Developer Workflow
39 articles about developer workflow.
1.6M Git Events Show AI Code Needs More QA
When AI agents generate most of your code, your review process must scale to match. Analysis of 1.6 million git events reveals where QA breaks down - and how to fix it.
AI Made My Team Write 21% More Code - The Review Queue Doubled
AI does not remove bottlenecks, it moves them downstream. When code generation gets faster, code review becomes the new constraint.
AI Tickets Need Way More Context Than Human Tickets
Writing Jira tickets for AI coding agents requires fundamentally different thinking. Humans infer meaning from vague tickets - AI agents go literal. How to
The Beauty of Deleting Code - Why Less Is Almost Always Better
The best engineering days are when you delete more lines than you write. How a 600-line parser became 40 lines of stdlib and why simplicity wins.
Skills vs Sub-Agents in Claude Code - When to Use Each Pattern
How to structure Claude Code skills vs sub-agents - splitting by type, managing 10+ skills, and choosing the right pattern for each workflow.
Drowning in AI? Start with a CLAUDE.md File
The biggest thing that helped me learn AI coding tools was treating the AI like a junior dev I am managing. Start with a CLAUDE.md file and build from there.
I Measured Every Hour My Human Worked for Two Weeks
After tracking a developer's time for two weeks, the data showed they stopped writing code entirely. With AI agents, output increased 89x while the human
Multi-Agent Code Review Loops - The Simple Pattern That Works
Running parallel AI coding agents works best with a simple pattern: one agent writes code, another reviews it. Here is how to set it up.
The Real Bottleneck with Parallel Agents Is Not Compute - It Is Git Conflicts
Running 5 coding agents in parallel sounds great until they all edit the same files. The bottleneck is coordination, not compute.
Sandbox vs YOLO Mode for AI Coding Agents
Should you run AI coding agents in a sandbox or let them execute freely? YOLO mode with frequent git commits offers the best balance of speed and safety.
Spotify Devs Haven't Written Code Since December - Specification-Driven Development
Specification-driven development is replacing hands-on coding. Write specs, let AI agents generate the implementation. Here's why it works.
Structuring Large Codebases for AI Agent Navigation with Layered Context
CLAUDE.md files at each directory level help AI agents navigate large codebases effectively. Learn the layered context pattern for better AI-assisted
Cursor Caught a Race Condition - Voice-Controlled Coding and Verbal Debugging
Voice-controlled AI coding agents don't just save keystrokes. Speaking your code logic out loud helps you think more clearly and catch bugs you'd miss typing.
AI Coding Technique: Change One File, Migrate the Entire Codebase
A practical AI coding technique - manually change one SwiftUI file, then have Claude Code migrate 1500+ hardcoded calls across the entire codebase to match.
Fixing AI Goldfish Memory with CLAUDE.md Constraints
When your AI agent confidently says it made a change but nothing changed, CLAUDE.md constraints prevent confident-but-wrong behavior across sessions.
Autonomous Multi-Session AI Coding Without Worktrees
Skip git worktrees entirely. Run 5 Claude Code instances on the same repo with CLAUDE.md as the shared spec and each agent handling a discrete task.
Why CLAUDE.md Is the Entire Game for Parallel Claude Code Agents
CLAUDE.md is the most important file when running parallel Claude Code agents. Without detailed specs, 5 agents on the same codebase will overwrite each other.
Hitting Claude's Context Limit Mid-Build and How CLAUDE.md Fixes It
When Claude Code hits the context limit during a build, you lose project context. A CLAUDE.md file prevents starting over by keeping essential specs persistent.
When Claude Files Bug Reports Against Its Own Code - And They Are Real
Running 5 parallel Claude agents with CLAUDE.md as the single source of truth leads to agents finding real bugs in each other's code. Here is how it works.
Put 'Challenge My Assumptions' in Your CLAUDE.md
Adding assumption-challenging directives to CLAUDE.md prevents AI agents from blindly implementing bad ideas. Make your agent argue with you before it builds.
