Train your agent
the
way you
train a teammate

Write your procedures in plain English, the same way you'd write an SOP. Add the conditions, the lookups and the actions, and your agent follows them the same way every time.

Create agent Get a demo

Procedures

My procedures

Templates

Search...

Status

Lead qualificationScores inbound leads by budget, role, and intent signals.

Active

Demo booking flowGuides prospects to schedule a product demo with the sales team.

Active

Pricing inquiry handlerResponds to pricing questions and routes high-intent leads to a rep.

Inactive

Objection responseAddresses common objections around cost, timing, and competitors.

Inactive

Onboarding welcomeGreets new sign-ups and prompts their first key actions.

Active

Support escalationDetects frustration signals and hands off to a human agent.

Draft

Upsell & Cross-sellIdentifies upgrade opportunities and presents relevant plan offers.

Draft

Churn preventionTriggers on cancellation intent and offers retention incentives.

Inactive

Follow-up sequenceRe-engages cold leads 48 hours after initial contact.

Active

Search...

Status

E-commerce

Order return & refundHelp customers return items and confirm refunds or replacements.

Order status lookupCheck order details and give real-time shipping status.

Cancel subscriptionHandle cancellations, capture reason, confirm or offer alternatives.

Product exchangeHelp customers exchange items for different sizes or colors.

Support

Gift card balance inquiryShow gift card balance and how to use it at checkout.

Account password resetHelp users reset passwords to securely regain account access.

Urgent issue / outage reportTriage system outage reports and create high-priority support tickets.

Billing

Account cancellationManage account closure, confirm intent, and ensure data removal or export.

Loyalty program enrollmentHelp customers join loyalty programs and explain membership benefits.

Ask

Sales agent

Good evening, John

What would you like to do today?

This week your AI agent handled 1,247 conversations, with automation up 4.2%↑. The biggest theme was pricing and billing questions, followed by account setup. Escalations rose slightly, driven by API integration errors that may benefit from an updated help article.

Summarize issues customers are facing

Suggest improvements from conversations

Add a new text based data source

Insights

Conversations87%

Escalation rate18%

Customer success score81

Suggestions

Add an action to automate issuing refund credits to users.

Resolution rate by ~15%

Trusted by over 10000+ businesses

4.8

1.Greet customer and ask how to help.

2.Ask for order number or email to locate order.

3.Use lookup_order to retrieve the order details.

4.Confirm which item the customer wants to return.

5.Check the return window eligibility.

6.Check the customer information.

7.Use payment_info to retrieve payment details.

The difference between answering and doing

Most agents answer the question. A procedure gives yours the steps to finish it, the same way every time.

Complex tasks, handled end to end

A refund with eligibility rules, a plan change with proration, a claim that needs three checks. Too involved for an answer, too routine for a person.

The same way every time

Two customers with the same problem get the same process. Not a similar answer, the same steps, in the same order, with the same checks.

Change it in minutes

A policy changes on Monday. Edit the step, re-run your tests, and every conversation follows the new rule. No sprint, no ticket.

Written like language, run like logic

Every support team already has procedures, in a Google Doc or in the head of whoever has been there longest. Procedures are the same, except your agent follows them.

Write it like you'd write it for a person

Numbered steps in plain English. "Ask for the order number." "Check whether it's inside the return window." Anyone who can brief a new hire can write one.

Conditions and branching

If the order is inside the return window, do this. If it isn't, do that. Real conditional logic, written as a sentence rather than assembled from blocks.

Steps that must happen

Verify identity before showing an account. Check eligibility before promising a refund. Mark a step as required and the agent can't skip past it to reach a faster answer.

Limits at the step level

Set what the agent can decide alone, what needs approval and what always goes to a person. Different rules for a $10 refund and a $500 one.

No improvisation inside a procedure

Outside a procedure the agent reasons freely. Inside one it follows your steps. You choose which is which.

Anyone can read what it will do

A procedure isn't hidden behind a canvas or a config screen. Compliance, a new manager or a lawyer can read the steps and know exactly what the agent does before it does it.

Everything your agent can do, out of the box

Here's your current plan.

Your subscriptions

Hobby+2

40.00 USD /m

Renews on April 12, 2025

Cancel plan

Update plan

Takes the action

Issue the refund, change the booking, update the subscription across all three systems.

Hey, I got the wrong size on order #84213

Thinking

Checked data sources

Return PolicyProduct Warranty Guide

Procedure: Order exchange

lookup_ordercheck_inventorycreate_exchangeescalate

See it run

Run the procedure against real scenarios and watch each step execute, including the branches you hope nobody hits.

Looks it up

Pull the order from Shopify or the invoice from Stripe, right where it's needed.

Branches on data

What comes back from one step shapes the next, not what the customer said.

Pauses for approval

Where a human should sign off, it stops, asks, and continues on approval.

Start from templates

Refunds, identity checks, billing disputes, bookings. Ready to adapt to how you work.

Regression tested

Save your scenarios and re-run the whole set on every edit.

Reads the trace

Which steps ran, which conditions were met, and what each lookup returned.

The procedures most teams need, ready to adapt

Process a return or refund

Check eligibility against your policy, offer the exchange first, issue the label, confirm the timeline.

Verify a customer's identity

Confirm who you're speaking to before anything sensitive is shared, with the checks your policy requires and an escalation path when they fail.

Change/cancel a subscription

Compare what they have with what they're asking for, apply the proration rules, take the change and confirm what happens next.

Account password reset

Help users reset passwords to securely regain account access.

See it run before a customer does

Simulate it

Talk over it, cut it off mid-sentence, change your mind or trail off. It stops, listens and picks up the thread, instead of finishing its sentence or starting its script again.

Save the conversations that matter as scenarios and re-run the whole set on every edit, so a fix for one case can’t quietly break another.

Every run shows which steps executed, which conditions were met and what each lookup returned, so when something looks off you can see exactly why.

Regression test every change

Read the trace

Talk over it, cut it off mid-sentence, change your mind or trail off. It stops, listens and picks up the thread, instead of finishing its sentence or starting its script again.