From 68% to 100%: Optimizing Skills With a Single Command

Explore all

Developers love Claude Code, but Microsoft’s reach gives Copilot the enterprise edge

While developers prefer Claude Code, Microsoft Copilot dominates in larger enterprises, highlighting a divide between individual preferences and corporate adoption trends.

CI/CD for Context in Agentic Coding: Same Pipeline, Different Rules

Explore how CI/CD principles apply to managing context in AI coding agents, focusing on evals as tests and the challenges of integrating them into development pipelines.

How we turned AI hallucination into a product feature

Explore how AI hallucinations can reveal gaps between user expectations and product capabilities, turning potential errors into opportunities for system improvement.

Anthropic brings evals to skill-creator. Here’s why that’s a big deal

Anthropic's skill-creator now includes evals, allowing developers to test and validate context files, improving the accuracy and efficiency of AI coding agents.

Claude Code gets remote access to live local terminals

Claude Code's new Remote Control feature allows developers to manage local terminal sessions from mobile devices, syncing commands and outputs across platforms.

GitHub brings Claude and Codex agents directly into Copilot

GitHub integrates Anthropic's Claude and OpenAI's Codex into Copilot, offering Business and Pro users a choice of coding agents for tasks like code drafting and review.

Ollama and OpenClaw make natural bedfellows for the local AI stack

Ollama and OpenClaw are good examples of a local-first AI stack, reducing cloud dependency by running models and agent frameworks on consumer hardware for enhanced control and efficiency.

The Context Flywheel: Why the Best AI Coding Teams Will Win on Context

The Context Flywheel explores how iterative context development in AI coding teams enhances agent output, expertise, team learning, and organizational alignment.

OpenAI moves beyond SWE-bench Verified as coding benchmarks saturate

OpenAI shifts focus from SWE-bench Verified as coding benchmarks reach saturation, exploring more complex evaluations for AI models in real-world scenarios.

Your AGENTS.md file isn't the problem. Your lack of AI Agent Evaluations is.

The issue with context files like AGENTS.md is not their existence but the lack of evaluation to validate their effectiveness in guiding AI agents.

Anthropic brings ‘frontier cybersecurity’ to Claude Code as cyber stocks slide

Anthropic introduces AI-driven Claude Code Security to help developers identify and fix software vulnerabilities, integrating into existing workflows.

My Coding Agent Needed a Package Manager for Its Own Brain (And I Gave It One Using a Skills Registry)

Explore how a skills registry transformed a coding agent's decision-making, enabling it to read library documentation and make informed stack decisions.