VS Code 1.135 ships four agentic upgrades: a second-opinion AI reviewer called Rubber Duck, persistent agent sessions, Agent Host Protocol infrastructure, and visible token usage.
VS Code 1.135 ships four agentic upgrades: a second-opinion AI reviewer called Rubber Duck, persistent agent sessions, Agent Host Protocol infrastructure, and visible token usage.
Counting Copilot seats tells you nothing about AI resource consumption. Here is a practical C# data model for tracking token usage by model, team, and repository.
AI coding agents delete failing tests instead of fixing bugs. Maxi Contieri's prompt discipline and harness rules close the most common escape routes.
The Gradle project is building Agentic Gradle: official skills, benchmarks, and potential build tool changes so AI coding agents can run builds reliably. Configuration Cache default moves from Gradle 10 to Gradle 11.
First Mate Technologies built QueueMate using a two-model AI workflow: one agent writes code, another designs tests and reviews before merge. Here's what they found.
JetBrains shipped a fully offline AI coding assistant for Apple silicon. No token costs, no cloud dependency, but you need 64GB RAM and an M4 Pro to run it.
Enterprise apps now carry 4.31 times more critical vulnerabilities than before AI coding assistants went mainstream. Development velocity is up nearly 5x, and security teams can't keep up.
AI agents querying Cosmos DB need a controlled tool layer, not raw database credentials. Here is the least-privilege architecture and the common mistakes to avoid.
Cursor launched Origin, a Git hosting beta aimed at GitHub, on August 17. Agents are first-class actors. Here is what it ships with and the risk worth pricing in.
A peer-reviewed state-of-the-art review of vibe coding assembles 17 months of empirical evidence and finds the productivity numbers contradict each other until you control for scope and time horizon.
Laravel Auditor is a free MIT-licensed dev package that equips Claude, Cursor, Codex, and other agents with a structured methodology for auditing Laravel 12 and 13 apps.
The GoLand team released Modern Go Guidelines, a free CLI plugin that teaches AI agents to write version-matched Go code from Go 1.0 through Go 1.27.