Escalations & Routing

Not every email can be handled by an AI agent. Complex issues, angry customers, or requests outside the agent's scope need human attention. Escalations let you route these cases to the right team member.

When to Escalate

Your agent should escalate when:

Unclear Intent: The email doesn't match any known category
Angry Customer: The message reads as frustrated, upset, or threatening
Complex Request: The issue requires human judgment
Out of Scope: The request is outside the agent's defined responsibilities
Escalation Keyword: The customer explicitly asks to speak with a human

Setting Up Escalation Rules

Step 1: Define Escalation Triggers

In your agent's settings, go to Escalation Rules and define when to escalate:

Tone-based

Escalate if the customer sounds angry, frustrated, or threatening
Escalate if the email contains words like "angry," "frustrated," "unacceptable"

Keyword-based

Escalate if email contains: "speak to a human," "manager," "complaint"
Escalate if subject contains: "URGENT," "CRITICAL," "COMPLAINT"

Category-based

Escalate if the email doesn't match any known category
Escalate if the request falls outside the agent's stated scope

You can write these as plain-language guidance (the agent interprets it), or add structured rules that match on the sender, keywords, or a dollar amount and always fire regardless of how the agent reads the message.

Step 2: What happens when an escalation triggers

When a rule escalates a message, the agent holds its reply for your review and notifies you — the agent's admin. You get:

A push notification on your devices
An entry on the Escalations view in the dashboard, showing the sender, subject, and the reason it was flagged
An optional text to your admin number — toggle "notify by SMS on escalation" in the agent's settings

A structured rule can also choose a softer action instead of a full escalation:

Escalate — hold the reply and notify you (above)
Draft only — write the reply but hold it for your approval
Notify admin — send the reply and let you know it happened
Auto-handle — let the agent proceed normally

Escalations are not forwarded to an arbitrary inbox, a Slack channel, or a customer webhook — they go to you, the agent's admin, through the notifications above.

Step 3: Add Context

Include context in the escalation:

Escalate if:
- [Condition 1]
- [Condition 2]
- [Condition 3]

Types of Rules

Keyword-based:

Escalate if the email mentions: refund, lawsuit, legal, complaint, angry, urgent

Tone-based:

Escalate if the customer seems very angry, frustrated, or threatening

Domain-based:

Escalate if the question is about pricing, contracts, custom solutions, or integrations

Priority-based:

Escalate if the sender is a VIP customer, enterprise client, or repeat escalator

Combination:

Escalate if:
- Customer mentions refund AND amount is over $500
- Email is from a VIP client
- Issue requires technical/engineering knowledge
- Customer has escalated before on this topic

Real-World Examples

Customer Support Agent

Good escalation rules:

Escalate if:
- Customer mentions refund, chargeback, or legal action
- Customer is very angry or threatening
- Issue requires technical/engineering knowledge
- Customer has contacted us 3+ times about the same issue
- Request is for a feature we don't have
- Customer mentions competitor or switching

Why these work:

Specific keywords (refund, legal, chargeback)
Tone detection (angry, threatening)
Domain-specific (technical issues)
Pattern recognition (repeat contacts)
Business logic (feature requests)

Sales Agent

Good escalation rules:

Escalate if:
- Prospect asks for custom pricing or enterprise terms
- Prospect mentions a competitor
- Deal size is over $50,000
- Prospect asks about integrations we don't support
- Prospect is from a Fortune 500 company
- Prospect mentions legal/contract concerns

Why these work:

High-value deals need human touch
Competitor mentions need strategy
Enterprise deals need special handling
Legal issues need legal review
Custom requests need sales expertise

Operations Agent

Good escalation rules:

Escalate if:
- Request involves data deletion or privacy
- Request is from a customer with pending issues
- Request requires manager approval
- Request involves refunds or credits
- Request mentions compliance or regulations

Best Practices

1. Start Broad, Then Narrow

Week 1: Escalate everything while you learn

Escalate if: anything seems unusual or important

Week 2: Escalate specific categories

Escalate if: customer is angry OR mentions refund OR issue is technical

Week 3+: Fine-tune based on patterns

Escalate if: [specific, tested rules]

2. Be Specific, Not Vague

❌ Too vague:

Escalate if customer seems confused
Escalate if issue is important
Escalate if something seems wrong

✅ Specific:

Escalate if customer asks about features we don't have
Escalate if customer mentions refund or legal action
Escalate if issue requires technical expertise