Workflow
51 articles about workflow.
Enterprise Automation Feedback Loops: How to Build Systems That Self-Correct
Enterprise automation feedback loops let workflows detect failures, adjust parameters, and recover without human intervention. Learn the architecture, patterns, and pitfalls.
How an AI Agent Handles Repetitive Desktop Workflows So You Don't Have To
Building a macOS agent that controls browser and desktop to automate repetitive tasks like filling forms and navigating between apps.
Using AI Agents to Manage Context Switching and Parallel Workstreams
Constant context switching kills productivity. AI agents can hold context for you, run tasks in parallel, and let you pick up where you left off without
Automation Does Not Fix a Broken Process - Do It Manually First
Building elaborate automation before validating the underlying workflow wastes time. Track your manual process for a week, identify what actually costs 30+
Blocking and Waiting Are Not the Same Kind of Nothing
Blocking has a promise attached - something will resolve. Waiting has no such guarantee. Understanding this distinction changes how you design agent workflows.
Bridging AI Chat and Coding Agents with Shared Context Files
There is a wall between AI chat interfaces and coding agents. CLAUDE.md files and shared context documents break down that wall and make both tools more
Tell Your Coding Agent to Ship Small Chunks
Large AI-generated PRs are unreviewable. Ship features in small chunks with per-feature CLAUDE.md specs and separate agent sessions for each piece.
Building Custom MCP Tools to Connect Claude Code to Production Systems
How to build custom MCP tools that give Claude Code direct access to your production databases, APIs, and internal services. With working TypeScript examples and safety boundary patterns.
Dumb Orchestrator With Smart Workers Beats One Big Agent
A simple decision-tree orchestrator routing tasks to specialized worker agents - browser, accessibility, sequential - is more reliable than a single
Explicit Checkpoints Prevent Context Drift in AI Agent Sessions
Explicit checkpoints where the human confirms before continuing save long agent sessions from context drift. How pausing for confirmation prevents
I Got Hired to Automate an Entire Company
When the mandate is automate everything, the hardest part is deciding what to automate first. Prioritization determines whether automation saves time or
I Hate Being Human Glue Between AI Steps - Spec File as the Deliverable
Stop being the glue between AI agent steps. Specification-first development lets you define what you want once and let agents execute autonomously.
Anyone Else Losing Track of ChatGPT Conversations?
How naming conventions with project prefixes can save you from drowning in hundreds of unnamed ChatGPT conversations.
Managing Multiple AI Agents: How to Filter Signal From Noise
Running many AI agents creates an overwhelming amount of output. Concrete strategies for filtering agent noise, tiering notifications, using aggregation, and building the morning review workflow that actually works.
Using Multiple LLMs for Multi-Agent Workflows - Orchestration Patterns That Work
How to run multi-agent workflows with different LLMs for different subtasks. Claude as orchestrator, specialized models for specific jobs, and env var
You Don't Need a Pre-Session Hook - Human Judgment Catches What Hooks Miss
Automated pre-session hooks sound appealing but miss the point. The human who notices context problems is doing work that no automation can replace
Notifications ON Survey - Agents That Need Notifications Cannot Plan Their Own Work
If your AI agent relies on notifications to know what to do next, it cannot plan its own work. A survey on notification dependency reveals a deeper agent
The One Rule That Makes AI Automation Stick - Automate What You Hate First
Most AI automation projects fail because people automate the wrong things. The one rule that works: start with the task you hate most. Motivation sustains
Running Parallel AI Agents on Isolated Git Worktrees for Small, Reviewable PRs
The biggest problem with AI-generated PRs is scope creep - agents touch dozens of files across unrelated concerns. Isolated git worktrees with one agent per concern fixes this and produces PRs humans can actually review.
How I Use AI Through a Repeatable Workflow to Stop Fixing the Same Mistakes
Phase splitting and a spec-first approach create a repeatable AI coding workflow. Plan first, implement second, review third. The structure prevents
I Rarely Use Planning Mode Anymore - Context Windows Are Big Enough
Planning mode was essential at 8K tokens. With 200K context windows - and 1M in Claude Opus 4.6 - the model can see your entire codebase and figure out the approach as it goes. Here is when it still matters.
How Developers Actually Use AI in Their Coding Workflow
What real AI-assisted development looks like vs the demo version. Five agents doing heavy lifting while you architect - the workflow nobody shows on Twitter.
How Do You Agent - Running 5-8 Claude Code Agents in tmux
Practical guide to running 5-8 AI coding agents simultaneously on one codebase using tmux - session management, task decomposition, and real-world parallel
Stop Pitching Automation and Start Doing Free Teardowns
Pitching automation gets pushback. Free workflow teardowns get trust. How to run a teardown, what to look for, and why people sell themselves once they see the time breakdown.
The Default Flipped
The default is now to use an agent, not avoid one. The burden of proof shifted - you need a reason NOT to use an agent, not a reason to use one.
