TICKET MANAGEMENT

SLA Pause Auditor: Open Linear Investigations for Repeat Pause-Gaming Agents

Weekly, aggregates flagged illegitimate pauses per agent and, when an agent crosses a repeat-offense threshold, automatically opens a Linear issue for the QA team…

CategoryTicket Management
Enginesim
Difficultyintermediate
Triggerschedule
Steps5
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires the aggregation
  • ActionPull per-agent pause violations for the week from BigQueryGoogle BigQueryBigQuery
  • LogicKeep only agents above the repeat-offense threshold
  • ActionCreate a Linear investigation issue per agent with evidenceLinearLinear
  • OutputPost summary of opened issues to SlackSlack

What it does

This turns scattered pause-gaming flags into accountable follow-up. Once a week it tallies how many times each agent paused the SLA clock under 'waiting on customer' while the customer had actually replied. Agents below the tolerance threshold are ignored; agents above it get a Linear issue opened automatically in the QA/coaching team's queue, pre-filled with the offending ticket IDs, dates, and the paused minutes saved, so a manager has a complete evidence trail to act on.

When to use it

Use it when one-off Slack pings get lost and you need a tracked, assignable workstream for coaching or escalation, with a clear paper trail per agent.

How it works

  1. 1A weekly schedule fires the aggregation.
  2. 2Pull the week's audited pause violations per agent from BigQuery.
  3. 3Branch: keep only agents whose violation count exceeds the threshold.
  4. 4For each, assemble the evidence trail of tickets, dates, and paused minutes.
  5. 5Create a Linear investigation issue assigned to the QA team.
  6. 6Post a summary of issues opened to Slack.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect BigQueryDatasets, queries, schemas.
  2. 2
    Connect LinearIssues, projects, cycles, triage.
  3. 3
    Connect SlackChannels, DMs, threads, mentions.
  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.