AI agents that call every admissions inquiry within minutes, help applicants finish the application and pay the deposit, and answer students and parents at any hour, in English, Spanish and more than 25 languages in all. They work from the inquiry, the application and the student record, and finish the task during the call: book the counselor call, send the upload or payment link, raise the request. Tilicho builds and runs them inside your own Google Cloud project, starting from accelerators for 24 education use cases.
The inquiry, the application and the enrolled student, each with its own agent. All three read and write the same student record, so one integration supports all three.
The agent calls every inquiry that consented to calls within minutes of the form. It confirms the program, the start term and the student's situation, answers from your published materials, and books a counselor call, an info session or a campus visit.
The agent calls applicants who stopped midway and admitted students who have not paid the deposit. It states what is pending, helps with what is stopping them, and sends the link before the deadline.
Students and parents call about billing, the schedule, grades, housing or the bus. The agent verifies the caller, answers from your records at any hour, in English, Spanish or the caller's language, and raises a request when your staff are needed.
The number is matched to the inquiry, the application or the student record: program, start term, stage, missing items, balance and past calls. Before an outbound call, the consent record, the do-not-call lists where they apply, the student's age and the local time are checked.
The agent confirms who it is speaking to, answers from your published materials and records, and books the appointment, sends the upload or payment link or raises the request while the caller is on the line.
A financial aid appeal, a complaint about staff, a disputed grade or any request for a person goes to your team live, with the record and the summary on screen. A student who sounds distressed or mentions self-harm is handed to a person at once.
Stage, outcome tag, transcript and recording are written to your CRM and student system. The reminder, the payment follow-up or the next 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 student, or to the parent or guardian for a student under 18, before it names the application or the balance.
Your institution'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 program, the application or the balance.
Outbound calls are placed only inside the hours you set, in the person'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.
Since the FCC ruled in February 2024 that AI-generated voices are artificial under the TCPA, outbound calls go only to people who gave prior express consent, and written consent where the call is telemarketing, such as a course offer. For telemarketing calls, the National Do Not Call Registry and your own do-not-call list are checked.
The agent shares a student's education records only with the student or a verified eligible party. A phone number alone opens nothing.
For a student under 18 the agent speaks to the parent or guardian on record.
PII is masked in transcripts and logs. Access is by role. The agent never asks for a full card number, a Social Security number, a one-time code or a password. Recordings and data stay in your Google Cloud project, in a US region.
A student who sounds distressed or mentions self-harm is handed to a person at once.
The agent runs in the Google Cloud region closest to your students. This is fixed before the build, since reply time cannot be tuned afterwards.
The agent mirrors the caller turn by turn, so it follows the caller'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 counselor sees the record, the transcript summary and the captured details before speaking.
An analyzer agent keeps each case open until it reaches an end state: enrolled, paid, answered, or handed to your team.
Anything not on this list, including your student information system, LMS or billing 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, which matters when the student speaks English and the parent prefers Spanish.
The agent shares a student's education records only with the student or a verified eligible party. The caller is verified, for example by student ID and date of birth, before the agent reads out anything from the record.
For a student under 18 the agent speaks to the parent or guardian on record. It confirms it has the right person before it names the application or the balance.
Yes, when the person has given the consent the TCPA requires for calls with an AI voice, inside the calling hours, and after the do-not-call lists are checked where they apply. The agent says it is an AI assistant at the start of every call.
The call is transferred live to your counselor or office with the record and the summary, so the family does not repeat the case. You decide which cases always go to a person, such as aid appeals and complaints. A student who sounds distressed is handed to a person at once.
No. The agent connects to your existing numbers and systems. There are more than 50 integrations, and other systems, such as your student information system or LMS, 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 inquiry follow-up, application completion or the student helpline.