CUSTOMER SUPPORT
AI agent that judges semantic duplicate support threads before merging
When a duplicate is suspected, an AI agent reads both conversation transcripts, decides whether they are truly the same issue.
How it runs
The automated pipeline, trigger to output.
- TriggerWebhook: candidate duplicate pair flaggedHTTP webhook
- ActionFetch both transcripts from ZendeskZendesk
- ActionAgent judges same-issue verdict + confidenceOpenAI
- LogicBranch on confidence: auto-merge vs review
- ActionMerge high-confidence pair in ZendeskZendesk
- OutputFile uncertain pairs as Linear review taskLinear
What it does
Goes beyond matching email addresses by having an AI agent actually read both transcripts and judge whether two threads describe the same underlying problem. Confident matches are merged automatically; ambiguous ones become a review task so nothing wrong gets stitched together.
When to use it
Use it when same-customer threads are sometimes about different problems, and naive identity matching would wrongly merge unrelated tickets.
How it works
- 1A webhook fires when an upstream detector flags two candidate threads.
- 2The flow fetches both full transcripts from Zendesk.
- 3An OpenAI step asks the agent to compare the issues and return a same-issue verdict with a confidence score and rationale.
- 4A logic branch routes the result: high confidence merges, low or medium confidence does not.
- 5High-confidence pairs are merged in Zendesk; everything else is filed as a Linear review task with the agent's rationale attached.
Set it up
What you configure once, before turning it on.
- 1Connect HTTP webhookTrigger any URL on agent actions.
- 2Connect ZendeskTickets, queues, knowledge base.
- 3Connect OpenAIModels, embeddings, files.
- 4Connect LinearIssues, projects, cycles, triage.
- 5Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 6Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 7Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Customer Support workflows
Close the loop with requesters when a Linear bug moves to Done
When a Linear issue created from a support escalation moves to Done after deploy, look up the originating Zendesk tickets and notify each requester that their reported bug is…
Reopen and notify Front conversations when their bug fix deploys
When a deploy resolves a Sentry issue, find the snoozed or closed Front conversations linked to it, reopen them, and send the customer a reply that the fix is now live.
Suggest the right Loom video by classifying Intercom message intent
Reads each new inbound Intercom conversation, classifies what the customer is trying to do, and surfaces the best-matching Loom walkthrough to the agent as an internal note.
Draft personalized fix-live replies for support to review
When a Sentry issue resolves, an agent reads each linked ticket's full thread and drafts a tailored 'your fix is live' reply per requester.
Send a tailored Loom onboarding sequence on Front first-reply
When a new customer's first email lands in Front, this picks the Loom onboarding walkthroughs matching their plan and use case, builds a friendly sequenced reply.
Article Volume-Rebound Early Warning (Datadog)
Streams support ticket-tag events into Datadog, watches for topics whose volume is reaccelerating against a decaying article.
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.