SUMMARIZATION

Resolved Discord thread to Linear feature request

When a feedback thread is marked resolved in Discord, summarizes the whole conversation, classifies it as bug or feature.

CategorySummarization
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerDiscord thread tagged resolvedDiscordDiscord
  • ActionFetch full thread with repliesDiscordDiscord
  • ActionSummarize and classify with OpenAIOpenAI
  • LogicCheck Linear for duplicate issueLinearLinear
  • OutputCreate or comment on Linear issueLinearLinear

What it does

It watches for feedback threads that get tagged as resolved or actionable in Discord, reads the entire thread, and produces a tight summary plus a classification (bug, feature request, or docs gap). That becomes a Linear issue with a clear title, the distilled context, and a link to the source thread — so nothing actionable evaporates after the conversation cools.

When to use it

Use this when your community discusses problems in long Discord threads but your engineering team works out of Linear. It closes the gap between "we talked about it" and "it's tracked."

How it works

  1. 1A Discord event fires when a thread receives the configured resolved tag.
  2. 2The workflow pulls the full thread, including replies and the original message.
  3. 3An OpenAI call summarizes the discussion, extracts the core request, and assigns a type and priority hint.
  4. 4A logic branch checks Linear for an existing open issue with a matching signature to avoid duplicates.
  5. 5If new, it creates a Linear issue with the summary, type label, and source link; if a match exists, it appends the new context as a comment.

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.