Vladislav Tankov is a Director of AI, leading the event of JetBrains AI and Grazie products, answerable for AI Assistant in JetBrains IDEs.
JetBrains is a world software company specializing within the creation of intelligent, productivity-enhancing tools for software developers and teams.
Are you able to provide an outline of JetBrains AI and its primary objectives?
We see the world of software development changing rapidly with the emergence of AI. That’s why we created JetBrains AI, a comprehensive suite of AI-powered tools designed for contemporary developers.
JetBrains AI leverages various large language models (LLMs), fine-tuned to work seamlessly inside your projects across various JetBrains IDEs. This integration of AI into your projects offers significant benefits:
- There’s no have to open additional tools while coding.
- Our AI service ensures you could have access to cutting-edge LLMs now and in the longer term, without the effort of researching or switching providers.
It’s also secure. Our products be certain that only the mandatory data is distributed to the LLMs, and neither we nor our service providers use your data or code to coach any generative models.
What are a number of the key features of JetBrains AI that differentiate it from other AI-powered development tools?
We’re independent and committed to delivering the perfect quality available across all modern LLM providers. We achieve this through the use of a mix of varied models, including our own, all while maintaining a powerful give attention to privacy.
For example of the important thing features we deliver, let’s take a better have a look at our AI Assistant. I’d like to focus on the next features:
- Multiline code completion: Are you able to imagine the satisfaction of seeing your code come together effortlessly?! This feature isn’t only a time-saver, it’s a game-changer. It autocompletes each single lines and whole blocks of code, all while staying true to your unique coding style and naming conventions.
- In-editor code generation: This feature permits you to turn your thoughts into reality, right in your editor. It helps you to quickly transform plain text descriptions into fully functional code snippets without ever breaking your flow.
- Context-aware AI chat: This powerful tool is seamlessly integrated into your IDE, able to assist you at any moment. Whether it’s essential to ask a matter, explain complex code, iterate on a task, or seek for files and usages, it’s there to enable you to.
You may discover more about our other capabilities here.
Could you elaborate on the machine learning models utilized in JetBrains AI and the way they’re implemented inside the IDE?
LLMs from OpenAI, Google, in addition to our own custom models power JetBrains AI. We then enrich the prompts with project-wide context collected with IDE functionality, which allows the models to generate responses which can be highly relevant and specific to your current project.
For instance, the code completion feature is implemented via in-house models and has cloud multiline and native single-line versions. Each are trained on permissive codebases with datasets tailored to our IDEs.
How does JetBrains AI ensure context awareness in its code suggestions and completions?
We use our expertise in code evaluation tools to offer AI with a comprehensive understanding of the codebase. We use code insight to get information concerning the project structure and enrich the context with it. Also, we offer LLMs with tools to introspect the project on their very own. Finally, we use code insight within the training stage to enhance the performance of our models.
This mixture of deep understanding in each areas enables us to cleared the path in AI features for coding.
How does JetBrains AI Assistant assist in reducing the cognitive load on developers?
Our latest research shows that a big majority of users have experienced positive outcomes from using JetBrains AI Assistant.
We see that JetBrains AI Assistant boosts the developer experience, enhancing productivity, happiness, and satisfaction. A notable 77% of users feel more productive. Similarly, 75% express that they’re happier with their JetBrains IDE experience, and 66% are more satisfied with their workflow when using JetBrains AI Assistant.
Moreover, our study found that JetBrains AI Assistant accelerates developer performance – 78% of respondents report spending less time on information search, 71% are capable of complete tasks more quickly, and 55% say that they’ve more time for more interesting work tasks.
JetBrains AI Assistant boosts efficiency and flow. Amongst participants, 58% report completing tasks with less mental effort, thus reducing their cognitive load. Moreover, nearly half of the participants notice enhancements of their ability to focus and enter a flow state, with 49% and 46% reporting improvements in each area, respectively.
What advancements does JetBrains AI offer when it comes to code generation, refactoring, and documentation creation?
Because of JetBrains AI’s deep integration with multiple JetBrains products, you may reap the advantages of AI-powered assistance right within the comfort of your IDE and team tools without increased investment.
With distractions and context switching out of the way in which, you may optimize your day by day development workflows, delegate some routines, and increase and lift your productivity while never compromising code quality.
Let’s discuss each of the activities you touched upon in your query:
- Code generation: As I discussed before, JetBrains AI permits you to quickly create functional code snippets from easy descriptions and might generate entire blocks of code that adhere to your project’s standards. The latter is especially useful when coping with repetitive patterns or boilerplate code.
- Refactoring: The AI refactorings are currently a piece in progress, but they’re already context-aware and fully integrated along with your codebase. While we proceed to perfect them, you may still profit from the IDEs’ built-in refactorings. JetBrains is renowned for its best-in-class refactorings, which were praised by Martin Fowler.
- Documentation creation: JetBrains AI automates the means of generating accurate and comprehensive documentation based on the code and comments inside your project. This feature helps maintain up-to-date documentation with minimal effort and ensures that your team all the time has reliable, well-documented code to work with.
How does JetBrains AI handle data security, especially when interacting with large language models?
We work only with the LLM providers which have been vetted and that adhere to the strictest principles of security and privacy. Not one of the LLMs utilized by JetBrains AI store or use our customers’ inputs for training any generative models. We adhere to those standards in the course of the development means of our own models, as well.
Are you able to elaborate on the recent partnership between JetBrains and Google Cloud to integrate Gemini models into JetBrains AI Assistant? How will this enhance the capabilities of AI Assistant for developers?
What truly sets JetBrains AI Assistant aside from other AI assistants is its ability to decide on essentially the most suitable LLM for every task. This ensures you may give attention to the creative features of coding while AI handles the repetitive stuff.
We see Gemini as certainly one of the leading LLMs in the marketplace. We consider that Gemini 1.5 Pro and Gemini 1.5 Flash running on Google Cloud’s Vertex AI will open up a spread of latest use cases for JetBrains AI Assistant with its long context window, advanced reasoning, and overall impressive performance. Gemini 1.5 Flash will help with use cases where high-volume cost efficiency and low latency are paramount.
What steps is JetBrains taking to be certain that AI Assistant continues to fulfill the evolving needs of developers?
We’re consistently looking for modern solutions, working with industry leaders and emerging startups to remain ahead of the race. This involves repeatedly evaluating and integrating the most recent advancements in AI and machine learning to make sure our tools remain on the leading edge.
We also invest heavily in research and develop our own models to make sure our relevance within the years to come back. By actively participating within the AI research community, we gain early insights into recent trends and technologies. This enables us to quickly adapt and implement the most recent advancements in our AI tools. Moreover, we repeatedly gather feedback from our developer community to refine and enhance our offerings in order that JetBrains AI evolves in keeping with the real-world needs of developers.
What impact do you foresee JetBrains AI having on the broader software development industry in the approaching years?
We consider AI is poised to revolutionize the software development landscape, and JetBrains AI will play a big role on this transformation.
While we’re starting with code generation and enhancing productivity through small features, that is only the start.
We expect that in the longer term AI won’t just assist with routine tasks but will turn out to be an integral a part of the event process, tackling increasingly complex challenges. Within the years to come back, developers will find themselves reviewing and refining code generated predominantly by AI agents relatively than by humans. This shift will redefine the role of developers, allowing them to give attention to higher-level problem-solving and innovation, with AI as their trusted collaborator.
