What Is an AI Coding Agent? Architecture and Implementation
AI coding agents aren't magic. They're four-stage systems that perceive context, reason with LLMs, execute actions, and evaluate results. Here's how they actually work.
feature
Junie for PhpStorm: Native AI Agent Built for PHP Developers
JetBrains' native AI agent for PhpStorm uses code navigation, inspections, and project structure to autonomously execute multistep PHP tasks. Here's what it means for Laravel developers.
JetBrains Junie Goes Async: GitHub Integration and 30% Speed Boost
JetBrains Junie now integrates with GitHub for async development — delegate tasks without opening your IDE. Plus: 30% faster in-IDE performance, MCP support, and free licenses for open-source projects.
JetBrains Launches Free AI Agents Course for Developers
JetBrains and Nebius released a free course on AI agent architecture, productivity strategies, and risk mitigation. Built by the teams behind Junie and IntelliJ IDEA, it teaches you how to collaborate with agents instead of just using AI tools.
JetBrains AI Assistant, Junie, and Kineto Add GPT-5 Support
JetBrains ships GPT-5 as the default model across AI Assistant, Junie, and Kineto. Internal benchmarks show 1.5× to 2× improvements in code quality and task complexity handling over previous OpenAI models.
Spec-Driven Development: How to Control AI Coding Agents
AI coding agents work best with structure, not vague instructions. Here's how to break complex features into requirements, plans, and tasks that keep you in control while the agent does the heavy lifting.
GitHub Agent HQ: Multi-Agent Orchestration Built Into Your Workflow
GitHub launches Agent HQ, a unified platform to orchestrate coding agents from Anthropic, OpenAI, Google, and more directly in your workflow. Mission control, Plan Mode, and enterprise governance ship today.