Blog Archive
All published posts in one crawlable list.
-
How Apple Designs for the Worst Day, Not the Best
-
Prompt engineering for code: Few-shot examples that teach taste, not just format
-
Handoff, Sidecar, and Universal Clipboard: Make Your Apple Devices Act Like One
-
The Dirt Under the Algorithm
-
Why Fast Hardware Still Feels Slow
-
Logging every turn so you can learn from the agent, not just use it
-
How AI Is Rewriting the Crop Forecast
-
The Physics of Heat, Noise, and Perceived Quality
-
The overlooked value of structural search and replace
-
The School That Got AI Right
-
Which iPad Should You Buy in 2026? The Whole Lineup, Decoded
-
Why Most AI Products Feel Like Features, Not Tools
-
When to reach for Cascade and when to fall back to pure editing
-
Master Spotlight: How to Run Your Whole Mac From the Keyboard
-
Standardized Tests' Last Stand
-
When Software Becomes Invisible, You've Won
-
Keeping tests running in the background while the agent edits
-
The Global AI Classroom Gap
-
Mac mini vs iMac vs Mac Studio: Which Desktop Mac Fits Your Desk?
-
Why Apple Products Are Easier to Trust
-
Keeping answers tight with explicit output contracts
-
How to Get a Full Day of Battery Out of Your iPhone Again
-
The STEM Mismatch
-
The Myth of 'Future-Proof' Technology
-
Treating Codex as a junior engineer with an infinite patience budget
-
What We Talk About When We Talk About Critical Thinking
-
MacBook Air 13 vs 15: Does the Bigger Screen Earn Its Price?
-
Why AI Frameworks Fail Outside Demos
-
Diffing agent output against main before you trust a single file
-
How to Use iCloud Properly Across Every Apple Device Without Paying for 2TB
-
The Homework Industrial Complex
-
The Difference Between Testing a Product and Living With It
-
Leaning on Copilot Edits for multi-file, reviewable diffs instead of raw chat
-
Higher Education Is About to Find Out What It Actually Sells
-
What Makes a Product Review Age Well After 2 Years
-
Caching embeddings locally for a private retrieval layer
-
The Personalization Trap
-
How Much RAM and Storage Do You Really Need on a Mac?
-
The Quiet Revolution of Apple Silicon (That Nobody Talks About)
-
The honest case for agents that only suggest
-
Switching From Windows to Mac: A Survival Guide for Your First Week
-
What the Calculator Wars Actually Teach Us
-
Why Most 'Pro' Products Are Designed for Nobody
-
Why your wiki should probably be an MCP resource, not a tool
-
The Teacher in the Age of AI
-
MacBook Air vs MacBook Pro: Which One Are You Actually?
-
Writing acceptance tests first, agents second
-
How to Force-Restart Any Frozen Apple Device: Mac, iPhone, iPad, and Watch
-
AI Tools That Feel Smart but Make You Slower
-
Every Student Has an AI. Now What Actually Changes?
-
Diffing prompts the way you diff code
-
The Science of Fatigue-Free Interfaces
-
The Tutor Problem
-
Which Mac Should You Buy in 2026? An Honest Decision Tree
-
Cline and Roo Code: open-source agents teach you more than closed ones
-
First Day With a New Mac: 12 Things to Change Before You Touch Anything Else
-
Why Benchmarks Lie More Than Marketing Claims
-
What EdTech Companies Are Actually Selling
-
JetBrains AI Assistant: not every green inspection is an agent task
-
Apple Doesn't Optimize for Speed. It Optimizes for Flow.
-
The Academic Integrity Crisis That Wasn't
-
The Hidden Cost of Power User Features Nobody Uses
-
Windsurf: the value of a pause button in an otherwise relentless agent
-
Why Schools Are Getting AI Wrong
-
Cheap wins: the keybindings that turn Cursor back into a proper editor
-
Why the Best Technology Feels Boring at First
-
The August Effect: How the Quietest Month in Tech Decides the Rest of the Year
-
The Complete Mac AI Setup, 2026 Edition — Everything in One Guide
-
Google Gemini: Using long context to write migration scripts that respect every edge
-
What July Taught Us About the Future of Technology
-
The 2023 AI Predictions That Were Most Wrong (And What We Should Learn)
-
What 100 Days of Daily Local AI Use Taught Me About the Hype
-
ChatGPT Codex: Splitting epics into Codex-sized tasks on purpose
-
Technology We Buy for Feeling, Not Features
-
Why AI Startups Pivot — And What the Pivot Usually Reveals About the Real Business
-
The Prompt Library Every Mac Power User Should Steal
-
Claude Code: Quiet art of pausing the agent instead of letting it churn
-
Why Long-Term Reviews Are More Valuable Than First Impressions
-
The Political Economy of Open Source AI: Who Benefits and Why
-
From Idea to Published App in a Weekend — With AI on a Mac
-
GitHub Copilot: Underrated power of /explain on legacy code no one dares to touch
-
The Science of Ergonomics: Why Some Products Don't Tire You Even After Hours of Use
-
Google Made the Web Worse and Is Now Making AI the Same Way
-
AI Meeting Notes That Don't Embarrass You — The Local Setup
-
Local LLMs with Ollama: When a local 7B beats a cloud 70B in latency-sensitive loops
-
How the Meaning of Premium Product Is Changing in 2026
-
Why Benchmarks Are Lying to You About AI Progress
-
The Multi-Mac AI Cluster — Insane Overkill or the Future?
-
Agentic coding: How to review a PR an agent opened in the middle of the night
-
When Software Becomes Invisible: The Ideal State of Technology
-
The Next Billion AI Users Won't Speak English. That's a Bigger Problem Than You Think.
