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.
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.
Let them say what went wrong in their own words before offering anything. Use their name, {{contact.name}}, once — not in every line.
Use @find_order to pull up the order they are talking about. Ask for the order number if they have it, otherwise the email they used.
Say plainly what our returns window is and where their order sits inside it, as of {{system.local_date}}. Do not promise an outcome you have not confirmed.
If a refund is the right remedy, say so and use @start_refund. If a replacement fits better, offer that first and explain why.
If they are still unhappy, or the order is outside anything you can settle, use @bring_in_teammate rather than repeating yourself.
Trusted by over 100+ businesses
⚡ lookup_order to retrieve the order details.⚡ payment_info to retrieve payment details.Most agents answer the question. A procedure gives yours the steps to finish it, the same way every time.
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.
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.
A policy changes on Monday. Edit the step, re-run your tests, and every conversation follows the new rule. No sprint, no ticket.
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.
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.
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.
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.
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.
Outside a procedure the agent reasons freely. Inside one it follows your steps. You choose which is which.
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.
Here's your current plan.
Issue the refund, change the booking, update the subscription across all three systems.
Hey, I got the wrong size on order #84213
lookup_ordercheck_inventorycreate_exchangeescalateRun the procedure against real scenarios and watch each step execute, including the branches you hope nobody hits.
Pull the order from Shopify or the invoice from Stripe, right where it’s needed.
What comes back from one step shapes the next, not what the customer said.
Where a human should sign off, it stops, asks, and continues on approval.
Refunds, identity checks, billing disputes, bookings. Ready to adapt to how you work.
Save your scenarios and re-run the whole set on every edit.
Which steps ran, which conditions were met, and what each lookup returned.
Check eligibility against your policy, offer the exchange first, issue the label, confirm the timeline.
Confirm who you’re speaking to before anything sensitive is shared, with the checks your policy requires and an escalation path when they fail.
Compare what they have with what they're asking for, apply the proration rules, take the change and confirm what happens next.
Help users reset passwords to securely regain account access.
Where is my order?Passed
How do I track my shipment?Passed
Can I get a refund on a sale item?Passed
How long do refunds take to process?Passed
Do you offer installment plans or financing?Passed
Do you refund shipping costs on returns?Passed
How do I cancel a subscription?Failed
Can I exchange my order?Passed
Where is my return label?Passed
Show me the latest collection…
Checked data sourcesReturn Policy
Procedure: Order return & refundShopify Get Order
Action: Generate Return LabelHere are 3 products…
Orange sneaker
Pastel sneakerEnhance Guzli by simplifying workflows and linking your preferred apps, with fresh integrations added regularly.
Read customer story“Figuring out what to automate and what needs a human — Guzli has been a great partner.”
Read customer story“Figuring out what to automate and what needs a human — Guzli has been a great partner.”
Read customer story“A genuinely capable clinical tool, deployed without an engineering team.”
Read customer story“A genuinely capable clinical tool, deployed without an engineering team.”
Read customer story“Guzli really enables us to control AI without letting AI control us.”
Read customer story“Guzli really enables us to control AI without letting AI control us.”
Guzli is committed to delivering the top customer support platform for those who demand excellence.
We follow industry-leading compliance standards and best-in-class encryption protocols to keep your customer data safe.
Full compliance with EU data protection standards.
Independently audited for security and reliability.
Built to handle protected health information safely.
Your data is only accessible to your AI agent and not used to train models.
Data is encrypted at rest and in transit using standard algorithms.
We use verified variables to ensure users access their own data.
A written set of steps your agent follows for a specific situation, the same way an SOP guides a teammate. You describe when it applies, what to check, what to ask and what to do, and the agent works through it the same way every time.
No. You write the steps in plain English. Where a step needs data or a system, you attach a lookup or an action to that step, and the rest stays ordinary writing.
Each procedure says when it applies, in its own first lines. The agent matches the customer's situation against those conditions and picks the procedure that fits, so you never script which one appears where.
Yes. Steps can pull live data (an order, a booking, an account) and run actions in your connected systems (issue the refund, change the booking, update the subscription). The agent runs them at the step where they belong.
The agent handles it. Customers interrupt, change their mind and trail off; the agent answers what came up, then picks the procedure back up at the right step instead of starting over.
Yes. Run it in a preview conversation and watch it work through the steps, including the lookups and actions, so you see it run before a customer does.
One agent across the whole platform. The same knowledge, the same brand voice, wherever the conversation goes.
Join thousands of teams using Guzli to build AI agents that deliver exceptional support at scale — across chat, email, and voice.