Developer Workflow

39 articles about developer workflow.

1.6M Git Events Show AI Code Needs More QA

·12 min read

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.

code-reviewqaai-codinggitdeveloper-workflow

AI Made My Team Write 21% More Code - The Review Queue Doubled

·2 min read

AI does not remove bottlenecks, it moves them downstream. When code generation gets faster, code review becomes the new constraint.

code-reviewbottleneckai-codingproductivitydeveloper-workflow

AI Tickets Need Way More Context Than Human Tickets

·2 min read

Writing Jira tickets for AI coding agents requires fundamentally different thinking. Humans infer meaning from vague tickets - AI agents go literal. How to

ai-agentsproject-managementjiradelegationdeveloper-workflowsaas

The Beauty of Deleting Code - Why Less Is Almost Always Better

·3 min read

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.

code-qualityrefactoringsimplicitydeveloper-workflowengineering

Skills vs Sub-Agents in Claude Code - When to Use Each Pattern

·2 min read

How to structure Claude Code skills vs sub-agents - splitting by type, managing 10+ skills, and choosing the right pattern for each workflow.

claude-codeskillssub-agentsarchitecturedeveloper-workflow

Drowning in AI? Start with a CLAUDE.md File

·2 min read

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.

ai-codinglearningclaude-mddeveloper-workflowgetting-started

I Measured Every Hour My Human Worked for Two Weeks

·2 min read

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

productivitytime-trackingai-agentsdeveloper-workflowcode-review

Multi-Agent Code Review Loops - The Simple Pattern That Works

·2 min read

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.

multi-agentcode-reviewparallel-agentsai-codingdeveloper-workflow

The Real Bottleneck with Parallel Agents Is Not Compute - It Is Git Conflicts

·2 min read

Running 5 coding agents in parallel sounds great until they all edit the same files. The bottleneck is coordination, not compute.

parallel-agentsgit-conflictsmulti-agentdeveloper-workflowcoordination

Sandbox vs YOLO Mode for AI Coding Agents

·3 min read

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.

ai-codingsandboxyolo-modedeveloper-workflowgit

Spotify Devs Haven't Written Code Since December - Specification-Driven Development

·2 min read

Specification-driven development is replacing hands-on coding. Write specs, let AI agents generate the implementation. Here's why it works.

specification-drivenai-codingno-codedeveloper-workflowai-agentsclaudeai

Structuring Large Codebases for AI Agent Navigation with Layered Context

·3 min read

CLAUDE.md files at each directory level help AI agents navigate large codebases effectively. Learn the layered context pattern for better AI-assisted

claude-mdcodebase-structureai-agentsdeveloper-workflowcontext-management

Cursor Caught a Race Condition - Voice-Controlled Coding and Verbal Debugging

·2 min read

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.

voice-codingverbal-debuggingrace-conditionai-codingdeveloper-workflowcursor

AI Coding Technique: Change One File, Migrate the Entire Codebase

·2 min read

A practical AI coding technique - manually change one SwiftUI file, then have Claude Code migrate 1500+ hardcoded calls across the entire codebase to match.

ai-codingclaude-codemigrationswiftuirefactoringdeveloper-workflow

Fixing AI Goldfish Memory with CLAUDE.md Constraints

·3 min read

When your AI agent confidently says it made a change but nothing changed, CLAUDE.md constraints prevent confident-but-wrong behavior across sessions.

claude-mdai-agentsmemoryconstraintsdeveloper-workflowclaude-code

Autonomous Multi-Session AI Coding Without Worktrees

·2 min read

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.

claude-codeparallel-agentsgit-worktreesmulti-sessiondeveloper-workflow

Why CLAUDE.md Is the Entire Game for Parallel Claude Code Agents

·2 min read

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.

claude-mdclaude-codeparallel-agentsdeveloper-workflowai-orchestration

Hitting Claude's Context Limit Mid-Build and How CLAUDE.md Fixes It

·2 min read

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.

claude-codecontext-windowclaude-mddeveloper-workflowproductivity

When Claude Files Bug Reports Against Its Own Code - And They Are Real

·2 min read

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.

claude-codeclaude-mdparallel-agentsbug-reportsdeveloper-workflow

Put 'Challenge My Assumptions' in Your CLAUDE.md

·3 min read

Adding assumption-challenging directives to CLAUDE.md prevents AI agents from blindly implementing bad ideas. Make your agent argue with you before it builds.

