CUSTOMER SUPPORT

Turn resolved Intercom chats into Confluence draft articles

When an Intercom conversation closes, detects whether the resolved question is already covered in Confluence and, if not, drafts a new Confluence page from the agent's reply…

CategoryCustomer Support
Enginesim
Difficultyintermediate
Triggerevent
Steps6
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerIntercom conversation closedIntercomIntercom
  • ActionSummarize question + resolution with OpenAIOpenAI
  • ActionSearch Confluence for matching pageConfluenceConfluence
  • LogicBranch: no strong page match?
  • ActionDraft Confluence page from resolved replyOpenAI
  • OutputCreate draft page and notify SlackSlack

What it does

Bridges Intercom support chats and your Confluence knowledge base. Each closed conversation is screened against existing Confluence content; if the question has no home in the docs, the workflow writes a clean draft page from the resolved chat so knowledge stops living only in agents' heads.

When to use it

Reach for this when your team runs support in Intercom but maintains its help docs in Confluence, and resolved chats routinely contain answers that never make it into the wiki.

How it works

  1. 1An Intercom conversation is marked closed, triggering the flow.
  2. 2OpenAI summarizes the customer's question and the agent's resolution.
  3. 3The workflow searches Confluence for a page that already covers the topic.
  4. 4A branch checks whether any existing page is a strong match.
  5. 5When no page qualifies, OpenAI generates a structured draft page from the resolved reply.
  6. 6The draft is created in a Confluence review space and a notice is sent to Slack.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect IntercomConversations, contacts, articles.
  2. 2
    Connect OpenAIModels, embeddings, files.
  3. 3
    Connect ConfluenceSpaces, pages, blueprints.
  4. 4
    Connect SlackChannels, DMs, threads, mentions.
  5. 5
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  6. 6
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  7. 7
    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.