AI agents that answer your service helpline, call owners before a warranty ends, and help your technicians at the customer's door, in more than 25 languages. They work from the registered product, the warranty and the service history, and finish the task during the call: raise the ticket, book the visit, reserve the part, send the payment link. Tilicho builds and runs them inside your own Google Cloud project, starting from accelerators for 23 consumer-durables use cases.
The helpline, the field and the warranty base, each with its own agent. All three read and write the same customer, product and ticket record, so one integration supports all three.
The customer calls the helpline. The agent finds the registered product, checks the warranty, any protection plan and any open ticket, and takes the call forward from there.
The technician calls from the customer's home and says the customer's phone number. The agent reads out the history, the likely faults and where the part is in stock.
The agent calls owners who have consented, before the warranty ends. A problem becomes a service ticket; no problem becomes an extended protection plan (service contract) offer priced for that model and age.
The number is matched to the customer's registered products: model, serial, install date, warranty or protection plan status, open tickets and past visits. Before an outbound offer call, the consent record, the Do Not Call lists and the local time are checked.
The agent confirms the product, takes the symptom or the error code, tries the fix the customer can do, and raises the ticket, books the slot or sends the payment link while the customer is on the line.
A smell of gas, sparks or burning, a repeat failure, a refund demand or any request for a person goes to your team live, with the product, the history and the summary on screen.
Ticket, outcome tag, transcript and recording are written to your CRM and service system. The visit reminder, the payment follow-up or the feedback call is scheduled.
Each agent starts from an accelerator, so a use case is on live calls in about one month.
The opening is fixed in the script. It is the same on every call, in every language.
On an outbound call the agent confirms it is speaking to the registered owner before it names the product.
Your brand's name and the purpose of the call, in the words your team approved.
The agent says it is an AI assistant and that the call is recorded.
Only then does the script move to the product, the problem or the plan.
Offer and renewal calls are placed only inside the hours you set, in the customer's local time, for example 8 am to 9 pm, the window the TCPA rules set for telemarketing calls. The helpline answers at any hour.
Offer and renewal calls are telemarketing. Since the FCC ruled in February 2024 that AI-generated voices are artificial under the TCPA, these calls go only to owners who gave prior express written consent. Numbers on the National Do Not Call Registry and your own do-not-call list are checked. Service calls the customer asked for are not telemarketing.
A technician hears a customer's details only for a job assigned to them. A phone number alone opens nothing.
PII is masked in transcripts and logs. Access is by role. The agent never asks for a full card number, a one-time code or a password.
The agent runs in your Google Cloud project, in a US region. Recordings and customer data stay in your storage.
A smell of gas: the agent tells the customer to leave the home and call the gas utility or 911 from outside, then puts the call through to a person. Sparks or burning: switch off at the breaker, then a person.
The agent runs in the Google Cloud region closest to your customers. This is fixed before the build, since reply time cannot be tuned afterwards.
The agent mirrors the customer turn by turn, so it follows the customer's language and not a setting.
A supervisor routes to small agents that share the state of the call. The script grows by adding agents.
A health-checked fallback model in the same region takes over mid-call, with the state of the call intact.
Your team member sees the product, the history, the transcript summary and the captured details before speaking.
An analyzer agent keeps each ticket open until it reaches an end state: fixed, paid, renewed, or handed to your team.
Anything not on this list, including your service, inventory or SAP system, is connected through its API during setup. Tilicho builds and maintains it at no extra cost.
More than 25 languages, including English, Spanish, Mandarin, Vietnamese, Tagalog, Korean, Arabic, French, Russian and Portuguese. The agent switches language during the call when the customer does, such as from Spanish to English.
The agent asks for the serial number from the product label, or the ZIP code and the name, and finds the product that way before it goes further.
No. The technician is identified by the registered phone and technician ID, and the agent reads out a customer's details only for a job assigned to that technician.
The call is transferred live to your team with the product, the history and the summary, so the customer does not repeat the case. You decide which cases always go to a person, such as safety issues and refund demands.
Yes, when the owner has given prior express written consent to calls with an AI voice, inside the calling hours, and after the Do Not Call lists are checked. The agent says it is an AI assistant at the start of every call.
In your own Google Cloud project and your storage. Tilicho runs the agent inside that project.
No. The agent connects to your existing numbers and systems. There are more than 50 integrations, and other systems, such as SAP, are connected through their APIs during setup.
A 30-minute session: a live call with the agent, then a walk through one use case of yours, such as the service helpline, technician assist or protection plan renewals.