Explores the Ralph Wiggum Loop, an autonomous agent pattern for software development, with a practical example using IBM Bob.
Explores the AI-driven evolution of software engineering from autocomplete to autonomous agents, shifting the developer's role from coder to orchestrator.
Experiments with AI coding agents building a web browser from scratch, generating over a million lines of code in a week.
Experiments with AI coding agents scaling to build a web browser from scratch, generating over a million lines of code.
An experiment testing the limits of autonomous AI code generation for a Spring Boot app, revealing current limitations and the need for human oversight.
Explores the critical but underdeveloped components of Agent-to-Agent (A2A) protocols: dynamic discovery, naming, and resolution for scalable AI agent ecosystems.
An analysis of OpenAI Codex as an autonomous coding agent, detailing a real-world task to improve label formatting logic.
An overview of LLM-powered autonomous agents, covering their core components like planning, memory, and tool use for complex problem-solving.
