Skip to main content

What’s new in Explyt 4.1

Explyt 4.1 introduces new powerful features for an even better coding, testing, and debugging experience.

Key improvements include:

  • Python support
  • MCP servers support
  • Rules and Workflows features added for a more accurate and careful agent’s work

Overall improvements

  • enhanced stability: the number of errors when the agent uses the built-in tools has significantly decreased
  • 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 new 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.

Download Explyt 4.1 from our website.

For bug reports and feature requests, use GitHub Issues.