KAFU intelligent systems - each plays a unique role in the university's digital ecosystem.
No agents found.
READINESS · 100%
KAFU AI Talapker
Virtual admissions assistant to help applicants and their parents with university admission.
ReadyIn operation
READINESS · 100%
KAFU AI Librarian
Digital library assistant for finding books, comparative tables, and formatting bibliographic references according to GOST.
ReadyIn operation
READINESS · 100%
KAFU AI Ústaz
AI platform for automated educational course creation, lecture recording with AI avatars and test generation.
ReadyIn operation
READINESS · 100%
KAFU AI International
Digital assistant for the adaptation of international students - accommodation, visas, academic process in three or more languages.
ReadyIn operation
READINESS · 100%
KAFU AI Students
Automation of student interaction with the university's digital ecosystem - certificates, debts, psychological assistance.
ReadyIn operation
READINESS · 100%
Kazzinc AI GPT
Intelligent AI agent based on GPT Builder for automating the filling of profession matrices for Kazzinc LLP.
ReadyFor Kazzinc only
READINESS · 100%
Kazzinc AI Translator
Intelligent AI agent based on a local model for automatic document translation for Kazzinc LLP.
ReadyFor Kazzinc only
READINESS · 90%
KAFU Senym AI
KAFU AI psychologist for anonymous 24/7 emotional support for students.
Not readyIn operation
READINESS · 90%
KAFU AI Research
Intelligent AI agent for searching scientific articles, analyzing sources, and selecting journals for publication.
Not readyIn development
READINESS · 50%
KAFU AI Smart Bilim
Intelligent assistant for analyzing student performance and the quality of the university's educational programs.
Not readyIn development
READINESS · 50%
KAFU AI Smart Queue
Intelligent platform (kiosk) with an AI agent for organizing a smart queue and answering applicant questions.
Not readyIn development
READINESS · 0%
KAFU AI Career
Intelligent platform with AI elements for employee selection and recruitment.
Not readyIn development
READINESS · 0%
KAFU AI Tour
Intelligent platform for an interactive 3D tour of the university campus with an AI assistant.
Not readyIn development
READINESS · 0%
KAFU AI Proctor
Intelligent platform with AI elements for online proctoring, exam monitoring, and ensuring academic integrity.
Not readyIn development
READINESS · 0%
KAFU AI Translator
Intelligent platform for translating presentations and documents using a local AI model.
Not readyIn development
Readiness
AI Agent
KAFU AI Talapker
Virtual admissions assistant.
100
Q2 2025
Implementation period
Q2 2025.
Agent description
This is an intelligent assistant for the admissions committee of the Kazakh-American Free University. It uses a local LLM and RAG system to find relevant answers to user queries.
Agent operation
Below are the main technologies and components that ensure the operation of the university's intelligent agent.
1PostgreSQL database - Used to store embeddings (vectors) of responses split into text chunks;
2Local model Qwen3-Embedding-0.6B - Multilingual model used to generate vector representations (embeddings) of texts;
Model context: 32,768 tokens.
3Local model Google/Gemma-4-31B - Multilingual language model with tool_choice support, allowing connection of external tools such as Internet search and the ability to process data from the RAG system;
Model context: 7,500 tokens.
4RAG and RAG-Fusion mechanism - Used to combine and rank results from multiple queries and form the most relevant context before generating a response by the model;
5Reranking mechanism using the bge-reranker-v2-m3 model - Used to select the most accurate and relevant answer from multiple found fragments;
6Voice recognition + RVC models - Operates based on the local Vosk model, providing speech-to-text conversion (currently in Russian) and an RVC server for generating human-like voice responses;
7Final result - Passing the final message in the format:
prompt
{Context}: %Result%. {Question}: %Question%. {Note}: Give an answer to the applicant.
Agent functions
♿ Inclusive features
🌎 Generating responses in different languages
🌐 Internet search capability
⭐ Brief summary of file contents
💬 Answers to questions about admission
🔊 Voice recognition (currently in Russian)
🛠️ Generating a response from LLM using the RAG system
Additional
The agent is available 24/7 on Telegram and helps applicants, parents, and schoolchildren learn everything about admission to our university.
This video shows how the agent greets the user, answers questions about admission, accommodation, and what educational programs are available at the university.
AI Agent
KAFU AI Librarian
Virtual digital library assistant.
100
Q2 2025
Implementation period
Q2 2025.
Agent description
This is a library assistant that helps users find books, recommend new items, create tables and compare them, and automatically format bibliographic references according to GOST.
API
A solution from OpenAI in the form of API access to models is temporarily used. A transition to a local LLM will be made soon. Testing of filling tables on a local LLM is underway.
Agent operation
Below are the main technologies and components that ensure the operation of the university's intelligent agent.
1MySQL database - After the integration of the automated library system KABIS, this agent gained the ability to query the book database to provide answers to user questions;
2Using the RMEL and IPRSmart API - Querying resources to search and retrieve books;
3Model gpt-4o-mini - Multilingual model that uses tool_choice to execute queries to the book database and output results;
Model context: 65,536 tokens.
4Final result - The model answers basic questions related to the library. In cases where the user requests any books, the model chooses when to call functions, after which it outputs the final result to the user.
