A technical guide exploring GitHub's new Agentic Workflows, which integrate AI agents into GitHub Actions for adaptive, intelligent automation.
Explores GitHub Copilot's new custom agents feature, detailing how to create specialized AI coding assistants for specific workflows and frameworks.
Learn how to use Background Responses in .NET's Microsoft Agent Framework to maintain AI agent state and resume interrupted tasks using continuation tokens.
A guide on teaching the Kiro AI agent to work with custom libraries and DSLs using steering files and the Model Context Protocol (MCP).
A timeline and analysis of major generative AI model releases and a security framework for AI agents from late 2025.
Argues against using API keys for securing enterprise AI tools like LLMs and agents, highlighting security flaws and recommending better alternatives.
A technical guide on automating presentation creation using Microsoft Agent Framework, Azure OpenAI, and the GAMMA API.
A comprehensive overview of over 50 modern AI agent benchmarks, categorized into function calling, reasoning, coding, and computer interaction tasks.
Learn to build AI agents in C# using Microsoft Agent Framework and Hugging Face MCP tools for image generation and analysis.
Explores the evolution from simple, stateless AI agents (Agent 1.0) to advanced, deep agents (Agent 2.0) capable of complex, multi-step tasks.
A guide to building a basic AI agent framework that uses AI for planning and orchestrates reusable, atomic functions to interpret natural language requests.
A developer shares practical website optimization tips, including updating HTTP links, using AI agents, and cleaning up config files.
Introduces agent-rules, an open-source CLI tool that standardizes security and coding rules across AI coding assistants like GitHub Copilot and Cursor.
A guide to building an AI-powered system using the Mastra AI framework to automate and streamline the evaluation of conference Call for Papers (CFP) submissions.
Explains the concept of AI subagents, specialized agents for specific tasks, and their architecture using an orchestrator model.
A proposed security evaluation framework for Model Context Protocol (MCP) servers, focusing on configuration and implementation risks for developers.
Analyzes AI's impact on software engineering, covering developer evolution, skill gaps, productivity myths, and the future of the profession.
A developer's personal reflection on the addictive nature of AI agentic engineering, the loss of work-life balance, and the industry-wide trend of extreme work hours in the AI space.
Explores how zero-trust environments like defense and finance can securely adopt AI using local-first agents and semi-autonomous workflows.
Explores key traits of AI-native products designed for efficient consumption by AI agents, focusing on context optimization and tool execution.
