CUSTOMER SUPPORT
Detect Front conversations with no matching doc and draft the missing article
When a Front conversation is resolved, checks whether the customer's question maps to an existing knowledge base article and, if none exists, drafts a new Notion article seeded…
How it runs
The automated pipeline, trigger to output.
- TriggerFront conversation resolvedFront
- ActionExtract canonical question + resolution with OpenAIOpenAI
- ActionSearch Notion knowledge base for a matchNotion
- LogicBranch: relevance score below threshold?
- ActionDraft new article from resolved reply with OpenAIOpenAI
- OutputCreate draft in Notion 'Needs review' databaseNotion
What it does
Closes the gap between answered tickets and documented knowledge. Every time a support conversation is resolved in Front, the workflow extracts the underlying question, searches your Notion knowledge base for a matching article, and when nothing relevant exists it drafts a brand-new article using the agent's winning reply as the source of truth.
When to use it
Run this when your team keeps answering the same questions in tickets but the help center never catches up. It turns resolved conversations into a steady pipeline of draft articles instead of relying on agents to remember to write docs.
How it works
- 1A Front conversation is moved to resolved, triggering the flow.
- 2OpenAI distills the conversation into a single canonical question and the resolution summary.
- 3The workflow searches Notion for an article that already answers that question.
- 4A branch checks whether the top match clears a relevance threshold.
- 5If no match qualifies, OpenAI drafts a structured article (title, problem, steps, answer) from the resolved reply.
- 6The draft is created in a Notion "Needs review" database for an editor to approve.
Set it up
What you configure once, before turning it on.
- 1Connect FrontShared inbox, conversations.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect NotionPages, databases, comments.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Customer Support workflows
Close the loop with requesters when a Linear bug moves to Done
When a Linear issue created from a support escalation moves to Done after deploy, look up the originating Zendesk tickets and notify each requester that their reported bug is…
Reopen and notify Front conversations when their bug fix deploys
When a deploy resolves a Sentry issue, find the snoozed or closed Front conversations linked to it, reopen them, and send the customer a reply that the fix is now live.
Suggest the right Loom video by classifying Intercom message intent
Reads each new inbound Intercom conversation, classifies what the customer is trying to do, and surfaces the best-matching Loom walkthrough to the agent as an internal note.
Draft personalized fix-live replies for support to review
When a Sentry issue resolves, an agent reads each linked ticket's full thread and drafts a tailored 'your fix is live' reply per requester.
Send a tailored Loom onboarding sequence on Front first-reply
When a new customer's first email lands in Front, this picks the Loom onboarding walkthroughs matching their plan and use case, builds a friendly sequenced reply.
Article Volume-Rebound Early Warning (Datadog)
Streams support ticket-tag events into Datadog, watches for topics whose volume is reaccelerating against a decaying article.
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.