24 Jul 20257 min read

Explyt Agent takes off: superpowers for routine tasks

Explyt TeamPublished 24 Jul 2025

Media

4 videos

Coding, testing, and debugging is more powerful now with a cutting-edge Explyt Agent released in Explyt 4.0. The agent can perform an arbitrary task upon request in the chat.

For example, the video above shows how the agent solves the following task: send the user an email with the message "Password reset successfully!" after the user changes the password. The agent reads the existing code, templates, and tests and adds the required functionality:

  1. the agent adds new code to services
  2. the agent adds a template for the email that will be sent to the user
  3. the agent adds the necessary strings to the resource files
  4. the agent adds an integration test for the new functionality

The agent writes a new service from scratch according to the specification

The application allows students to view educational video courses. The video shows how the agent creates a new service according to the specification, allowing the student to manage bookmarked pages, for example, add a course to bookmarks and view a list of bookmarks. Agent adds:

  • required DTOs for bookmarks
  • service for managing bookmarks and its implementation
  • repository for managing bookmarks
  • controller for managing bookmarks

Agent adds comments to code

Agent reads repository code and adds docstring comment to each method of required service

Agent writes documentation for code

Agent reads repository code and adds documentation for required service:

  • its key responsibilities
  • description of main methods
  • how data validation and error management are performed
  • how interaction with the database is performed
  • how caching occurs
  • what are the regularly scheduled tasks
  • how logging is arranged
  • what is the service's responsibility in terms of security
  • what dependencies does the service have

Explyt Agent can independently:

  • use tools for editing code
  • use tools for researching the project
  • execute commands in the terminal
  • analyze the project for compilation errors

The agent sees and can modify all files in this project, in particular: code, tests, templates, resources, documentation, build configurations. The agent can add new files of any type if necessary.

User:

  • checks the changes made by the agent, can accept or cancel any of them
  • can allow or prohibit the agent from using some tools, for example, calling console commands

Preview Notice:

⚠️ Note: Explyt Agent is currently in preview state (EAP). Some features may not work as expected.

Reproduce, inspect and fix inside JetBrains IDEs, with the debugger, run configurations and IDE facts as evidence.

Newsletter

Get Explyt updates in your inbox

Release notes, engineering deep dives, and new articles like this one. No spam, unsubscribe anytime.

Comments

Loading comments...

Keep reading

All articles

Why choose Explyt?

Feature

Debugger

Yes

Ultimate only

No

No

No

No

SAST vulnerability scanner

Yes

No

No

No

No

No

IDE refactorings (Rename, Change Signature…)

Yes

No

No

No

No

No

Test coverage guarantees

Yes

Coverage gates

No

No

No

No

No

Semantic code model (types, find-usages)

Yes

Full code model

Yes

LSP

No

LSP

No

Reads dependency source

Yes

No

LSP

No

No

No

Auto-review of generated code

Yes

Via verify

/review

PR only

No

No

Context compression

Yes

No

Yes

No

No

Yes

Multi-IDE support

JB only

JB only

Yes

Yes

Yes

Yes

Pricing (all top models)

$15-200/mo

Credit-based

$20–200/mo

$20–60/mo

$10–39/mo

BYOK

What IDE-native AI feels like

What impressed me most is how well the agent understands the existing project. Its plans fit naturally into what is already built, even when I am working outside my usual tech stack.

Mariya Remenyuk
Mariya Remenyuk

Senior Analyst Developer · DXC Technology

LSP gives an agent coordinates; the full IDE gives it the project model. That native IDE context makes all the difference on real Java code.

Akiner Alkan
Akiner Alkan

Software Architect & AI Board Lead · Siemens

IDE-native stepping makes the difference on stateful Java applications.

Masaood
Masaood

Software Engineer

Webinar: Working with AI Tools at the User Level

Methodology, SDD + TDD, feedback loops, and subagents — a practical framework for getting predictable results from AI coding agents. For senior Java developers and team leads using JetBrains IDEs.

Explyt 5.20

Explyt 5.20: stop waiting in the chat — a background task panel and notifications outside the IDE

Frequently Asked Questions

Getting Started

IDE Integration & Workflow

How Explyt Compares

Models & BYOK

Pricing & Billing

Privacy & Security