What the school offers
KSE Agentic AI School — an engineering environment where solutions are created in practice, rather than studied on slides
"AI is a technology that cannot be ignored. On the one hand, it provides deep insights and automates processes that used to be time-consuming. On the other hand, those who delegate all their thinking to AI are cognitively capitulating. KSE Agentic AI School offers solutions and the knowledge needed to prevent this capitulation and to be part of the first generation of AI agent architects in Ukraine. The first intake has already demonstrated that this approach works: the teams have created projects with the potential for funding and commercial development, and some participants are already receiving enquiries from international companies. In the second intake, we aim to train even more people who do not simply use AI, but are capable of building next-generation systems.”
Tymofiy Mylovanov, President of KSE
About the programme
9 weeks of study and work on a team projecta
Three practical cycles of hypothesis testing and product development
Regular office hours with lecturers from various disciplines
The foundation consists of mathematics and computer science, supplemented by practical experience with agent-based systems using real-world case studies
Each stage is completed by an agent or tool deployed on a shared platform
Learning through problem-solving, rather than through the passive absorption of material
By the end of the course, you will be able to
(01)
Formulate tasks for AI systems, rather than just writing prompts
(02)
Working with logs, errors and model limitations
(03)
Developing prototypes of AI tools for real-world tasks
(04)
Building agent workflows consisting of several steps
(05)
Check the quality of the result, rather than relying on the first answer
(06)
Present the solution to users and technical teams
What will you be after the programme?
AI Agent Builder
You will be able to create agents capable of independently carrying out complex, multi-step tasks: collecting data, testing hypotheses, invoking tools and generating results
AI Systems Architect
You will learn how to design the logic of autonomous systems: how an agent makes decisions, where human intervention is required in the loop, how to minimise errors, and how to make the system suitable for real-world use
AI-Native Problem Solver
You’ll be able to take a complex challenge from the fields of education, business, analytics, engineering or the public sector—and turn it into a working AI prototype
Builder with Demo Day Portfolio
By the end of the course, you’ll not only have a certificate, but also a final project that you can present to technical teams, partners and potential users
Opportunities for participants
9 weeks of hands-on practice
Intensive work with autonomous agents on real-world problems
GPU infrastructure included
Direct access to GPUs and agentic runtime for running full-scale models
Free participation
You don’t buy a place on the programme. You go through a competitive selection process and prove that you’re ready to create competitive solutions
Scholarship
$600 per month for programme participants.A scholarship equivalent to 600 dollars per month is available to participants on the main track, subject to academic achievement. Participants on the business track are not eligible for this scholarship
Demo Day
Final presentation of team solutions to technical teams, partners and potential users
Certificate following the defence of the final project
Participants who complete the programme and successfully present their final team project at Demo Day will receive a certificate from the KSE Agentic AI School
Real-world problems
Case studies from partner organisations
6 ECTS credits
Participants receive 6 ECTS credits upon completion of the programme
Choose your participation format
Business Track: Submit a project for your business
For entrepreneurs, executives, and business leaders with a specific task or idea for applying AI in their company.
Submit a project request to the school. A team of competitively selected students who are learning to build AI agents may be assigned to work on your project.
In your application, please outline:
How the course is organised
Format
In-person, at shelter-equipped locations
Start
26 October 2026
Duration
9 weeks
Volume
6 ECTS credits
Languages of instruction
Ukrainian and English
Number of places
35
Introduction
competitive selection
Classwork
● 9 weeks of study and work on a team project
● Three practical cycles of hypothesis testing and product development
● Regular office hours with lecturers from various disciplines
Independent and team work
● Each stage is completed by an agent or tool deployed on a shared platform
● Work on a team project throughout the programme
Programme
9 weeks, 3 sprints
● Week 1: The LLM landscape, how modern LLMs work, an overview of platforms and tools
● Week 2: Prompt engineering, context, RAG, security, and prompt injection
● Week 3: Tool use, function calls, MCP servers, integration of external systems
● Week 4: Reasoning, planning, memory, long-term planning and memory in agents
● Week 5: Agent architecture and orchestration (ReAct, reflection, planning, multi-agent, LangGraph, PydanticAI), state management and human-in-the-loop
● Sprint Demo #1
• Week 6: Coding agents, software development using agents, and code verification• Week 7: Reinforcement learning, preference learning and self-improvement loops• Sprint Demo #2
• Week 8: Evaluation, safety, Responsible AI and deployment• Week 9: Production hardening, observability, documentation and pitch preparation• Final Demo Day / Sprint Demo #3
KSE Agentic AI School Business Track
Nine weeks working on your own AI product or feature alongside the school’s technical team. You bring the concept and product vision — and play an active role in the development as a product owner.