-
Why I Downgraded From the Biggest AI Model — and Got Better Results
-
MCP servers: Composing agents over a catalogue of shared MCP tools
-
Why Apple Usually Doesn't Win on Paper, But Wins in Practice
-
The Real Reason Tech Layoffs Follow a Specific Pattern Every Single Time
-
The AI Language Learning Method That Replaced My Duolingo Streak
-
AI coding workflows: Treating diffs as the primary artefact, chat as exhaust
-
The Future of Consumer Electronics: Fewer Devices, More Context
-
How Stripe Quietly Became More Important to AI Than Any AI Company
-
Local AI Security — What Can Actually Leak and How to Lock It Down
-
Prompt engineering for code: How to write a system prompt you can still read in six months
-
How Technology Influences Our Decision-Making More Than We Realize
-
What Nobody Explains About How a Transformer Actually Works
-
I Compressed 10 Years of Bookmarks Into One Searchable AI Brain
-
Cline and Roo Code: Roo modes that codify team-specific workflows
-
Reviews Without Benchmarks: How to Evaluate a Product Based on Real-World Usage
-
Why the Metaverse Failed and What That Means for AI's Optimistic Scenarios
-
The Freelancer's AI Stack — Run Your Whole Business From a MacBook
-
JetBrains AI Assistant: Writing specs as Markdown that Junie can consume
-
Why Power Users Are the Most Dangerous Target Audience for a Product
-
The Grid Problem Nobody in AI Is Talking About Publicly
-
MCP Explained — Why Your AI Can Finally Use Your Mac Apps
-
Windsurf: Pairing Cascade with a linter that refuses bad taste
-
How Product Design Changed After Apple Silicon Arrived
-
Software Always Eats the Hardware Advantage — Here's Why AI Will Be No Different
-
The Backup Strategy for People With 500GB of AI Models
-
Cursor: Right amount of automation before it becomes magical thinking
-
The Future of Ecosystems: Why the One That Annoys Users Least Will Win
-
China's AI Governance Strategy Is Smarter Than the West Admits
-
Your Mac Can Watch Videos for You — Local Vision Models Explained
-
Google Gemini: Generating Mermaid architecture diagrams the agent can then critique
-
The Science Behind Smoothness: Why Some Systems Feel Faster Even When They Aren't
-
The Specific Mechanism by Which LLMs Confabulate (And Why It Can't Be Fixed with More Data)
-
Local AI for Students — The Study System That Beats Tutoring
-
ChatGPT Codex: Auditing the diff, not the narrative – the code is the contract
-
When Is It Worth Buying a New Generation Product – and When Not at All
-
How Privacy Became a Luxury Product (And Who That Hurts Most)
-
The AI Photography Workflow Pros Run on MacBook Pros
-
Claude Code: Keeping Claude honest with explicit acceptance criteria, not vibes
-
How to Recognize When Technology Has Matured and Isn't Just Hype
-
What the Newspaper Industry's Death Teaches the Web About Surviving AI
-
Make Siri Actually Smart — The Local LLM Bridge Trick
-
GitHub Copilot: Copilot Spaces as shared context libraries for team onboarding
-
Why Most AI Features Today Don't Actually Solve Anything
-
Why 'Alignment' Is the Wrong Word for What We're Actually Worried About
-
I Tracked Every AI Query for a Month — The Results Changed My Setup
-
Local LLMs with Ollama: Thermal budget of a MacBook pretending to be a server
-
Invisible Details That Separate Premium Products From Average
-
France Had the Best AI Research in the World in 1990. Then This Happened.
-
The Spreadsheet Killer — Local AI Data Analysis on Your Mac
-
Agentic coding: Guardrails before autonomy, always
-
How Apple Tests Products in Extreme Scenarios Users Will Never See
-
Why Neuroscience Got AI Wrong for Half a Century
-
AI Voice Cloning on Mac — Useful, Creepy, and How to Do It Right
-
MCP servers: Least-privilege auth for MCP in a real enterprise
-
The Future of Work: Hardware Is No Longer the Limit – We Are
-
The Data Center Workers Nobody Writes About
-
Why Your Next Home Server Should Be a Mac Mini, Not a Raspberry Pi
-
AI coding workflows: Scorecard question: did this PR have to exist?
-
Why Battery Life Is More Important Than GPU Performance
-
Why Venture Capital Makes AI Both Better and Worse at the Same Time
-
The Podcast Production Stack That Runs Entirely on One MacBook
-
Prompt engineering for code: Structured outputs: JSON schemas that keep agents honest
-
The Science of Attention: Why You Use Some Products Every Day and Others Not
-
What's Missing From Every AI Safety Conversation (And Why Nobody Wants to Bring It Up)
-
I Made My Mac Read Every Contract Before I Sign It
-
Cline and Roo Code: Building an internal guardrails library on top of Cline
-
What Hardware Actually Makes Sense to Buy Today (and What Is Just Marketing)
-
Japan's AI Strategy Failed in the 1980s. Here's What Europe Should Learn.
-
LM Studio vs. Ollama — The Local AI Showdown Nobody Wrote Honestly
-
JetBrains AI Assistant: When the IDE already knows the answer and the agent just needs to ask
-
Apple vs. Unnecessary Complexity: Why Fewer Features Often Means a Better Product
-
How Your Phone Became the Most Surveilled Object in Human History
-
The One Mac App Every AI Power User Installs First
-
Windsurf: What Windsurf teaches about the ergonomics of agent IDEs
-
The Silent Revolution: Why You Can't Recognize a Top Product at First Glance Anymore
-
The Quiet Extinction of the Software Engineer as We Knew It
-
Apple Notes + AI — The Knowledge System Hiding in Plain Sight
-
Cursor: Resetting indexes when completions start feeling stale
-
How to Recognize Technology That Will Still Be Relevant in Five Years
-
How the People Who Build AI Actually Use It (It's Very Different from How They Describe It)
-
Your MacBook Battery Can Handle 8 Hours of Local AI — Here's How
-
Google Gemini: Pairing Gemini with Code Assist for refactors that span a whole module
-
Why Most Product Reviews Have Zero Value for Real Decision Making
-
The Real Reason Silicon Valley 'Moved Fast and Broke Things' (It Wasn't a Philosophy)
-
The AI Reading Workflow That Lets Me Process 50 Articles a Day
-
ChatGPT Codex: Keeping the human in the loop by requiring explicit acceptance
-
What Happens When We Stop Chasing New Features and Start Optimizing Old Ones
-
What IBM Watson's Failure Tells Us About Every AI Hype Cycle That Follows
-
Run DeepSeek-Class Models on a Mac — The Complete Guide
-
Claude Code: Hooks that enforce lint, test and security gates before any write
-
The Future of Laptops: Why Performance Is No Longer the Main Selling Point
-
Every Nation That Dominated One Tech Era Got Left Behind in the Next
-
I Gave AI Full Access to My Calendar — Here's My Week Now
-
GitHub Copilot: Constraining the agent with .github/copilot-instructions.md for reproducible behaviour
-
How Technology Is Changing the Way We Sleep – and Why It's Not Always for the Better
-
The Intelligence Illusion: Why What AI Does Is Not Thinking
-
The Mac Terminal Commands That Unlock Hidden AI Power
-
Local LLMs with Ollama: Running evals locally before trusting a new model
-
Why Most Smart Products Actually Get Dumber After a Year of Use
-
What We Got Wrong About AI in the First Half of 2026: A Mid-Year Reckoning
-
What's Coming Next for AI on Mac — and How to Be Ready
-
Agentic coding: Planning outputs as the real product of the first turn
-
Monthly Retrospective: What Technology Taught Us in June 2026
-
The Attention Economy Was Just the Prototype. AI Is the Real Thing.
