CUSTOMER SUPPORT
Suggest the best macro by matching tickets against Help Center articles
Embeds new Zendesk tickets, retrieves the most relevant Help Center articles and macros, and recommends a grounded macro with a citation when there is a strong match.
How it runs
The automated pipeline, trigger to output.
- TriggerNew Zendesk ticket createdZendesk
- ActionEmbed ticket text with OpenAIOpenAI
- ActionRetrieve nearest articles and macros from PostgresPostgres
- LogicGate on retrieval similarity score
- ActionSelect best macro from candidates with OpenAIOpenAI
- OutputPost cited macro recommendation as an internal noteZendesk
What it does
This is a retrieval-augmented triage flow. New tickets are embedded and matched against a vector index of your Help Center articles and macro library stored in Postgres. When a confident match exists, the workflow suggests the specific macro and cites the supporting article, so agents trust the recommendation and reuse approved language.
When to use it
Use this when keyword tagging is too blunt and you want recommendations grounded in your actual documentation. Best for teams with a mature knowledge base who want macro suggestions backed by a source link rather than a guess.
How it works
- 1A new Zendesk ticket triggers the workflow.
- 2OpenAI creates an embedding of the ticket subject and body.
- 3An action queries the Postgres vector store for the nearest articles and macros.
- 4A logic step checks similarity; weak matches are tagged `no-confident-macro` and stop.
- 5OpenAI selects the single best macro from the retrieved candidates.
- 6The output posts the recommended macro plus the cited article link as an internal note in Zendesk.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 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.