CHATBOTS

Log resolved Discord support threads to Postgres analytics

When a support thread is marked resolved, it summarizes the question, the answer, and the ReadMe source used, then writes a structured row to Postgres for deflection analytics.

CategoryChatbots
Enginesim
Difficultyintermediate
Triggerevent
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerResolved reaction or tag added to Discord threadDiscordDiscord
  • ActionFetch full thread message historyDiscordDiscord
  • ActionSummarize question, answer, and cited docOpenAI
  • LogicClassify topic and resolver (bot vs human)
  • OutputInsert analytics row into PostgresPostgreSQLPostgres

What it does

When a Discord support thread gets a resolved reaction or tag, this flow captures the full exchange, summarizes the question and the resolution, records which ReadMe page was cited, and stores it as one analytics row in Postgres. Over time you get a queryable record of what developers ask and which docs actually resolve issues.

When to use it

Run this when you need hard numbers on bot deflection rate, top question topics, and which docs are doing the heavy lifting. It feeds dashboards and informs where to invest documentation effort.

How it works

  1. 1A resolved reaction or tag added to a Discord thread triggers the run.
  2. 2The flow fetches the thread's full message history.
  3. 3An LLM step summarizes the question, the resolving answer, and extracts the cited ReadMe page if present.
  4. 4A logic step classifies the topic and whether the bot or a human resolved it.
  5. 5The flow inserts a structured row into the Postgres analytics table with timestamps and topic tags.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect DiscordCommunity channels + voice + bots.
  2. 2
    Connect PostgresAny Postgres URL — query, write, migrate.
  3. 3
    Connect OpenAIModels, embeddings, files.
  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.