Tag: developer tools
GitHub Puts Guardrails on Copilot’s Sandbox Inside JetBrains IDEs
Tom Smith | | AI agents, AI coding agents, AI Governance, Copilot sandbox, Developer Security, developer tools, Enterprise AI, filesystem controls, GitHub Copilot, GitHub Copilot JetBrains, IDE security, JetBrains, managed policies, MCP governance, network controls, OpenTelemetry, platform engineering, sandbox security, software developmentJetBrains IDEs are where a lot of enterprise backend work happens — Java, Kotlin, Spring, big monorepos with a lot to break. So when an AI coding agent starts running shell commands ...
Rust’s First Debugging Survey Shows Most Developers Skip the Debugger Entirely
Tom Smith | | async Rust, dbg macro, developer experience, developer tools, GDB, LLDB, platform engineering, print debugging, runtime debugging, Rust compiler, Rust debugger, Rust debugging, Rust developers, Rust tooling, software debugging, software development, systems programming, ustMost Rust developers don't use a debugger. That's the headline finding from the Rust compiler team's first dedicated debugging survey, and it's worth sitting with for a second. Rust has spent years ...
GitHub’s New Copilot Feature Takes the Guesswork Out of Picking AI Models
Tom Smith | | agentic AI, AI agents, AI coding assistants, AI cost optimization, AI Governance, AI model routing, Code Generation, developer tools, devops, github, GitHub Copilot, model selection, multi-model orchestration, platform engineering, Project HydraFusion, software developmentGitHub’s Project HydraFusion brings multi-model orchestration to Copilot, automatically routing coding tasks across AI models to balance quality, cost and complexity ...
GitHub Puts Copilot in the Approval Seat for Pull Requests
Tom Smith | | AI code review, AI coding, AI Governance, automated code review, branch protection, code review, Copilot code review, developer productivity, developer tools, devops, Engineering Governance, github, GitHub approvals, GitHub Copilot, PR approvals, pull requests, software development, software lifecycleGitHub Copilot can now submit binding pull request approvals, moving AI code review from advisory feedback into the merge decision itself ...
GitHub Tightens Copilot’s Billing and Governance Rules Ahead of a Busy Fall
Tom Smith | | AI cost management, AI Governance, Balanced review, chat data retention, Copilot billing, Copilot Business, Copilot Chat, Copilot cloud agent, Copilot code review, Copilot Enterprise, developer tools, GitHub AI Credits, GitHub Copilot, GitHub Mobile, Lite review, platform engineering, token-based billing, usage based billingGitHub Copilot is tightening enterprise controls with upfront seat billing, longer chat retention and a Balanced code review default ...
Adronite Unveils AI Coding Tool Based on Embedded Context Engine
Mike Vizard | | ACE, Adronite, Adronite Context Engine, AI code generation, AI coding assistants, AI coding tool, AI-generated code, code review, codebase context, Codistry, developer tools, devops, open-weight AI models, software development, token efficiencyAdronite launches Codistry, an AI coding tool that uses a context engine to map codebases, reduce token usage and generate more production-ready code ...
GitHub Copilot’s Latest Update Bets on Model Choice, Not Model Loyalty
Tom Smith | | Agent Plugins 1.0, AI agents, AI coding tools, Claude model switching, Copilot CLI, Copilot Memory, Copilot updates, developer tools, devops, GitHub Copilot, GitHub Copilot models, Kimi K3, MAI-Code-1.1-Flash, Ollama, platform engineering, VS Code 1.133GitHub’s latest Copilot updates add Kimi K3, MAI-Code-1.1-Flash, Agent Plugins 1.0, model switching, CLI improvements, and local Ollama support ...
Anthropic Makes Claude Code’s Auto Mode the Default, Betting Automation Beats Manual Review
Tom Smith | | agent permissions, agentic coding, AI code generation, AI coding agents, AI Governance, AI guardrails, AI permissions, AI safety, AI security, Anthropic, autonomous coding agents, Claude Code, Claude Code auto mode, Claude Code security, coding automation, developer productivity, developer tools, human engineering the loop, human-in-the-loop, permission fatigue, prompt injection, Pull Request Automation, secure AI agents, software development, software engineeringAnthropic is making Claude Code’s auto mode the default for Pro, Max and Team users, replacing constant permission prompts with classifier-based guardrails designed to catch risky actions without slowing developers down ...
CodePen 2.0 Turns a Design Playground Into a Real Deployment Tool
Tom Smith | | browser coding, browser-based IDE, Cloud development environment, Cloud IDE, CodePen, CodePen 2.0, CodePen Projects, custom domains, developer tools, devops, file-based projects, front-end development, one-click deployment, production deployment, real-time collaboration, shadow infrastructure, version history, web developmentCodePen 2.0 transforms the front-end playground into a file-based development platform with collaboration, version history and one-click deployment ...
GitHub Copilot Gets Its Own App — and It’s More Than a Coding Assistant
Tom Smith | | Agent Merge, agentic development, AI coding assistant, CI/CD, developer tools, devops automation, GitHub Copilot, software development lifecycleGitHub has launched a standalone Copilot desktop app in technical preview, moving beyond the IDE to introduce a dedicated cockpit for agentic development. The app enables developers to manage parallel, isolated agent ...
5 Facts About AI Coding Agents from Comprehensive Benchmarking
Graham Neubig | | AI coding agents, benchmarking, developer tools, Large Language Models, software developmentAI coding agents are becoming more capable, but evaluating them is harder than it looks. Most benchmarks focus on a single dimension of agent capabilities; for instance, the popular SWE-Bench benchmark only ...
GitHub Copilot CLI Gets a Second Opinion — and It’s From a Different AI Family
Tom Smith | | AI agents, AI code review, Claude Sonnet 4.6, cross-family collaboration, developer tools, GitHub Copilot, GPT-5.4, Rubber Duck, SWE-Bench ProGitHub Copilot CLI’s "Rubber Duck" experimental feature uses cross-family model collaboration (Claude + GPT-5.4) to catch architectural flaws and reduce logic errors ...