-
The 7 AI Mistakes Mac Power Users Keep Making
-
MCP servers: Testing MCP servers with a plain JSON-RPC client first
-
What the Ideal Home Office Looks Like According to Science
-
Why Democracy and AI Are on a Structural Collision Course
-
Mac Studio as a Family Photo AI — Find Any Memory in Seconds
-
AI coding workflows: Pair-with-AI rituals that survive a team of ten
-
Technologies That Will Disappear Within Five Years
-
The Country That Will Win AI Without Building a Single Model
-
I Connected AI to My Smart Home Through a Mac Studio
-
Prompt engineering for code: Difference between role prompts and persona cosplay
-
The Best Technology Investments Aren't Gadgets, but Habits
-
Why the 'AGI Is Near' Crowd Is Both Completely Right and Catastrophically Wrong
-
The AI Email Workflow That Saves Me 5 Hours Every Week
-
Cline and Roo Code: Routing cheap models for boilerplate, frontier models for design
-
Apple vs. the Open World: Does the Walled Garden Still Make Sense?
-
Every Historical Monopoly Predicted What Big Tech Will Do Next
-
Why Every Writer Needs a Local LLM (and How to Set One Up)
-
JetBrains AI Assistant: Scoping Junie tasks by module to keep review tractable
-
Test Data: The Unsung Hero of the QA World
-
The Real Cost of Training an AI Model That Nobody Wants You to Know
-
AI Video Upscaling on Mac — Restore Old Family Videos This Weekend
-
Windsurf: Using write-mode sparingly to protect your muscle memory
-
How to Automate Your Personal Workflow with Python
-
Why AI Will Never Replace Lawyers (And That's Not the Point)
-
The M-Series Chip Buying Guide for AI — What Actually Matters
-
Cursor: Pairing tab with explicit intent comments to steer predictions
-
Monitoring Is More Important Than New Features
-
The Semiconductor Shortage Was a Dress Rehearsal. The Real Crisis Is Coming.
-
Local AI Translation Beats Google Translate — and It's Private
-
Google Gemini: Auditing IAM policies with a million-token sweep over Terraform
-
Micro-SaaS as a Side Project for Developers
-
Why the EU's AI Act Is Both the Best and Worst Thing That Could Have Happened
-
I Ran an AI Agent Overnight on My Mac — Here's What It Built
-
ChatGPT Codex: Parallelising bug-fix attempts and picking the cleanest patch
-
How Programming Will Change When AI Writes 95% of Code
-
The Engineer Who Built the Foundation of Modern AI (And Died Without Recognition)
-
The Truth About Mac vs. NVIDIA for AI — I Tested Both
-
Claude Code: Checkpointing long sessions to protect yourself from context rot
-
The Most Underrated macOS Features That Save Hours Every Week
-
Why Every Company That Claims to 'Do AI' Is Lying to You in Exactly the Same Way
-
Apple Shortcuts + AI Is the Automation Stack Nobody Talks About
-
GitHub Copilot: Switching models mid-conversation when reasoning quality starts to degrade
-
Why Smartwatches Will Soon Replace Half of Medical Check-Ups
-
The Countries Being Left Behind by AI (And Why That Should Terrify Everyone)
-
RAG on Your Own Notes — Build a Second Brain That Actually Answers
-
Local LLMs with Ollama: Pairing Ollama with Continue or Cline for a private IDE
-
What Your Phone Knows About You in a Single Day
-
The Ghost in the Machine: What AI Hallucinations Reveal About Intelligence
-
The Hidden macOS AI Features Apple Shipped Quietly
-
Agentic coding: What to log when an agent writes for you
-
The End of Passwords Is Closer Than You Think: The World After Passkeys
-
How the Pentagon's Budget Quietly Shapes Every AI Tool You Use
-
Your Mac Studio Can Replace a $1,500/Month AI API Bill
-
MCP servers: Treating MCP servers as a supply chain, not a side project
-
How to Build a Personal AI Assistant Without a Single Line of Code
-
Why Small AI Models Are the Future and Nobody Wants to Admit It
-
Fine-Tune Your Own AI Model on a MacBook — Yes, Really
-
AI coding workflows: Daily shutdown routine that actually ships code
-
Why Privacy Is the New Luxury of the Digital Era
-
Every Major Tech Partnership Ends the Same Way — Here's Why
-
The Mac Menu Bar Apps That Give You AI Everywhere
-
Prompt engineering for code: Turning specs into prompts without losing the nuance
-
Technologies That Look Boring Today But Will Change the World
-
What the Steam Engine Teaches Us About AI Inequality
-
I Let AI Organize 20 Years of Photos and Files on My Mac
-
Cline and Roo Code: Plan mode as a cheap dry run before committing budget
-
iPad as a Full Computer in 2026 – Reality Without Marketing
-
The Last Human Skill: Why Judgment Cannot Be Automated Away
-
The Raycast AI Workflow That Replaced 5 Mac Apps for Me
-
JetBrains AI Assistant: Using inspections as invisible rails for the agent
-
What Happens to the Internet When AI-Generated Content Floods It
-
Why the Next Financial Crisis Will Be Caused by an Algorithm Nobody Understands
-
Apple Intelligence vs. Local LLMs — What Apple Doesn't Tell You
-
Windsurf: Keeping the editor quiet until you ask for help
-
M1, M2, M3, M4, M5: Does It Still Make Sense to Chase a New Mac Every Year?
-
How China Built a Parallel Internet (And Why It's Actually Better for AI)
-
Your Mac Can Summarize Any YouTube Video in 30 Seconds
-
Cursor: Composer runs that land a feature in a single reviewable diff
-
Why Traditional Apps Will Soon Be a Thing of the Past
-
The Biggest Lie in Tech Is Being Told Again, Louder Than Ever
-
Run Stable Diffusion on Your Mac — No Cloud, No Limits, No Cost
-
Google Gemini: Using Gemini CLI as glue between Cloud Run and your local repo
-
Minimalist Digital Life: How I Reduced My Apps by 80%
-
The New Standard Oil: How AI Is Concentrating Wealth Like the Robber Barons
-
The AI Coding Setup That Made Me 3x Faster on My MacBook
-
ChatGPT Codex: Using AGENTS.md to describe the environment the sandbox must respect
-
How AI Will Change Education Before Teachers Even Realize It
-
Why AI Systems Have No Memory (And Why That's the Most Profound Thing About Them)
-
I Built a Private ChatGPT for My Family on a Mac Mini
-
Claude Code: Writing a CLAUDE.md that captures tacit team knowledge
-
Apple Vision Pro After Two Years: Revolution or Expensive Toy?