claude-mdai-agentsdeveloper-workflowcode-qualitybest-practices

Is Claude Overkill? Adding Anti-Over-Engineering Directives to CLAUDE.md

·2 min read

Claude Code tends to over-engineer solutions. Adding 'avoid over-engineering, only make changes that are directly requested' to your CLAUDE.md keeps it

claude-codeclaude-mdover-engineeringdeveloper-workflowbest-practices

Making Claude Code Skills Repeatable - 30 Skills Running Reliably

·3 min read

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

claude-codeskillsreliabilityautomationdeveloper-workflow

Why the Claude API Plan Is a Game Changer for Concurrent Agent Sessions

·2 min read

Claude usage limits frustrate developers until they discover the API plan. Here is why concurrent sessions on a Swift/Rust codebase demand it.

claude-codeapi-planusage-limitsconcurrent-sessionsdeveloper-workflow

The Scope Shift in Code Copying - From Stack Overflow Snippets to Full AI Interaction Flows

·2 min read

AI changed how developers copy code. Instead of grabbing individual accessibility API snippets from Stack Overflow, we now generate entire interaction flows

ai-codingaccessibility-apidesktop-automationdeveloper-workflowstack-overflow

Context Management Is 90% of the Skill in AI-Assisted Coding

·5 min read

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.

ai-codingcontext-managementclaude-codepersistent-memorydeveloper-workflow

Reducing Context Switching Cost with Running Notes - How AI Agents Solve the Same Problem

·3 min read

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.

context-switchingproductivityclaude-mdai-agentsdeveloper-workflow

Cowork vs Claude Code: Why Terminal Gives You More Control

·2 min read

Claude Code in the terminal offers more control than GUI alternatives like Cowork - especially when running 5 parallel instances on the same codebase.

claude-codecoworkterminalparallel-agentsdeveloper-workflow

Developers Are Becoming Their Own Business Analysts in the AI Era

·2 min read

The most productive developers now spend their day writing detailed requirements and acceptance criteria, then handing them to Claude. Writing specs is the

developer-workflowai-codingrequirementsspecificationsclaude-code

Explicit Acceptance Criteria in CLAUDE.md to Stop Premature Victory

·2 min read

How adding explicit acceptance criteria to CLAUDE.md stops Claude Code from declaring victory prematurely. Tests must pass, files must exist, no regressions.

claude-mdacceptance-criteriaclaude-codetestingdeveloper-workflowquality

Running 5 AI Agents on the Same Codebase Without Branch Isolation

·3 min read

Lessons from running 5 Claude Code agents in parallel on a Swift, Rust, and Flutter desktop app. Same repo. Same branch. No isolation.

parallel-agentsmulti-agentcodebase-managementdeveloper-workflowclaude-code

Five Months In: Why Parallel Claude Code Beats Nested Subagents

·2 min read

After five months of trying subagents, the nesting limitations made them impractical. Running 5 separate Claude Code processes in parallel on the same repo

claude-codeparallel-agentssubagentsdeveloper-workflowproductivity

From Copilot to Claude Code - Why a 200-Line CLAUDE.md Changed Everything

·3 min read

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.

claude-codecopilotclaude-mdparallel-agentsdeveloper-workflow

The Shift from Writing Code to Writing CLAUDE.md Specifications

·3 min read

Six months ago my workflow was Swift, Rust, and Flutter by hand. Now I write CLAUDE.md files and let agents handle the implementation.

claude-mdai-agentsdeveloper-workflowspecificationsproductivity

Large SaaS Claude Workflow - Five Agents Running Off the Same CLAUDE.md Spec

·2 min read

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.

claude-codeclaude-mdparallel-agentssaasdeveloper-workflow

How MCP Servers Changed My Coding Workflow After 10 Years of Backend Dev

·3 min read

MCP servers eliminated copy-pasting between apps. Direct tool interaction from Claude Code changed how a backend developer writes and ships code.

mcpbackend-developmentdeveloper-workflowclaude-codeproductivity

Building Persistent Memory for Claude Code Agents with CLAUDE.md

·2 min read

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.

claude-codeclaude-mdpersistent-memoryparallel-agentsdeveloper-workflow

When Developers Stop Writing Code and Start Reviewing AI Agents

·3 min read

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

code-reviewparallel-agentsclaude-codedeveloper-workflowai-developmentproductivity

Stop Losing Context When Claude Code Compacts - Run It Inside tmux with Logging

·3 min read

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.

claude-codetmuxloggingdeveloper-workflowcontext-management

The Irony of Writing Documentation That AI Agents Actually Read

·3 min 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

documentationclaude-mdspecsdeveloper-workflowai-agents

Browse by Topic