TICKET MANAGEMENT
Promote reproducible Intercom bugs into Linear (skip how-to questions)
When an Intercom conversation is tagged or closed, classify whether it describes a reproducible bug or a how-to question, and only create a Linear issue for genuine bugs.
How it runs
The automated pipeline, trigger to output.
- TriggerIntercom conversation tagged bug-reviewIntercom
- ActionFetch full transcript and customer metadataIntercom
- LogicClassify: reproducible-bug vs how-to vs unclearOpenAI
- LogicDrop anything that isn't a reproducible bug
- ActionCreate Linear issue with repro steps and severityLinear
- OutputPost Linear issue link back to IntercomIntercom
What it does
Reads each qualifying Intercom conversation and decides whether the customer reported a *reproducible defect* (clear steps, expected vs. actual behavior, an environment) or simply asked *how to do something*. Reproducible bugs become Linear issues; how-to questions are left alone so engineering's backlog stays signal-dense.
When to use it
When support volume is high enough that manually triaging which conversations deserve an engineering ticket is a daily chore, and you want only true bugs to reach Linear, not feature confusion or usage questions.
How it works
- 1An Intercom conversation is tagged `bug-review` (trigger).
- 2The full conversation transcript and customer metadata are fetched from Intercom.
- 3An LLM step classifies the thread into `reproducible-bug`, `how-to`, or `unclear`, extracting repro steps, expected/actual behavior, and severity when present.
- 4A branch drops anything not classified `reproducible-bug`.
- 5For confirmed bugs, a Linear issue is created with the repro steps, severity label, and a back-link to the Intercom conversation.
- 6The Intercom conversation is updated with the new Linear issue URL so support can reference it.
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.