Human Review

Catch risky or important messages and route them to your team — notify staff, pause the AI, or hand over the conversation.

Human Review#

Some messages shouldn't be left to the AI alone — an angry customer, a legal question, a big order, a VIP. Human Review lets you set rules that watch your incoming messages, comments, reviews, and emails, then take the right action: notify your team, pause the AI, hand the conversation to a human, or draft a careful reply for approval.

Find it under Automations > Human Review.

How It Works#

Human Review sits on top of everything your agent handles. When a new message, comment, review, or email comes in, your rules decide whether it needs a person.

Code
New message / comment / review / email
            |
    Matches a Human Review rule?
            |
   ┌────────┴─────────┐
  Yes                 No
   |                   |
Take action:      Agent replies
- Notify team       as normal
- Pause AI
- Hand over
- Draft a safe reply

Anything flagged shows up in the Activity workspace under Needs Attention, and your team is notified on the channels you've set up.

The Two Tabs#

Rules#

Create and manage the conditions that route work to humans.

  • Filter by source — apply rules to all channels, or just Messages, Comments, Reviews, or Email
  • Condition — what to watch for (keywords, tone, or the type of request)
  • Action — notify staff, pause the AI, hand over the conversation, or prepare a draft reply
  • History — an audit trail of which rules fired and when

Suggestions#

AlonChat reviews recent conversations and suggests rules you might be missing — patterns that look like they should be escalated. Review each suggestion and accept the ones that fit your business.

What These Rules Are (and Aren't)#

Human Review is AlonChat's attention routing layer — it decides what happens when something notable occurs. It is not, by itself, a support ticket or a permanent handover. Depending on your rules, a flagged event can simply notify you, pause the AI for one conversation, or — if you use it — create a Help Desk ticket for your team to own.

Best Practices#

  1. Start with the obvious risks — complaints, refunds, "speak to a human", legal/medical questions.
  2. Use Suggestions — let AlonChat surface patterns you didn't think to add.
  3. Pair notify + pause for sensitive topics so the AI doesn't keep replying while a human steps in.
  4. Review the history weekly to tune rules that fire too often or not enough.

Related Pages#