> ## Documentation Index
> Fetch the complete documentation index at: https://docs.duckie.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Rollout Plan

> Move ticket triage from shadow mode to live tagging and routing

Ticket triage is a good candidate for staged rollout. Start by observing and recommending, then gradually turn on helpdesk writebacks as confidence improves.

## Rollout Stages

<Steps>
  <Step title="Model the support taxonomy">
    Start with a small set of intents, product areas, urgency levels, routes, and missing-context categories. Use historical tickets and support team feedback to define the initial values.
  </Step>

  <Step title="Build context enrichment">
    Connect read-only tools for helpdesk, CRM, subscription, product, order, incident, and prior-ticket context. Produce a stable context bundle before classification.
  </Step>

  <Step title="Run shadow classification">
    Create the ticket triage deployment in **Testing** mode. Have Duckie classify tickets and recommend tags without writing to the helpdesk.
  </Step>

  <Step title="Compare against human triage">
    Review a sample of tickets by intent, route, customer segment, and confidence band. Track where humans changed tags or routes.
  </Step>

  <Step title="Enable low-risk writebacks">
    Turn on internal notes, shadow tags, or custom fields first. Avoid assignment, priority, and SLA changes until the team trusts the routing rules.
  </Step>

  <Step title="Enable live routing for known paths">
    Start with high-confidence intents that have simple deterministic routes, such as billing questions, access issues, or known-incident updates.
  </Step>

  <Step title="Add escalation and daily reporting">
    Route low-confidence or high-risk tickets to a Slack escalation agent, and schedule a Duckie Assistant reporting agent for stakeholder visibility.
  </Step>

  <Step title="Review and expand">
    Use a Duckie Assistant feedback agent to review corrections, reroutes, and failures. Expand the taxonomy and routing rules only after replay testing.
  </Step>
</Steps>

## Testing Plan

Use historical tickets before live routing:

* Replay tickets across all major intents and channels
* Include edge cases with missing account matches, angry customers, priority accounts, and known incidents
* Compare Duckie tags and routes against human-applied tags
* Review low-confidence cases separately
* Verify that helpdesk writebacks use only allowed values
* Confirm that escalation requests are concise and answerable
* Run batch tests after every taxonomy or routing change

## Success Metrics

Track:

* Percent of tickets triaged automatically
* Classification confidence by intent
* Human correction rate
* Reroute rate after initial assignment
* Time to first assignment
* SLA-at-risk tickets
* Missing context rate
* Escalation volume and resolution time
* Helpdesk writeback failures
* Support team satisfaction with handoff notes

## Launch Guardrails

Start conservatively:

* Require human review below a confidence threshold
* Keep sensitive categories out of live routing at first
* Use allowlists for helpdesk tags, queues, priorities, and custom fields
* Limit write tools to the smallest required scopes
* Keep assignment and SLA changes behind explicit workflow branches
* Post daily reports during rollout
* Review reroutes and corrections weekly

<Info>
  The safest first live action is usually an internal note with Duckie's suggested intent, tags, route, and reasoning. Assignment and SLA updates can come later.
</Info>

## Related Docs

<CardGroup cols={2}>
  <Card title="Deployment Modes" icon="toggle-on" href="/deployments/deployment-modes">
    Move from Testing to Live when the triage path is ready.
  </Card>

  <Card title="Batch Testing" icon="flask" href="/testing/batch-testing">
    Evaluate changes across groups of historical tickets.
  </Card>

  <Card title="Alerts" icon="bell" href="/analytics/alerts">
    Notify the team when triage failures or SLA risks appear.
  </Card>

  <Card title="Guardrails" icon="shield" href="/guardrails/overview">
    Control risky or sensitive behavior.
  </Card>
</CardGroup>