TICKET MANAGEMENT
Intercom Chat Deflection via Zendesk Known-Issue Match
When a customer opens an Intercom chat, it matches their message to known issues from solved Zendesk tickets and either sends self-serve reproduction-and-workaround steps…
How it runs
The automated pipeline, trigger to output.
- TriggerNew Intercom conversation openedIntercom
- ActionMatch message against Zendesk known-issue indexOpenAI
- LogicBranch on match confidence
- ActionReply in Intercom with workaround and repro contextIntercom
- OutputAssign to human with matched known issue attachedIntercom
What it does
This workflow catches inbound Intercom conversations and tries to deflect them with proven answers. It matches the customer's opening message against known issues mined from solved Zendesk tickets. On a strong match it replies in-chat with the workaround and reproduction context; on a weak match it routes to a human agent and attaches the closest known issue as a note so the handoff is warm.
When to use it
Use this on a live chat channel where many conversations are repeat reports of the same known defects. It cuts first-response time and lets humans focus on the genuinely novel cases.
How it works
- 1A new Intercom conversation triggers the flow.
- 2OpenAI matches the opening message against the known-issue index built from solved Zendesk tickets.
- 3A branch checks match confidence.
- 4On a strong match, it replies in Intercom with the workaround and a note that the issue is known and tracked.
- 5On a weak match, it assigns the conversation to a human and attaches the closest candidate plus repro steps as an internal note.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect ZendeskTickets, queues, knowledge base.
- 3Connect OpenAIModels, embeddings, files.
- 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
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.
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.
Escalate repeat reopens to a Linear bug
Detects when the same underlying issue reopens across multiple tickets, uses an AI agent to cluster them by root cause.
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.