Participation in the business track is free of charge. No scholarship is available
Who is eligible to apply
Entrepreneurs, product managers, executives and specialists from various sectors — anyone with a vision for a product or feature they want to create using AI
What is required at the time of submission
Just a rough idea: what you want to create, who might find it useful, and why you’re willing to work on it throughout the programme. Previous experience in product management, programming or machine learning isn’t essential, nor is a prototype, collected data, a fully-formed technical concept or your own business
Selection and the team
We select product owners and form teams from the school’s technical participants
Roles in the workplace
Engineers develop and implement the technical aspects of the project. The product owner is responsible for the vision, priorities, feedback and ensuring that the solution meets the needs of future users
Nine weeks
The team is working on the product, determining who the solution is for and what its purpose is
How much does it cost?
Free participation
You don’t buy a place on the programme. You go through a competitive selection process and prove that you’re ready to create competitive solutions
Scholarship
A scholarship equivalent to 600 dollars per month is available to participants on the main track, subject to academic achievement. Participants on the business track are not eligible for this scholarship
GPU infrastructure included
Direct access to the GPU and the agent runtime for running full-scale models
Demo Day
Final presentation of team solutions to technical teams, partners and potential users
Limited number of participants
35 places. Competitive selection.
Apply by 5 October
6 ECTS credits
A certificate and 6 ECTS credits following the defence of the final project at Demo Day
Stages of the competitive selection process
We don’t assess formal qualifications, but rather how you think, how you work with AI tools, how you iterate, how you spot mistakes and how you produce useful results
Stage 1
Fill in the form
Apply via the form on the programme’s website: describe yourself, your idea, the problem you want to solve, your future users and your motivation
Stage 2
Competitive selection
A test and an interview for technical candidates. There is a separate selection process for the business track
Stage 3
Announcement of the results
Selection results and invitations
Stage 4
Start of the course
The course takes place in person in Kyiv
Frequently Asked Questions
How many places are available on the course?
35 places. Selection is by competition.
When does it start, and until what date are applications being accepted?
Applications — By 5 October 2026 via the online form on the programme’s website. The course starts on 26 October 2026.
How long does the course last?
Nine weeks.
How much does it cost to take part?
Participation in both tracks is free of charge. Participants on the main track are eligible for a scholarship equivalent to 600 dollars per month, subject to academic performance. Participants on the business track do not receive a scholarship.
Is it possible to study if you don’t live in Kyiv?
Yes. Participants from outside Kyiv are provided with accommodation for the duration of the course.
In which languages are the courses taught?
In Ukrainian and English.
What will I get out of the programme?
A certificate based on the results of the final project defence and 6 ECTS credits.
How does the selection process work?
For technical participants — a test task and an interview. There is a separate selection process for the business track: in their application, candidates describe themselves, their idea, the problem they wish to solve, their future users and their motivation.
Who can apply?
Year 11 pupils; students studying mathematics, computer science, physics and engineering; students studying economics, business and public policy; engineers and physicists. Separately, for the business track: entrepreneurs, product managers, executives and specialists from various sectors.
Do you need programming experience to get onto the business track?
No. Previous experience in product management, programming or machine learning is not essential. All you need is an initial idea: what solution you want to create, who it will benefit and what problem it solves. You do not need a finished prototype, a technical concept or your own business.
Will there be exams?
Throughout the program, participants will complete practical homework assignments and take quizzes to check their understanding of the material. However, the primary focus of evaluation is on hands-on work: each stage of the program concludes with a tangible outcome—an agent or tool deployed on a shared platform. Participants will present their final solutions at Demo Day to jury members, industry experts, program partners, and project business owners.
What will happen to the project after the programme?
The strongest projects will be eligible for funding and support from the KSE business ecosystem to develop solutions and test their potential beyond the scope of the study programme.
Where should I write to with any questions?
au.gro.esk%40dsc