I like to analyze codebases I start working on, or that I left for months. I ask my coding assistant, case in point, Copilot CLI: 'analyze the following codebase and report to me improvements and possible bugs.' It’s vague enough to leave room for crappy feedback, but also for some interesting insights.   I did it last week on a code base. Copilot returned a list of a dozen items. I asked it to create a GitHub issue for each, with the relevant labels, including priority.

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 developer shares a workflow using AI sub-agents (via Copilot CLI) to parallelize implementation of GitHub issues. Key insights include: using `gh` CLI instead of GitHub MCP Server for write permissions, using `git worktree` to give each sub-agent an isolated branch/folder, and the importance of context isolation — each sub-agent starts fresh, avoiding context pollution. The post also reflects on the broader implications of AI replacing junior developers and the long-term risk of a senior developer shortage.

Experimenting with AI subagents