-
The Country That Holds the AI Supply Chain Hostage
-
The 128GB Mac Studio Trick AI Researchers Don't Want You to Know
-
GitHub Copilot: Running Copilot CLI as a scriptable review step inside pre-commit hooks
-
The Biggest Tech Myths People Still Believe
-
How Big Tech Learned to Make Governments Afraid of Regulating AI
-
Stop Paying for Transcription — Your Mac Does It Better, Free
-
Local LLMs with Ollama: Keeping a small local model honest with tight prompts
-
The Truth About Batteries: Why Phone Battery Life Hasn't Really Improved in Years
-
The Hidden Math That Explains Why AI Keeps Getting Smarter
-
Apple MLX Is the Most Underrated AI Framework Right Now
-
Agentic coding: Difference between an agent and a slow script
-
What a Typical Work Day Will Look Like in 2030
-
Why Open Source AI Will Win Even If It Loses
-
The MacBook Pro Setting That Doubles Your AI Performance
-
MCP servers: Exposing read-only resources before you expose write actions
-
The Chip That Started the Second Cold War
-
I Replaced My $20 AI Subscriptions With One Mac Studio
-
AI coding workflows: Small reversible steps instead of one heroic prompt
-
The Hidden iPhone Feature 90% of People Never Use – But Should
-
Why the AI Race Is Really a Power Grid Race
-
Your Mac Is a Local AI Supercomputer You're Using at 10% Capacity
-
Prompt engineering for code: Acceptance criteria as the only prompt that matters
-
Why 2026 Changes Personal Productivity Rules More Than the Last Decade Combined
-
The Future of Search: Why Google Is Slowly Losing Control of the Internet
-
Cline and Roo Code: Auditing every tool call before it touches a file
-
Which Technologies Will Really Change the World in the Next 10 Years
-
JetBrains AI Assistant: Refactorings that remain safe because JetBrains understands types
-
Why Simplicity Is the Greatest Innovation of the 21st Century
-
Windsurf: Flows that preserve intent across a long refactor
-
Sustainable Technology: Can Gadgets Be Ecological?
-
Cursor: Agent mode as a disciplined driver, not a replacement for review
-
Cybersecurity in an Era When Everything Is Online
-
Google Gemini: Debugging a production incident from a screenshot and a log bundle
-
The Future of Displays: MicroLED, Holograms, and Glasses Instead of Monitors
-
ChatGPT Codex: Scoping tasks tightly enough that the agent can finish in one pass
-
How Technology Is Transforming Education for the Next Generation
-
Claude Code: Using sub-agents for parallel research across a large codebase
-
Autonomous Cars: The Technical Dream vs Legislative Reality
-
GitHub Copilot: Pairing inline completion with a custom instructions file to enforce house style
-
Why Software Updates Matter More Than New Features
-
Local LLMs with Ollama: Picking a local model for the specific task, not for the benchmark
-
Home Robotics: We're Closer Than We Think
-
Agentic coding: Budgets as the only feature that stops a bad loop
-
The Future of Remote Work: Hybrid as the New Standard
-
MCP servers: Smallest MCP server that earns its keep
-
Apple and Privacy: The Last Big Competitive Advantage?
-
AI coding workflows: Review cycle that keeps agent output honest
-
How Programming Is Changing in the Era of Generative AI
-
Prompt engineering for code: Shortest prompt that still passes review
-
Microchips in Everyday Life: From Cars to Refrigerators
-
Cline and Roo Code: Picking a model per task instead of per editor
-
The Metaverse After the Hype: What Actually Remained?
-
JetBrains AI Assistant: Letting Junie drive while the IDE still owns correctness
-
Why Open Source Is the Key to Technological Progress
-
Windsurf: Cascade as a deliberate planning surface, not an auto-pilot
-
The Future of Data-Driven Healthcare and Wearable Electronics
-
Cursor: Writing .cursorrules that actually stay short and enforceable
-
The Apple Ecosystem as a Digital Fortress: Benefits and Limits
-
Google Gemini: Feeding an entire service plus its tests into a single prompt
-
The Technology of Silence: Why Offline Mode Is Coming Back
-
ChatGPT Codex: Letting Codex open the PR while you stay the reviewer of record
-
What Will the Office Look Like in 2030?
-
Claude Code: Planning mode as a cheap insurance policy against cascading edits
-
AI Ethics: Who Is Responsible for AI Mistakes?
-
GitHub Copilot: Using the @workspace agent to plan multi-file refactors before a single line is written
-
Why Small Devices Are Smarter Than Ever
-
Local LLMs with Ollama: Sunday-afternoon project: your own code reviewer that runs offline
-
The Future of the Internet Without Passwords: Passkeys and Digital Identity
-
Agentic coding: Building trust with agents the way you build it with juniors
-
Can AI Replace Programmers? Reality vs Myths
-
MCP servers: Where the protocol ends and your product begins
-
How Apple Silicon Changed the Rules for Developers
-
AI coding workflows: Resting the agent: when taking the keyboard back beats another turn
-
Batteries of the Future: Solid-State, Graphene, and What Comes Next
-
Prompt engineering for code: When to stop prompting and start coding
-
Why Software Is Becoming More Important Than Hardware
-
Cline and Roo Code: Treating the agent as a shell you can still read
-
Quantum Computing: Real Revolution or Just Marketing?
-
JetBrains AI Assistant: AI that respects your refactoring history instead of fighting it
-
The Future of Computers Without Keyboards: Voice, Gestures, and Neural Interfaces
-
Windsurf: Turning agent output into atomic, reviewable commits
-
How AI Is Changing Creative Work: Tool or Competition?