Agent functions
♿ Inclusive features
⚡ Search and delivery of books from RMEL
📖 Search and delivery of books from KABIS
📙 Search and delivery of books from IPRSmart
📊 Creating comparative tables
🌎 Generating responses in different languages
🙋🏻♂️ Providing personalized results to the user
Additional
The library assistant is available on the university website and helps students, teachers, and researchers 24/7.
This video shows how the library AI assistant helps students find the books they need and format bibliographic references.
AI Agent
KAFU AI Ústaz
AI platform for automated educational course creation.
100
Q4 2025
Implementation period
Q4 2025.
Agent description
This is an AI platform for automated educational course creation, lecture recording with AI avatars and test generation.
Agent operation
Below are the main technologies and components that ensure the operation of the university's intelligent agent.
1Video recording with teacher AI avatars - Built-in system for creating video lessons with realistic AI avatars. Avatars are generated based on photos and audio recordings of real teachers, creating a "live presence" effect and increasing student trust;
2Generation of educational materials - The agent automatically generates lecture texts, presentations, teaching aids and practical assignments for a given discipline. It uses university standard templates and discipline databases;
3Realistic AI avatars - Face generation and speech synchronization models with a high degree of realism (up to 95%) are used. This allows students to perceive content as a live lecture, which increases engagement and trust in the teacher;
4Final result - The agent creates a ready-made multimedia course: includes video lectures, teaching materials, tests and links. The teacher only has to approve and publish the course;
5Test creation - To generate tests in GIFT format and lecture materials, the local model Google/Gemma-4-31B is used
Model context: 9,500 tokens.
6Image creation - To generate images, the local model Fooocus and the RTX 5090 32 VRAM graphics card are used.
Agent functions
♿ Inclusive features
🖼️ Local image generation
🎓 Automation of online course creation
📋 Generation of lecture materials and tests
🎥 Recording video with teacher AI avatars
📝 Generation of lecture texts and teaching aids
💻 Integration of created videos into the Moodle platform
🤖 High degree of avatar realism to increase student trust
Additional
The AI platform is available 24/7, allowing users to create high-quality videos with virtual avatars, speech synthesis and support for multiple languages, as well as lecture materials and tests at any time.
This video shows how a lecture is prepared and a teacher's digital AI avatar is created.
AI Agent
KAFU AI International Student
Helping international students adapt.
100
Q4 2025
Implementation period
Q4 2025.
Agent description
Digital assistant to help international students adapt to the Kazakh-American Free University. Answers questions about accommodation, visa support, academic process and student life.
Agent operation
Below are the main technologies and components that ensure the operation of the university's intelligent agent.
1FastAPI - Web framework for building API and processing user requests;
2Redis - Used for temporary storage of chat history;
3Local model Qwen3-Embedding-0.6B - Creates embeddings and helps the system understand the meaning of queries;
Model context: 32,768 tokens.
4Local model Google/Gemma-4-31B - Main language model for generating responses to users;
Model context: 7,500 tokens.
5LangChain - Library that ensures interaction between local models and dialogue logic;
6Final result - Personalized response to international students' questions:
prompt
{Question}: What educational programs are available? {Answer}: The following educational programs are available: …
Agent functions
🎓 Answers to questions about studying
📝 Storing dialogue history in Redis
🏠 Consultations on accommodation and dormitories
🌍 Helping international students adapt
💬 Communication in English, Russian and Kazakh
🧠 Generating responses through local model and LangChain
Additional
The agent is available 24/7 and is hosted on the KAFU AI-Sana platform. Its goal is to facilitate the adaptation process for international students and make communication with the university more convenient and understandable.
This video shows how the AI assistant answers questions from international students in different languages.
AI Agent
KAFU AI Students
Automation of student interaction processes with the university's digital ecosystem.
100
Q2 2025
Implementation period
Q2 2025.
Agent description
This is an intelligent assistant for students of the Kazakh-American Free University. It uses a local LLM and RAG system to find relevant answers to user queries.
Agent operation
Below are the main technologies and components that ensure the operation of the university's intelligent agent.
1PostgreSQL database - Used to store embeddings (vectors) of responses split into text chunks;
2Local model Qwen3-Embedding-0.6B - Multilingual model used to generate vector representations (embeddings) of texts;
Model context: 32,768 tokens.
3Local model Google/Gemma-4-31B - Multilingual language model with tool_choice support, allowing connection of external tools such as Internet search and the ability to process data from the RAG system;
Model context: 7,500 tokens.
4RAG and RAG-Fusion mechanism - Used to combine and rank results from multiple queries and form the most relevant context before generating a response by the model;
5Reranking mechanism using the bge-reranker-v2-m3 model - Used to select the most accurate and relevant answer from multiple found fragments;
6Voice recognition + RVC models - Operates based on the local Vosk model, providing speech-to-text conversion (currently in Russian) and an RVC server for generating human-like voice responses;
7Final result - Passing the final message in the format:
prompt
{Context}: %Result%. {Question}: %Question%. {Note}: Give an answer to the student.
Agent functions
♿ Inclusive features
🤝 Psychological assistance + AI
📝 Obtaining a certificate of study
💵 Obtaining information about debt
🔊 Voice recognition (currently in Russian)
🔒 Obtaining login and password from Moodle and Platonus
💬 Answers to questions about the educational process
🛠️ Generating a response from LLM using the RAG system
Additional
The agent is available 24/7 on Telegram and helps students find out the necessary information about our university.