TICKET MANAGEMENT
GitHub Issue Duplicate Auto-Linker with Maintainer Override
On every new GitHub issue, searches existing open issues for a duplicate, and when one match clears a strict confidence bar, comments with a cross-link and a duplicate label.
How it runs
The automated pipeline, trigger to output.
- TriggerNew GitHub issue openedGitHub
- ActionEmbed issue + search existing open issuesOpenAI
- LogicRequire single match above strict threshold
- ActionComment cross-link + apply duplicate labelGitHub
- LogicWait window for maintainer veto reaction
- OutputClose issue as duplicate of canonicalGitHub
What it does
This workflow catches duplicate GitHub issues at filing time. It compares each new issue to existing open ones, and when a single high-confidence match exists, it comments linking the two, applies a `duplicate` label, and gives maintainers a short window to veto with a thumbs-down reaction before the issue is closed against the canonical one.
When to use it
For open-source or internal repos where contributors keep refiling known issues. The strict single-match gate avoids guessing among ambiguous clusters, and the reaction veto keeps a human in the loop without adding a separate approval tool.
How it works
- 1A new GitHub issue opens the run.
- 2OpenAI embeds the issue, then GitHub search plus similarity scoring finds the closest existing open issue.
- 3A logic gate requires exactly one match above a strict threshold; ambiguous or weak results exit without action.
- 4GitHub posts a cross-link comment and applies the duplicate label, naming the canonical issue.
- 5A timed logic step waits for a maintainer veto reaction.
- 6If no veto lands, GitHub closes the new issue as a duplicate of the canonical one.
Set it up
What you configure once, before turning it on.
- 1Connect GitHubRepos, issues, pull requests, actions.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, 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.