-
Cursor: Using MCP inside Cursor to give the agent a real toolbox
-
How to Build a Personal Knowledge Base for Developers
-
Google Gemini: Separating research (AI Studio) from execution (Code Assist) on purpose
-
Why Fewer Tools Is Often More: Minimalism in the QA Toolchain
-
The Economics of Famine as Policy
-
Monthly Retrospective: What April Taught Me About Technology and Productivity
-
ChatGPT Codex: Replaying failed tasks with tighter prompts instead of starting over
-
How Slave Trade Profits Financed Industrialization
-
Why Process Matters More Than Technology
-
Claude Code: Running Claude Code headlessly in CI as a structured reviewer
-
The Economics of the Linen Trade
-
Personal Automation Pipeline: From Idea to Finished System
-
GitHub Copilot: Wiring MCP servers into Copilot to give it domain-specific tools
-
How Trade Unions Changed Labor Markets
-
What Being a 10x Developer Actually Means
-
Local LLMs with Ollama: Quantisation choices that actually matter for code
-
The Economics of Colonial Land Systems
-
API Design from the User's Perspective, Not the Architect's
-
Agentic coding: Why short agent loops beat heroic ones
-
How the Scientific Revolution Changed Production
-
Developer Ergonomics: Setting Up Your Environment for Long Work Hours
-
MCP servers: Sandboxing MCP tool calls so one bad prompt cannot ruin a week
-
The Economics of Medieval Urban Growth
-
How to Build Your Own Micro-SaaS in a Weekend
-
AI coding workflows: Time-boxing agent loops before they eat the day
-
How American Tariffs Built Industrial Capacity
-
Why Good Enough Is Often Better Than Perfect
-
Prompt engineering for code: Prompts as contracts, not wishes
-
The Economics of the Amazon Rubber Trade
-
How to Conduct a Personal Workflow Audit
-
Cline and Roo Code: Memory banks that outlive a single session
-
The Economics of Plantation Agriculture
-
Automated Tests That Actually Make Sense
-
JetBrains AI Assistant: Pairing AI Assistant with Code With Me for remote reviews
-
The Economics of the Suez Canal
-
What I Learned from the Worst Production Bugs
-
Windsurf: Indexing strategies for a monorepo with generated code
-
How Credit Rating Systems Emerged
-
Time Management for Technical People Without Motivational Nonsense
-
Cursor: Migrating a legacy module without losing git history or sanity
-
The Economics of Australian Colonization
-
Reliable Backup Strategies for Developers
-
Google Gemini: Crossing modalities: log, screenshot, code, spec, all in one turn
-
How Chicago Made the American Midwest
-
Why Monitoring Is More Important Than Feature Development
-
ChatGPT Codex: Catching silent test skips before they ship to main
-
The Economics of the American Civil War
-
How to Build Custom CLI Tools for Everyday Work
-
Claude Code: Composing slash commands into a bespoke team-specific DSL
-
How Free Trade Ideology Emerged
-
Debugging Mindset: The Art of Systematic Bug Hunting
-
GitHub Copilot: Measuring acceptance rate honestly instead of celebrating vanity metrics
-
The Economics of Colonial Tax Systems
-
Home Lab for Testing: Cheap and Smart
-
Local LLMs with Ollama: RAG over internal docs without handing them to a third party
-
How the Federal Reserve Was Created
-
Why Documentation Matters More Than Perfect Code
-
Agentic coding: Rollback plans for changes you did not watch land
-
The Economics of Japanese Industrialization
-
Technical Debt: How It Arises and How to Realistically Pay It Off
-
MCP servers: Versioning MCP servers like APIs, not like scripts
-
How Medieval Town Charters Created Urban Commerce
-
AI as a Junior Colleague: How to Work With It Effectively
-
AI coding workflows: Rescue patterns when an agent has gone off the rails
-
The Economics of Oil Discovery
-
Why Checklists Are an Underrated Tool in IT Projects
-
Prompt engineering for code: Few-shot examples that teach taste, not just format
-
How Standardization Enabled Modern Industry
-
The Biggest Productivity Myths Developers Believe
-
Cline and Roo Code: Logging every turn so you can learn from the agent, not just use it
-
The Economics of Ancient Phoenician Trade
-
How to Create Your Own Custom Developer Dashboard
-
JetBrains AI Assistant: Overlooked value of structural search and replace
-
The Economics of the Great Depression
-
Code Review as a Superpower – Not a Necessary Evil
-
Windsurf: When to reach for Cascade and when to fall back to pure editing
-
How Tenant Farming Structured Agricultural Development
-
How to Build Your Own Custom Developer Dashboard
-
Cursor: Keeping tests running in the background while the agent edits
-
The History of Minimum Wage Laws
-
Local AI vs Cloud AI: When Does Each Make Sense
-
Google Gemini: Keeping answers tight with explicit output contracts
-
The Economics of the Louisiana Purchase
-
Why Copy-Paste Is the Biggest Enemy of Sustainable Code
-
ChatGPT Codex: Treating Codex as a junior engineer with an infinite patience budget
-
How Coal Transformed Industrial Geography
-
How to Build a Personal Knowledge Base That Actually Works
-
Claude Code: Diffing agent output against main before you trust a single file
-
The Economics of Colonial India Under British Rule
-
Minimalism in Software: Fewer Features Equals a Better Product
-
GitHub Copilot: Leaning on Copilot Edits for multi-file, reviewable diffs instead of raw chat
-
How the Panama Canal Transformed Global Trade
-
Why April Fools Is the Best Day for Testing Critical Thinking in IT
-
Local LLMs with Ollama: Caching embeddings locally for a private retrieval layer
-
The Economics of the Amber Trade
-
The Successor to Python Pandas: Why Polars, DuckDB, and Modern Alternatives Are Reshaping Data Analysis
-
Agentic coding: Honest case for agents that only suggest
-
How Cottage Industry Preceded Industrialization
-
Text Expander: Your Tool for Taking Productivity to the Next Level
-
MCP servers: Why your wiki should probably be an MCP resource
-
Pre-Colonial West African Economies
-
Obsidian Notes as Your Second Brain: The Complete Guide to Building a Personal Knowledge System
-
AI coding workflows: Writing acceptance tests first, agents second
-
The Economics of the Laws of the Sea
-
Standing Desks: Alternating Positions at Work – Trend or Real Benefit?
-
Prompt engineering for code: Diffing prompts the way you diff code
-
Medieval Trade Fairs as Information Markets
-
Next-Level Productivity Through Strategic Note-Taking and Mind Mapping
-
Cline and Roo Code: Why open-source agents are a better teacher than closed ones
-
How Colonial Land Grants Shaped American Development
-
ANC Headphones for Open Office Survival: Is the Sony WH-1000XM5 Still King?
