Tag
GitHub Copilot code review now supports custom agent skills and MCP server connections in public preview, allowing organizations to bring their own standards and context into code reviews.
GitHub promotes its Copilot app as a tool that reduces context switches by keeping the entire development workflow from issue to merge in one place.
The article critiques the shift from outcome-based productivity claims (e.g., 55% faster task completion) to volume-based claims (e.g., 75% of code AI-generated) by AI coding tool vendors, arguing the latter are less meaningful and harder to falsify.
The article examines whether Microsoft has lost its competitive edge in AI, noting disappointing Copilot uptake, GitHub reliability issues, and competition from Anthropic's Claude Code, despite Satya Nadella's optimistic Build keynote focused on agentic AI.
A survey of memory implementations across major AI agent harnesses (Claude Code, Codex, Copilot, etc.) reveals common boundary failures including bounded local storage, keyword retrieval, harness scoping, weak staleness handling, and 57-71% cross-user contamination rates, highlighting unsolved problems in agent memory infrastructure.
The article examines how the explosive growth of AI coding agents (1400% in 2026) is straining GitHub's infrastructure, leading to notable uptime issues, and discusses GitHub's plans to adapt its platform for this new era.
Microsoft introduces MAI-Code-1-Flash, a coding model optimized for production workflows with fewer tokens and higher accuracy than Claude Haiku 4.5 across multiple benchmarks.
Microsoft launches Scout, an AI assistant built on the OpenClaw framework, designed as an always-on agentic assistant integrated into Microsoft 365 with persistent memory, customizable skills, and security protections.
GitHub Copilot is an AI-powered code completion tool that assists developers by suggesting code snippets and functions in real-time.
Microsoft is set to launch a revamped Copilot super app; leaked screenshots show it powered by an AI agent named Scout.
Microsoft is set to announce new AI models including its first reasoning model, MAI-Thinking-1, along with Windows 11 developer experience improvements and Copilot updates at its Build conference.
Microsoft is planning to unveil a unified Copilot super app at Build 2026, with new screenshots revealing a coding surface with GitHub Copilot integration and a Cowork tab for data aggregation. The app aims to consolidate scattered tools into a single home.
An opinion piece examines whether AI coding tools like Claude Code and Copilot truly enhance developer skills or merely accelerate flawed decision-making, highlighting the need for new metrics to evaluate human-AI collaboration in engineering.
Microsoft is building a super app to unify its various Copilot AI tools including GitHub Copilot, Copilot Chat, and a new agentic workflow capability called Autopilot, aiming to provide a single destination for users and address customer confusion.
Emily is a voice AI copilot designed for coworking and coliving operators.
Microsoft plans to release a new AI coding model at its Build conference next week, aiming to regain competitiveness against rivals like Anthropic's Claude Code and OpenAI's Codex.
SocialEcho 2.0 is an AI-powered social media copilot designed for teams and agents to manage social media activities.
ORCA is a copilot for end-to-end causal analysis that uses agents to guide users through workflows including causal discovery, effect estimation, and root cause analysis, with structured reports.
This article examines the steep decline in programming book sales as AI chatbots like ChatGPT and GitHub Copilot replace traditional learning methods, noting a 16.9% drop in 2023 and publishers ceasing to report the category.
A hot take predicting that by 2027, AI will shift from customer-facing chatbots to backend tools that assist employees, improving efficiency and user satisfaction.