Skip to main content
Reduce manual work with automation rules that react to ticket events. Review AI-generated replies before they’re sent so you stay in control of the customer experience.

​
What it does

Automations:
  • Trigger events — react to ticket creation, status changes, replies, assignment, SLA escalation, invoice generation, CSAT received, or a quote being accepted/declined
  • Conditions — match on priority, status, category, contact email, company, and more
  • Actions — auto-assign, change priority, update status, add internal notes, send notifications, or send a webhook
  • Rule priority — execute rules in order; stop processing after a match if enabled
  • Execution logs — view every time a rule ran, whether it matched, and what it did
AI Reviews (admin-only):
  • Pending reviews — see tickets where a technician has already acted on an AI draft, sorted by confidence (lowest first), awaiting a manager’s confirm-or-override
  • Manager confirm/override — mark the tech’s decision Correct, or override it with Override: AI Was Right / Override: AI Was Wrong
  • Audit trail — every review is written to the audit log, and Recent Reviews shows the tech’s action next to the manager’s

​
How to create an automation rule

1

Open Automations and click New Rule

In the PSA module sidebar, click Automations, then click New Rule.
2

Name and describe the rule

Enter a name (e.g. “Auto-assign Critical tickets to Tom”) and optional description.
3

Choose a trigger event

Ticket Created, Ticket Status Changed, Ticket Reply Added, Ticket Assigned, SLA Escalation, Invoice Generated, CSAT Received, or Quote Decided.
4

Add conditions (optional)

Click + Add Condition. For each, choose a field (e.g. Priority), operator (Equals), and value (CRITICAL). All conditions must match for the rule to execute.
5

Add actions

Click + Add Action. Choose: Assign Ticket, Change Priority, Change Status, Add Internal Note, Send Notification, or Send Webhook. Configure the payload (e.g. which technician).
6

Set priority and options

Lower Priority = executed first. Check Enabled to activate. Check Stop after match to prevent other rules from running if this one matches.
7

Save the rule

Click Create Rule.

​
How to test an automation rule

1

Open the rule

Find the rule in your Automations list.
2

Click the test icon

A dry-run executes the rule against a sample ticket. You’ll see the test ticket evaluated, which conditions matched, what actions would have executed, and a “Would Execute” / “Would NOT execute” summary.
3

Review and adjust

If the test shows unexpected behavior, edit the conditions or actions and test again.

​
How a technician handles an AI draft

On a ticket with a suggested reply, the technician reviews the draft text directly on the ticket (editing it in place changes nothing about the review process below — it’s just the reply text) and either clicks Send to Customer (then confirms with Confirm and Send, Send & Resolve, or Send & Close) or Discard. This decision — accepted as-is, edited, or discarded — is what later shows up as the “tech action” in AI Reviews.

​
How admin review works (AI Reviews)

AI Reviews is a retrospective quality-control page for admins, not a pre-send approval gate — by the time a ticket shows up here, the technician has already sent or discarded the reply.
1

Open AI Reviews

In the PSA sidebar, click AI Reviews (admin-only entry, near the bottom of the sidebar).
2

View pending reviews

The Pending Reviews card lists tickets whose AI draft was acted on by a technician but not yet reviewed by a manager, sorted by confidence (lowest first).
3

Open a ticket

Click a ticket to go to its detail page, where a Manager Review card shows the tech’s action (Accepted / Edited / Discarded / Auto-sent) and the AI’s confidence score.
4

Confirm or override

  • Correct — the tech’s decision was the right call.
  • Override: AI Was Right — the tech rejected or discarded a draft that was actually good.
  • Override: AI Was Wrong — the tech accepted a draft that was actually bad.
Overriding a rating updates that ticket’s stored quality score, which weights how likely it is to be pulled back in as an example for future AI drafts — it isn’t a fine-tuning or retraining step on the underlying model.

​
Understanding AI confidence

AI replies include a confidence score (0-100%) representing how sure the model is. Low scores mean the AI was uncertain — review carefully. Low confidence does not always mean wrong; high confidence does not guarantee correct. Always review the actual reply text and the ticket context before sending.

​
AI and ticket priority

The AI auto-analyzer suggests, never sets, ticket priority. The priority chosen at ticket creation — by the customer (portal or Teams bot), by the inbound-email classifier, or by the operator (manual UI) — is the sole source of truth.
This is a hard guarantee. A customer-submitted CRITICAL ticket will arrive in the PSA at CRITICAL regardless of what the AI’s per-ticket analysis suggests. Notification rules and SLA timers keyed on customer priority always fire correctly.
The Change Priority automation action listed in the rule-builder above is for operator-authored MSP rules. It does not represent AI behavior. Use it freely — your rules are policy you define, not AI judgment.

​
Automation Value

Automation Value (PSA sidebar → Automation Value) tracks how many technician-minutes each platform automation saves, so client reports can show the true value of auto-resolved work instead of just a ticket count. Every automation signal Regentra ships has a platform default — a reasonable estimate of how long the equivalent manual work would take. You can override any of them for your organization:
  • Browse Platform Defaults to see the default minutes for each automation signal.
  • Click Override to set your own manual minutes equivalent for your organization, plus an optional fixed hourly rate (otherwise the client’s own agreement rate is used).
  • Overridden signals show an Overridden badge; remove an override at any time to fall back to the platform default.
If a signal has no override and no platform default, Regentra falls back to a global default shown at the top of the page. Per-rule automations you build yourself (Settings → Automations) set their own minutes directly on the rule rather than through this page.

​
Frequently asked questions

No. Save the rule first, then use the test button. Drafts cannot be tested.
Rules execute in priority order (lower number = first). If a rule has Stop after match enabled, execution stops there. Otherwise all matching rules execute in sequence.
Yes. Click the play/pause icon next to the rule. It’s disabled immediately and won’t execute on new tickets.
Yes. AI Reviews is an after-the-fact quality check on drafts technicians already accepted, edited, or discarded — it does not gate whether a reply is sent. Automations execute immediately with no manual review either way.
Not in the sense of retraining the model. Marking a review Correct or Override updates that ticket’s stored quality score, which influences whether it’s pulled in as an example for future AI drafts (via retrieval), rather than fine-tuning the underlying AI model.