I continue to experiment with AI in the context of software engineering. I’m fortunate that my team supports me in exploring different ways to improve our daily work. This week, I designed a team of autonomous agents to implement features, from design to implementation.   Why autonomous agents?   A long time ago, we were delighted when the IDE offered auto-completion. In the previous two years, things have changed. A lot.   Coding assistants have become our primary interfaces for coding.

Frankel's platform  covers topics related to software development, technology trends, and coding tutorials. Through articles, tutorials, and personal anecdotes, Frankel offers insights into programming languages, development frameworks, and best practices in software engineering. Readers can learn about software design principles, development methodologies, and emerging technologies to enhance their coding skills and build high-quality software applications.

A Java geek

A hands-on exploration of designing a team of autonomous AI agents using Claude Code's experimental agent teams feature. The author outlines the 8 levels of agentic engineering, explains how to define custom subagents via Markdown files in a `.claude/agents` folder, and describes a four-agent team (planner, challenger, coder, tester) coordinated through a custom `/implement` skill. Key challenges discussed include the autonomy vs. security tradeoff, frequent permission requests, and the experimental nature of the feature. The post concludes that agent teams are the next logical step as developers shift from writing code directly to managing agents.

Designing a team of agents