The Synthesis Layer - Where Raw Outputs Become Coherent
AI agents generate raw outputs from multiple tools and sources. The synthesis layer is where those fragments become coherent, actionable information.
tmux Beats Multiple IDE Windows for Managing AI Agents
Instead of juggling five VS Code windows, run Claude Code in tmux panes. Here's why terminal-based agent management is faster and more reliable than
Queue Up a Clear So You Can Queue Up Work - tmux Sessions and Git Worktrees
Running one tmux session per agent with separate git worktrees lets you queue up work without context collision. Clear the workspace before loading the next
What Humans Learn from AI and Vice Versa
AI learns guardrails and judgment from humans. Humans learn consistency and speed from AI. The best teams treat this as a bidirectional learning relationship.
Real Productivity Needs Cross-App Automation - Not Single-App AI
Draft in Docs, send via email, update the spreadsheet, post to Slack. Most AI tools only work inside one app. Cross-app automation is where real time
Running AI Agents as Actual Employees in Real Workflows
How to run multiple Claude Code instances in parallel as actual team members - task assignment patterns, git worktree isolation, coordination rules, and real workflow examples from daily use.
Browser Agents Are Impressive - But Desktop Control Is the Next Step
Browser automation handles web tasks well. But your workflow includes files, native apps, system settings. Full desktop control through accessibility APIs
The Copy-Paste-Debug Loop Is Killing Your Productivity
Copying code from ChatGPT, pasting it, watching it fail, and repeating wastes more time than writing the code yourself. Here is why agentic coding fixes this and how the numbers compare.
When to Use Claude CoWork vs Claude Code for Browser Automation
Claude Code excels at file editing and terminal work. CoWork and desktop agents shine when you need browser automation as part of your dev workflow
CSS Conventions in CLAUDE.md for 5 Parallel Agents
How putting all CSS conventions in CLAUDE.md lets you run 5 parallel Claude Code agents that all produce consistent, on-brand styling without conflicts.
Dual-Input AI Setup - Voice for Direction While Typing to Parallel Agents
Run voice commands to one agent for high-level direction while typing detailed prompts to Claude Code instances. Dual-input workflows maximize throughput
OpenClaw Is NOT for Coding - Desktop Agents Handle Your Entire Workflow
Why computer use agents are not just coding tools - the real value is handling emails, browser tasks, documents, and CRM through voice-first desktop automation.
Pair Programming with AI - Write the Spec First, Approve the Plan
The best workflow for AI pair programming: write a short spec, let the agent propose its plan before writing any code, then approve step by step. Control
Parallel AI Agents Only Work with Genuinely Isolated Tasks
Running 5 AI agents in parallel sounds great until they step on each other's files. The key to parallel agents is genuinely isolated tasks with zero overlap.
Rebuilding a Website from Lovable to Claude Code - Why Custom Skills Win
Why rebuilding a Lovable-generated website with Claude Code and custom skills produces better results. Custom skills encode your workflow, not just your code.
Organize SKILL.md Files Per Folder for Parallel Agent Isolation
How maintaining 30+ skill specs with clean per-folder isolation gives each parallel agent the exact context it needs without noise.
Stop Fighting the Context Limit - Scope Each Agent to One Small Task
Instead of cramming everything into one LLM context window, scope each AI agent to a single small task. Fix this crash. Add this button. One job, one agent.
Tmux for Parallel AI Agents - Layout, Feedback Loops, and Review Workflow
How to use tmux to monitor multiple AI coding agents simultaneously, catch failures fast, and build a terminal review workflow that keeps output clean.
What Running Parallel AI Agents Actually Feels Like
The honest experience of running 3-5 AI coding agents simultaneously - the chaos, the triaging, why it still works, and how experienced users manage the overhead.
Managing Parallel AI Agents with tmux and Git Worktrees
Step-by-step setup for running multiple AI coding agents in parallel using tmux panes and git worktrees - separate branches, separate directories, zero file conflicts.
Using Claude Code Hooks for Native macOS Swift Development
How Claude Code hooks transformed native macOS Swift development. Auto-format on save, run tests before commit, validate builds - the workflow game changer.
Why Mandating AI Coding Tools Fails - Organic Adoption Wins
Forcing developers to use AI coding tools backfires. The developers who get the most from AI got there organically because it genuinely made them faster
How to Manage Multiple Claude Code Sessions with tmux
Running multiple AI coding agents at once gets chaotic fast. Here is how tmux keeps your Claude Code sessions organized with named sessions, branch
Using Claude as an Execution Layer - Markdown Specs, MCP Tools, No Traditional Code
What happens when your entire app is markdown specs that Claude executes, with MCP servers as the only real code. A year of building this way.
Planning a Trip with an AI Desktop Agent - Flights, Hotels, Itinerary, and Email in One Command
The most impressive AI agent task is not coding - it is the multi-app workflows like researching flights, drafting itineraries in Google Docs, and emailing
Local LLMs Are Not Just for Inference Anymore - Real Workflows on Your Machine
The shift to local LLMs is moving beyond chat and inference into real desktop automation. Browser control, CRM updates, document generation - all without