAI
- ActionVector-search recent open ticketsPostgres
- LogicKeep matches above similarity threshold
- ActionDraft merge rationaleOpenAI
- OutputPost private merge-suggestion comment in FrontFront
What it does
Every time a customer opens a new Front conversation, this workflow checks whether it's a duplicate of an existing open ticket and, if so, drops a private internal comment on the new conversation suggesting which ticket(s) to merge it into.
When to use it
Run this on inbound support inboxes where the same outage, bug, or billing event triggers a flood of near-identical tickets. It stops agents from independently working the same issue and keeps one canonical thread.
How it works
- 1A Front webhook fires when a new conversation is created, passing the subject and first message body.
- 2OpenAI generates an embedding of the subject plus body text.
- 3A Postgres query (pgvector) finds the top open tickets within a cosine-similarity threshold from the last 14 days.
- 4A logic step keeps only matches above 0.86 similarity; if none clear the bar, the run ends quietly.
- 5OpenAI drafts a short rationale naming each candidate and why it looks like the same issue.
- 6The workflow posts a private internal comment on the Front conversation with the ranked candidates and one-click merge links.
Set it up
What you configure once, before turning it on.
- 1Connect FrontShared inbox, conversations.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Ticket Management workflows
Intercom Known-Issue Auto-Responder
When a new Intercom conversation matches a known active incident, it attaches the conversation to that incident's parent ticket and sends the customer the current status reply.
Weekly reopen-by-agent coaching digest
Aggregates each agent's solved-then-reopened tickets for the week, identifies the most common reopen reason per agent, and emails a private coaching digest to the support manager.
Deduplicate Discord bug reports against existing Linear issues
Before creating anything, searches Linear for issues matching a new Discord bug report; if a duplicate exists it comments and links the report there, otherwise it opens a fresh…
Enrich Discord bug reports with Sentry errors before filing in Linear
Takes a Discord bug report, has an LLM pull out likely error signatures, searches Sentry for matching events.
Front-to-Linear Recurring Bug Linker
When a Front ticket is tagged as a bug, it searches Linear for an existing matching issue and either links the ticket to that parent issue or opens a new tracked one.
Front Duplicate Conversation Clusterer
When a new Front conversation arrives, it semantically compares the report against open conversations.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.