-
JetBrains AI Assistant: Resisting the urge to turn every green inspection into an agent task
-
How River Commerce Shaped European Geography
-
Learning Kubernetes with Rancher and Raspberry Pi: The Complete Homelab Guide
-
Windsurf: Value of a pause button in an otherwise relentless agent
-
How Agricultural Surplus Created the First States
-
Smart Rings: The Subtle Art of 24/7 Health Monitoring Without the Bulk
-
Cursor: Cheap wins: keybindings that turn Cursor into a proper editor
-
The Commercial Revolution Before the Industrial Revolution
-
Smartwatch as Your Training Partner: The Complete Guide to Wearable Fitness Technology
-
Google Gemini: Using long context to write migration scripts that respect every edge
-
How Harbor Infrastructure Created Commercial Value
-
The Best Personal Development Podcasts: Your Guide to Growth on the Go
-
ChatGPT Codex: Splitting epics into Codex-sized tasks on purpose
-
The History of Bankruptcy Law
-
The Power of Subtle Skills: The Invisible Competencies That Separate Good From Exceptional
-
Claude Code: Quiet art of pausing the agent instead of letting it churn
-
How Cotton Built the American South
-
Atomic Habits in Practice: The Implementation Guide That Turns Theory Into Lasting Change
-
GitHub Copilot: Underrated power of /explain on legacy code no one dares to touch
-
The Economics of the American Cattle Frontier
-
How to Write a Book: The Complete Guide From Blank Page to Finished Manuscript
-
Local LLMs with Ollama: When a local 7B beats a cloud 70B in latency-sensitive loops
-
How Banking Panics Led to Central Banking
-
Breakthrough Patents That Could Reshape Our World: The Innovations Hiding in Plain Sight
-
Agentic coding: How to review a PR an agent opened in the middle of the night
-
The Economics of Ancient Greek Colonization
-
Logitech MX Master 4 Reviewed: The Productivity Mouse That Justifies Its Premium Price
-
MCP servers: Composing agents over a catalogue of shared MCP tools
-
How Apprenticeship Systems Transmitted Craft Knowledge
-
Choosing Hardware for Local AI: The Complete Guide to Running Small Language Models at Home
-
AI coding workflows: Treating diffs as the primary artefact, chat as exhaust
-
The Economics of the Tobacco Trade
-
Virtualization on macOS: How to Maximize Your Mac Studio's Potential With Virtual Machines
-
Prompt engineering for code: How to write a system prompt you can still read in six months
-
The Economics of Nomadic Pastoralism
-
The Productivity Books That Actually Work: Read These and Level Up Your Entire Approach
-
Cline and Roo Code: Roo modes that codify team-specific workflows
-
How Alphabetic Writing Enabled Commerce
-
The Best Story-Driven Games on PS5: A Curated Guide for Narrative Hunters
-
JetBrains AI Assistant: Writing specs as Markdown that Junie can consume
-
The Economics of Financial Bubbles
-
Maximizing Productivity on macOS: The Complete Guide to Unlocking Your Mac's Full Potential
-
Windsurf: Pairing Cascade with a linter that refuses bad taste
-
The Columbian Exchange's Economic Consequences
-
Maximizing Productivity on Windows 11: The Complete Guide to Working Smarter Not Harder
-
Cursor: Right amount of automation before it becomes magical thinking
-
The Economics of Migration Through History
-
The Essential Homebrew Applications Your Mac Deserves: A Curated Guide for Power Users
-
Google Gemini: Generating Mermaid architecture diagrams the agent can then critique
-
The History of Marine Insurance
-
Why Smartphones Got Boring: The Innovation Plateau Nobody Wants to Admit
-
ChatGPT Codex: Auditing the diff, not the narrative – the code is the contract
-
How the Printing Press Transformed Information Markets
-
Choosing a MacBook in 2026: The Decision Framework That Cuts Through the Confusion
-
Claude Code: Keeping Claude honest with explicit acceptance criteria, not vibes
-
The Economics of the Triangular Trade
-
Augmented Reality: The Interface Revolution Hiding in Plain Sight
-
GitHub Copilot: Copilot Spaces as shared context libraries for team onboarding
-
How Manorialism Structured Medieval Economies
-
The Healthcare Innovation Paradox: Why the Most Regulated Industry Is About to Change the Fastest
-
Local LLMs with Ollama: Thermal budget of a MacBook pretending to be a server
-
The Economics of Ancient Egypt
-
The Art of Decomposition: How to Solve Almost Any Problem by Breaking It Into Smaller Pieces
-
Agentic coding: Guardrails before autonomy, always
-
How Geographic Chokepoints Control Commerce
-
The Future Tech Landscape: What's Actually Coming vs What's Just Hype
-
MCP servers: Least-privilege auth for MCP in a real enterprise
-
The Economics of Roman Infrastructure
-
How to Win Friends and Influence People: The 87-Year-Old Book That Still Knows You Better Than Your Therapist
-
AI coding workflows: Scorecard question: did this PR have to exist?
-
How Venice Became Europe's First Financial Superpower
-
The Work Laptop Decision Matrix: How to Choose a Machine That Won't Betray You
-
Prompt engineering for code: Structured outputs: JSON schemas that keep agents honest
-
The Economics of the Trans-Atlantic Slave Trade
-
The Automation Manifesto: Building Systems That Work While You Sleep
-
Cline and Roo Code: Building an internal guardrails library on top of Cline
-
The Choreography of Hours: Turning Daily Chaos Into a Performance of Flow
-
JetBrains AI Assistant: When the IDE already knows the answer and the agent just needs to ask
-
The Portfolio of Hours: Managing Time as Capital in a Volatile World
-
Windsurf: What Windsurf teaches about the ergonomics of agent IDEs
-
The Chessboard of Time: Playing Hours as Strategy Instead of Sprinting Toward Checkmate
-
Cursor: Resetting indexes when completions start feeling stale
-
The Navigation of Hours: Steering Through Deadlines, Currents, and Hidden Reefs
-
Google Gemini: Pairing Gemini with Code Assist for refactors that span a whole module
-
The Business Value of Logging Before It's Too Late
-
ChatGPT Codex: Keeping the human in the loop by requiring explicit acceptance
-
The Architecture of Time: Designing Your Day Like a Scalable System
-
Claude Code: Hooks that enforce lint, test and security gates before any write
-
The Farm of Hours: Cultivating Time Like Crops in a Field
-
GitHub Copilot: Constraining the agent with .github/copilot-instructions.md for reproducible behaviour
-
The Kitchen of Hours: Cooking Your Schedule into a Feast of Productivity
-
Local LLMs with Ollama: Running evals locally before trusting a new model
-