Is Claude Overkill? Adding Anti-Over-Engineering Directives to CLAUDE.md
Claude Code tends to over-engineer solutions. Adding 'avoid over-engineering, only make changes that are directly requested' to your CLAUDE.md keeps it
Making Claude Code Skills Repeatable - 30 Skills Running Reliably
Running 30 Claude Code skills reliably for a macOS agent. The key to repeatability is explicit frontmatter, narrow scope per skill, and clear input/output
Why the Claude API Plan Is a Game Changer for Concurrent Agent Sessions
Claude usage limits frustrate developers until they discover the API plan. Here is why concurrent sessions on a Swift/Rust codebase demand it.
The Scope Shift in Code Copying - From Stack Overflow Snippets to Full AI Interaction Flows
AI changed how developers copy code. Instead of grabbing individual accessibility API snippets from Stack Overflow, we now generate entire interaction flows
Context Management Is 90% of the Skill in AI-Assisted Coding
The real skill in AI-assisted coding is not prompting - it is context management. Persistent memory, CLAUDE.md files, and layered context separate productive developers from frustrated ones.
Reducing Context Switching Cost with Running Notes - How AI Agents Solve the Same Problem
Context switching destroys productivity because you lose your mental model. Running notes files help humans, and CLAUDE.md does the same thing for AI agents.
Cowork vs Claude Code: Why Terminal Gives You More Control
Claude Code in the terminal offers more control than GUI alternatives like Cowork - especially when running 5 parallel instances on the same codebase.
Developers Are Becoming Their Own Business Analysts in the AI Era
The most productive developers now spend their day writing detailed requirements and acceptance criteria, then handing them to Claude. Writing specs is the
Explicit Acceptance Criteria in CLAUDE.md to Stop Premature Victory
How adding explicit acceptance criteria to CLAUDE.md stops Claude Code from declaring victory prematurely. Tests must pass, files must exist, no regressions.
Running 5 AI Agents on the Same Codebase Without Branch Isolation
Lessons from running 5 Claude Code agents in parallel on a Swift, Rust, and Flutter desktop app. Same repo. Same branch. No isolation.
Five Months In: Why Parallel Claude Code Beats Nested Subagents
After five months of trying subagents, the nesting limitations made them impractical. Running 5 separate Claude Code processes in parallel on the same repo
From Copilot to Claude Code - Why a 200-Line CLAUDE.md Changed Everything
How switching from GitHub Copilot to Claude Code with a 200-line CLAUDE.md running 5 parallel agents transformed a solo developer's entire workflow.
The Shift from Writing Code to Writing CLAUDE.md Specifications
Six months ago my workflow was Swift, Rust, and Flutter by hand. Now I write CLAUDE.md files and let agents handle the implementation.
Large SaaS Claude Workflow - Five Agents Running Off the Same CLAUDE.md Spec
How to write everything in CLAUDE.md and run 5 parallel Claude agents off the same spec for large SaaS projects. A practical workflow guide.
How MCP Servers Changed My Coding Workflow After 10 Years of Backend Dev
MCP servers eliminated copy-pasting between apps. Direct tool interaction from Claude Code changed how a backend developer writes and ships code.
Building Persistent Memory for Claude Code Agents with CLAUDE.md
Why CLAUDE.md is the only memory that survives across Claude Code sessions. How to build persistent context for 5 parallel agents working on the same repo.
When Developers Stop Writing Code and Start Reviewing AI Agents
Going from writing code to mass-reviewing output from 5 parallel Claude agents. Haven't typed a function in weeks. The new developer workflow is review, not
Stop Losing Context When Claude Code Compacts - Run It Inside tmux with Logging
Claude Code clears your terminal scrollback when it compacts context. The fix: run it inside tmux with logging enabled so you never lose conversation history.
The Irony of Writing Documentation That AI Agents Actually Read
Developers now write more documentation than ever - but it is CLAUDE.md specs for AI agents. The irony: AI agents read every word, which is more than most