TICKET MANAGEMENT

Deduplicate Discord bug reports against existing Linear issues

Before creating anything, searches Linear for issues matching a new Discord bug report; if a duplicate exists it comments and links the report there, otherwise it opens a fresh…

CategoryTicket Management
Enginesim
Difficultyadvanced
Triggerevent
Steps6
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerNew bug report in Discord channelDiscordDiscord
  • ActionSummarize and extract search keywords with LLMOpenAI
  • ActionSearch Linear for matching open issuesLinearLinear
  • LogicDecide if a true duplicate exists
  • ActionComment on duplicate or create new Linear issueLinearLinear
  • OutputReply in Discord thread with canonical issue linkDiscordDiscord

What it does

Prevents duplicate Linear issues from a busy Discord channel. When a new bug arrives, an LLM distills it into search terms, the flow queries open Linear issues, and the model judges whether any existing issue is the same bug. If so, it adds a comment with the new reporter's details and reuses that issue. If not, it creates a new, properly structured issue. The Discord thread is updated either way.

When to use it

Use it when popular bugs get reported many times and your Linear board fills with near-identical issues. This keeps reporter signal attached to a single canonical issue and saves triagers from manual merging.

How it works

  1. 1A new Discord bug message triggers the flow.
  2. 2An OpenAI call extracts a normalized summary and candidate search keywords.
  3. 3The flow searches Linear for open issues matching those keywords.
  4. 4A logic step asks the model whether a returned issue is a true duplicate.
  5. 5If duplicate, it comments the new context on the existing Linear issue; otherwise it creates a new structured issue.
  6. 6It replies in the Discord thread with the canonical issue link.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DiscordCommunity channels + voice + bots.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect LinearIssues, projects, cycles, triage.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.