The Ecology of Hours: Designing Your Day Like an Ecosystem Instead of a Factory
-
Agentic coding: Planning outputs as the real product of the first turn
-
The Bridges of Time: Building Strong Connections Between Tasks, Goals, and Meaning
-
MCP servers: Testing MCP servers with a plain JSON-RPC client first
-
The Gardening of Time: Why Hours Bloom Better With Seasons, Soil, and Pruning
-
AI coding workflows: Pair-with-AI rituals that survive a team of ten
-
The Ecosystem of Hours: Time Management Through the Lens of Ecology
-
Prompt engineering for code: Difference between role prompts and persona cosplay
-
The Boiling Point of Time: Why Managing Heat Matters More Than Managing Hours
-
Cline and Roo Code: Routing cheap models for boilerplate, frontier models for design
-
The Architecture of Hours: Designing Time Like a Building Instead of a To-Do List
-
JetBrains AI Assistant: Scoping Junie tasks by module to keep review tractable
-
The Algebra of Time: Solving for X in a World of Infinite Equations
-
Windsurf: Using write-mode sparingly to protect your muscle memory
-
The Agriculture of Hours: Farming Time for Sustainable Growth
-
Cursor: Pairing tab with explicit intent comments to steer predictions
-
LG's UltraFine 4K Reviewed: The Monitor That Tests Your Subtle Skills
-
Google Gemini: Auditing IAM policies with a million-token sweep over Terraform
-
Temporal Firewalls: Building Boundaries That Protect Your Deep Work
-
ChatGPT Codex: Parallelising bug-fix attempts and picking the cleanest patch
-
Thankfulness as a Subtle Force of Culture
-
Claude Code: Checkpointing long sessions to protect yourself from context rot
-
Teach the Machines to Sell Your Product
-
GitHub Copilot: Switching models mid-conversation when reasoning quality starts to degrade
-
LG 34WN80C-B Reviewed: An Ultrawide Monitor That Rewards Subtle Skills
-
Local LLMs with Ollama: Pairing Ollama with Continue or Cline for a private IDE
-
How To Build A Simple Subscription Project That Actually Prints Money
-
Agentic coding: What to log when an agent writes for you
-
How To Build A Newsletter That Pays Its Own Bills
-
MCP servers: Treating MCP servers as a supply chain, not a side project
-
Generative Engine Optimisation and the SaaS Survival Playbook
-
AI coding workflows: Daily shutdown routine that actually ships code
-
How the Medici Bank Shaped Renaissance Europe
-
Curating the Library of Hours: Why Time Management Is an Act of Editorial Genius
-
Prompt engineering for code: Turning specs into prompts without losing the nuance
-
The History of the Grain Trade and Urban Food Security
-
Conducting the Symphony of Hours: Time Management Lessons from Music
-
Cline and Roo Code: Plan mode as a cheap dry run before committing budget
-
The Economics of the Roman Empire at Its Peak
-
Stop Guessing: 9 Prompt Engineering Frameworks That Actually Work
-
JetBrains AI Assistant: Using inspections as invisible rails for the agent
-
The Economics of Ancient Athens
-
BenQ EX3501R Reviewed: An Ultrawide That Tests Your Subtle Skills
-
Windsurf: Keeping the editor quiet until you ask for help
-
The Physics of Time Leaks: Plugging the Holes That Drain Your Day
-
Cursor: Composer runs that land a feature in a single reviewable diff
-
The Labyrinth of Hours: Navigating Time Without Losing the Thread
-
Google Gemini: Using Gemini CLI as glue between Cloud Run and your local repo
-
The Queue Theory of Time: Why Your Day Needs Scheduling Like a Data Pipeline
-
ChatGPT Codex: Using AGENTS.md to describe the environment the sandbox must respect
-
The Kitchen of Hours: Cooking Time Into Meals Instead of Eating It Raw
-
Claude Code: Writing a CLAUDE.md that captures tacit team knowledge
-
Why Subtle Support Never Stops After the First Push
-
GitHub Copilot: Running Copilot CLI as a scriptable review step inside pre-commit hooks
-
The Hidden Business of Cron Jobs That Could Save—or Sink—Your SaaS
-
Local LLMs with Ollama: Keeping a small local model honest with tight prompts
-
The Fine Art of Indexing That Decides Whether Your SaaS Survives
-
Agentic coding: Difference between an agent and a slow script
-
The Cartography of Hours: Mapping Time as Territory Instead of Counting It
-
MCP servers: Exposing read-only resources before you expose write actions
-
The Architecture of Hours: Designing Time as if Your Life Were a Cathedral
-
AI coding workflows: Small reversible steps instead of one heroic prompt
-
Samsung Odyssey G8 OLED Reviewed: The Curved Monitor That Teaches Subtle Skills
-
Prompt engineering for code: Acceptance criteria as the only prompt that matters
-
The Orchestra of Hours: Conducting Time Like a Maestro
-
Cline and Roo Code: Auditing every tool call before it touches a file
-
The Economics of the Black Death
-
The Overlooked Power Of Micro SaaS
-
JetBrains AI Assistant: Refactorings that remain safe because JetBrains understands types
-
The Geometry of Hours: Designing Angles, Shapes, and Symmetry in Your Daily Schedule
-
Windsurf: Flows that preserve intent across a long refactor
-
The Fluid Mechanics of Time - Why Your Day Should Flow Like Water Instead of Crack Like Concrete
-
Cursor: Agent mode as a disciplined driver, not a replacement for review
-
The Subtle Economics of Email Deliverability in SaaS
-
Google Gemini: Debugging a production incident from a screenshot and a log bundle
-
LG's UltraFine 5K Reviewed: The Subtle Skills Hidden Behind the Pixels
-
ChatGPT Codex: Scoping tasks tightly enough that the agent can finish in one pass
-
The Farming of Hours: How to Cultivate Time Like a Field Instead of Burning It Like Fuel
-
Claude Code: Using sub-agents for parallel research across a large codebase
-
The Fabric of Hours: Weaving Time Like Cloth Instead of Marching on a Timeline
-
GitHub Copilot: Pairing inline completion with a custom instructions file to enforce house style
-
The Economics of Hours - Treating Your Time Like Capital Instead of Loose Change
-
Local LLMs with Ollama: Picking a local model for the specific task, not for the benchmark
-
The Library of Hours: Cataloguing Time for Clarity and Control
-
Agentic coding: Budgets as the only feature that stops a bad loop
-
Lenovo ThinkVision P27h-20 Reviewed: A Professional Display That Rewards Subtle Skills
-
MCP servers: Smallest MCP server that earns its keep
-
Humour as Soft Power in Leadership and Connection
-
AI coding workflows: Review cycle that keeps agent output honest
-
How Understatement Becomes the Most Powerful Voice in the Room
-
Prompt engineering for code: Shortest prompt that still passes review
-
