TICKET MANAGEMENT
Agent-driven review of unclear Intercom bug reports
An agent works a queue of Intercom conversations that automated classification marked unclear.
How it runs
The automated pipeline, trigger to output.
- TriggerConversation enters unclear review queueIntercom
- ActionAgent identifies missing reproducibility detailsOpenAI
- ActionSend targeted follow-up questionIntercom
- LogicRe-evaluate: bug, how-to, or invalidOpenAI
- ActionFile structured Linear issue for confirmed bugsLinear
- OutputRecord disposition on Intercom conversationIntercom
What it does
Handles the gray zone: conversations the deterministic classifier couldn't confidently label as bug or how-to. An agent reviews each one, drafts a precise clarifying question to the customer (missing repro steps, version, expected behavior), and waits. When the reply makes it a clear reproducible bug, it files a well-formed Linear issue; otherwise it closes the loop as a how-to or invalid report.
When to use it
When too many real bugs are getting lost in the `unclear` bucket because the customer's first message was ambiguous, and you want an autonomous agent to chase the missing details rather than a human doing it.
How it works
- 1A conversation lands in the `unclear` review queue (trigger).
- 2The agent reads the full thread and identifies what's missing for reproducibility.
- 3It drafts and sends a targeted follow-up question in Intercom.
- 4On the customer's reply, the agent re-evaluates reproducibility.
- 5A branch decides: confirmed bug, how-to, or invalid.
- 6Confirmed bugs are filed as structured Linear issues; the agent records the disposition back on the Intercom conversation.
Set it up
What you configure once, before turning it on.
- 1Connect IntercomConversations, contacts, articles.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect LinearIssues, projects, cycles, triage.
- 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.