CUSTOMER SUPPORT
Score Zendesk bug tickets on repro completeness and auto-request missing fields
Grades every inbound Zendesk bug ticket on how reproducible it is (steps, expected vs actual, environment, version, frequency) and, when the score is too low, replies…
How it runs
The automated pipeline, trigger to output.
- TriggerNew Zendesk ticket tagged 'bug'Zendesk
- ActionExtract repro fields and compute score (LLM)OpenAI
- LogicBranch: repro score below threshold?
- ActionReply requesting missing fields, set on-holdZendesk
- OutputTag repro-verified and route to agent queueZendesk
What it does
Every new Zendesk ticket tagged as a bug is parsed and scored against a fixed reproducibility rubric: clear steps to reproduce, expected result, actual result, environment/OS, app version, and how often it happens. The workflow assigns a 0-100 repro score and either lets the ticket flow to agents or holds it and asks the customer for only the missing pieces.
When to use it
Use it when agents waste the first reply round-tripping for basic repro details. It front-loads that collection so tickets land on the queue already actionable.
How it works
- 1A new or updated Zendesk ticket tagged `bug` triggers the run.
- 2An LLM extracts each rubric field from the ticket body and computes a weighted repro score plus the list of missing fields.
- 3A branch checks the score against a threshold (default 70).
- 4If below threshold, Zendesk posts a public reply naming exactly the missing fields and applies a `needs-repro` tag and on-hold status.
- 5If at or above threshold, the ticket is tagged `repro-verified` and routed to the agent queue untouched.
Set it up
What you configure once, before turning it on.
- 1Connect ZendeskTickets, queues, knowledge base.
- 2Connect OpenAIModels, embeddings, files.
- 3Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 4Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 5Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Customer Support workflows
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.
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.
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.
Tell Intercom users their reported bug shipped after a Vercel deploy
On a successful Vercel production deployment, match the release's resolved Sentry issues to Intercom conversations and message each affected user that their reported issue is…
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.