Explyt 4.1 introduces new powerful features for an even better coding, testing, and debugging experience.
Key improvements include:
- Python support: you can use assistant’s features in PyCharm
- MCP servers support
- Rules and Workflows features added for a more accurate and careful agent’s work
Reproduce, inspect and fix inside JetBrains IDEs, with the debugger, run configurations and IDE facts as evidence.
Overall improvements:
- enhanced stability of the agent and tools
- support for running and fixing tests for IntelliJ IDEA users on Windows under WSL
- better Gradle and Maven support: the agent now reuses your IDE build settings and suggests syncing when configurations change
Added LLM models:
- OpenAI GPT-5-mini
- OpenAI GPT-5
Python support
You can use assistant’s features in PyCharm.
Rules: how they improve your coding experience
The Rules feature allows you to ensure the Explyt Agent follows your instructions for specific contexts. A rule is a Markdown snippet that is added to the system prompt.
Well-defined rules can significantly improve your experience with the Explyt Agent
Tips to start:
- specify a scope for when the rule should be applied
- instruct the agent on the expected steps the agent should follow when completing your queries
- instruct the agent what it should not do (for example, editing forbidden files)
- define the desired output format (for example: plan, proposed edits, summary) to make results predictable
- ask agent
Workflows: save you time and tokens working with prompts
The Workflows feature allows you to save repeated prompts and manually use them when appropriate. A workflow is a simple Markdown file that you add to your prompt via the input area. This allows you to reuse effective pipelines and boost your productivity.
Tips to start:
- instruct the agent to ask you appropriate questions before moving to the implementation
- instruct the agent on how to gather context for the request
- specify the expected steps the agent should take
- you can attach files to your request and reference them in your workflow
- keep workflows reusable by using placeholders (for example: {goal}, {files}) and filling them when invoking
MCP servers
With MCP, developers don't need to build custom integrations for every single tool.
The protocol supports two-way communication: AI agents can not only request and receive data, but also perform actions in external applications or even directly in the operating system. In short, MCP provides a universal interface that makes it easier for LLMs to work with external tools and resources.
Explyt 4.1 supports test frameworks: JUnit 5, JUnit 4, TestNG, kotlin-test, mocking frameworks: Mockito, Mockito-Kotlin, MockK, SpringMockK, and build systems: Maven, Gradle, IntelliJ Build System.
You can access language models either through Explyt servers or by using your API-keys.
Explyt Enterprise with Virtual Private Cloud (VPC) or self-hosting solution guarantees corporate data security. Your company's code is not sent to the internet and is not used for model training.
Reproduce, inspect and fix inside JetBrains IDEs, with the debugger, run configurations and IDE facts as evidence.
