JetBrains logo

HAX Research

HAX Research

Invent and investigate Human-AI interaction scenarios that enhance the work of technology creators.

About Us

JetBrains develops tools for technology creators, and in the Human-AI Experience (HAX) research team, we’re all about making those tools even better.

Our research spans three core areas of interaction with AI: design, impact, and quality. We investigate critical questions, such as the most effective HAX implementation in the development lifecycle, the influence of HAX on users' experiences, and the key attributes of AI output that best help to support our users. By understanding how developers work with AI, we can suggest new seamless and intuitive AI feature ideas and prototypes tailored to JetBrains users' needs.

Our approach goes beyond traditional UX research and A/B testing. We leverage our expertise in behavioral sciences and data analysis to conduct experimental mixed-method studies, adhering to rigorous academic standards. Our expertise also helps to approach technical tasks with attention to unique human characteristics, optimizing the user interface and functionality of AI-driven JetBrains tools.

A lot of our work happens in partnership with academic researchers. We learn from their experience and help them to improve the efficiency and robustness of their studies, pushing the boundaries of knowledge together.

We’re here to be part of the transformative changes happening in the world.

The HAX Team

Agnia Sergeyuk
Team Lead

Agnia graduated with distinction from St. Petersburg State University with a Specialist degree in Clinical Psychology. She then went on to pursue a PhD in Computer Science at TU Delft. In her spare time, Agnia enjoys playing Dungeons and Dragons and traveling.

Ilya Zakharov
Senior Researcher

Ilya graduated with distinction from Lomonosov Moscow State University. He then went on to earn a PhD in Psychology, with the background in the intersection between psychology, neuroscience, and behavioral genetics. In another life (and with better music abilities), he would have liked to become an avant-garde musician.

Ekaterina Koshchenko
Researcher

Ekaterina received a Master’s degree in Applied Mathematics and Informatics from the Higher School of Economics in St. Petersburg and now lives in Amsterdam. In her professional capacity, she researches how AI influences IT specialists and their interactions. Outside of work, she spends her time dancing, bouldering, surfing, and doing nerdy things.

Ongoing Research Collaborations

User-Centered In-IDE HAX

with Delft University of Technology

We believe that there is significant space for innovation in the field of human-AI interaction. IDE users have their own workflows and the injection of new complex features, such as LLM-based ones, is a non-trivial task. While chat is a popular and user-friendly way to use LLMs, we think there are better ways to integrate them into IDEs.

The goal of this project is to embed emerging LLM practices into the developer workflow without disturbing the user and, at the same time, improving their productivity.

Code Review for AI-generated Code

with Lund University

LLMs increasingly generate code, but code review tools have not kept up. Reviewing an AI-generated multi-file change is a different task than reviewing a colleague's pull request.

We aim to understand what this process actually requires. The result would be a developer-grounded workflow and IDE prototype that embeds AI-generated code review into the developer's existing process to support appropriate trust.

Reasoning Trace Continuation

with University of California, Irvine

We aim to establish an empirical foundation for understanding human-AI collaborative problem-solving by characterizing reasoning strategies, their relationship to solution quality, and their role in enabling successful handover between human and LLM agents.

Select publications

Human-AI Experience in Integrated Development Environments: A Systematic Literature Review

Empirical Software Engineering: Human-Centered AI for Software Engineering

Agnia Sergeyuk, Ilya Zakharov, Ekaterina Koshchenko, Maliheh Izadi

Developer Needs and Feasible Features for
AI Assistants in IDEs

ICSE-SEIP '26: Proceedings of the IEEE/ACM 48th International Conference on Software Engineering: Software Engineering in Practice

Agnia Sergeyuk, Ekaterina Koshchenko, Ilya Zakharov, Timofey Bryksin, Maliheh Izadi

Evolving with AI: A Longitudinal Analysis of Developer Logs

ICSE '26: Proceedings of the IEEE/ACM 48th International Conference on Software Engineering

Agnia Sergeyuk, Eric Huang, Dariia Karaeva, Anastasiia Serova, Yaroslav Golubev, Iftekhar Ahmed

Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward

Information and Software Technology, vol 178

Agnia Sergeyuk, Yaroslav Golubev, Timofey Bryksin, Iftekhar Ahmed

Want to collaborate?

We’re looking for collaborators – researchers, developers, and other HCI professionals – interested in advancing human-AI experience in real-world software development tools.

By collaborating with us, you can:

  • Build and evaluate HAX features directly in production-grade developers' tools.
  • Test your hypotheses using real-world IDE data or with a sample of professional tech creators.
  • Bring your ideas about the future of human-AI collaboration in tech creation, and get support in planning, implementing, and evaluating them.

Our current areas of interest include how mental models of AI tools influence their acceptance and effective use, how AI is shaping collaboration in developer teams, and how multimodal AI can support coding tasks. We are also open to exploring other promising topics related to human-AI interaction in tech creation.

We provide access to infrastructure, developer workflows, and research-grade support to enable rigorous, impactful experimentation.

Interested? Email us at collaborations@research.jetbrains.org.

You are also welcome to take part in our prediction tournament on Metaculus until June 2026. You can try to predict which AI features will emerge in software development, compete for a cash prize, and help us to learn how developer attitudes and forecasting skills evolve.

Contact usPredication tournament