Encouragement as Subtle Leadership
-
Cline and Roo Code: Picking a model per task instead of per editor
-
Emotional Timing as a Subtle Superpower
-
JetBrains AI Assistant: Letting Junie drive while the IDE still owns correctness
-
Dell's UltraSharp U3223QE Reviewed: A Display That Rewards the Subtle Skills
-
Windsurf: Cascade as a deliberate planning surface, not an auto-pilot
-
Calendar Capitalism: Turn Meetings Into Margins and Buy Back Your Day
-
Cursor: Writing .cursorrules that actually stay short and enforceable
-
Building Bonds Through Subtle Skills
-
Google Gemini: Feeding an entire service plus its tests into a single prompt
-
Boundary-Setting as the Subtle Skill of Strength
-
ChatGPT Codex: Letting Codex open the PR while you stay the reviewer of record
-
ASUS ProArt PA32UCX Reviewed: A Display That Rewards Subtle Skills
-
Claude Code: Planning mode as a cheap insurance policy against cascading edits
-
Asking Questions That Redefine Conversations
-
GitHub Copilot: Using the @workspace agent to plan multi-file refactors before a single line is written
-
Why Error Handling Might Be The Secret To Your First $1K In Recurring Revenue
-
GitHub Copilot: First honest week with GitHub Copilot on a real codebase
-
Why Composure Outshines Chaos
-
Local LLMs with Ollama: Teaching a team to trust a model they own end to end
-
The Hidden Revenue Power Of Fast Queries
-
Agentic coding: What agentic coding taught us about how we really work
-
The Tyranny of the Open Tab: How Closing Your Browser Windows Can Save Your Sanity
-
MCP servers: First comparison between MCP and home-grown tool plumbing
-
The Unsung Revenue Driver Of Data Backups
-
AI coding workflows: What we retired because an agent finally did it well
-
The Hidden Art Of Database Design For $1K MRR Apps
-
Prompt engineering for code: Prompt engineering as writing, not programming
-
The Cache Conspiracy Behind Fast SaaS Apps
-
Cline and Roo Code: Teaching juniors by pairing on Cline sessions
-
Shifting Without Losing Shape
-
JetBrains AI Assistant: Writing specs tight enough for Junie to execute cleanly
-
Samsung Smart Monitor M8 Reviewed: A Hybrid Display That Rewards Subtle Skills
-
Windsurf: Retrospective after our first Windsurf-heavy sprint
-
The Productivity Power of the Two-Hour Rule
-
Cursor: Teaching Cursor the house style without a wall of prose
-
The Session Management Trap That Slowly Eats Your SaaS Revenue
-
Google Gemini: Gemini for Workspace as the quiet engineering multiplier
-
Philips 499P9H Reviewed: A Super-Ultrawide That Tests Your Subtle Skills
-
ChatGPT Codex: Pairing Codex with tight acceptance criteria for the first time
-
How Quiet Questions Reshape Power and Progress
-
Claude Code: First pass at measuring Claude Code against ordinary coding
-
Empathy's Quiet Twin in Decision-Making
-
GitHub Copilot: Small refactor Copilot did not quite nail, and why it mattered
-
The 30-Minute Reset: Why Micro-Breaks Outperform Endless Grinding
-
Local LLMs with Ollama: First honest benchmark between local and cloud models
-
Humility as Subtle Authority
-
Agentic coding: Retrospective after our first week of full agentic coding
-
LG 40WP95C-W Reviewed: An Ultrawide Monitor That Rewards Subtle Skills
-
MCP servers: Testing MCP servers with the same rigor as customer-facing APIs
-
Why Waiting Becomes a Superpower
-
AI coding workflows: When taking the keyboard back was the real productivity move
-
Speed Isn't Optional: Why Performance Is the Silent Killer of SaaS Dreams
-
Prompt engineering for code: Honest taxonomy of prompts, as discovered in practice
-
The Subtle Skill of Letting Others Shine
-
Cline and Roo Code: Plan mode budget that caught a runaway loop early
-
The Two-Minute Gravity Rule: How Shrinking Tasks Destroys Procrastination Before It Starts
-
JetBrains AI Assistant: First safe refactor that felt genuinely new
-
The Two-Minute Triage: Why Micro-Decisions About Small Tasks Save Hours of Cognitive Drain
-
Windsurf: Onboarding a new hire with Windsurf already installed
-
Eizo ColorEdge CG319X Reviewed: A Monitor That Teaches the Subtle Skills of Trust
-
Cursor: First code review after a heavy Cursor day
-
Influence Through What Is Not Said
-
Google Gemini: First attempt at Vertex evaluations for code tasks
-
C++ Memory Optimization Mastery
-
The Art of Building MRR and ARR That Actually Sticks
-
ChatGPT Codex: Measuring what Codex actually merged, not what it attempted
-
How To Build a SaaS Micro-Tool That Prints MRR
-
Metal 4 Ultra: Dissecting a Sub-Millisecond Mandelbrot Benchmark on Apple Silicon
-
Claude Code: Learning to pause the agent on purpose
-
Dell's UltraSharp U2723QE Reviewed: A Display That Rewards Those Who Notice
-
GitHub Copilot: Onboarding a junior engineer with Copilot already in the seat
-
Building The Quiet SaaS That Pays Your Rent
-
Local LLMs with Ollama: Cost-per-token in wall time, discovered by accident
-
How Smart In-App Notifications Can Fuel Your First $1K In Recurring Revenue
-
Agentic coding: Deliberate agent downtime as an early productivity discovery
-
Building a Business That Pays You While You Sleep
-
MCP servers: Teaching the team MCP through a single example server
-
ASUS TUF VG34VQL1B Reviewed: An Ultrawide Monitor That Rewards Subtle Skills
-
AI coding workflows: Daily checklist that outlasted two tool migrations
-
Subtle Persuasion as the Quiet Art of Influence
-
Prompt engineering for code: Shorter prompts after a month of deliberately deleting words
-
The Garden of Hours: Cultivating Time Instead of Racing Through It
-
Cline and Roo Code: What closed-source agents still did better, and where they did not
-
The Chessboard of Hours: Playing the Strategic Game of Time Without Losing Your Queen
-
JetBrains AI Assistant: Teaching Junie through existing Markdown docs
-
The Hidden Architecture of Time: Why Schedules Lie and Rhythms Don't
-
Windsurf: Write mode restraint in the first month of use
-
The Garden of Hours: Cultivating Time with Seasons, Soil, and Sustained Growth
-
Cursor: Learning to write intent in comments, not in chat
-
The Cuisine of Hours: Cooking Productivity Like a Master Chef
-
Google Gemini: Honest cost of long-context prompts in a small team
-
Latency Budgets for Humans: Engineer Your Day Like a Backend
-
ChatGPT Codex: Small playbook that made Codex predictable
-
The Emotional Calendar: How to Harness the Moods of Time Instead of Fighting Them
-
Claude Code: Moment Claude Code beat a human reviewer on taste
-
The Negotiation of Hours: How to Bargain with Time Without Losing Your Soul
-
GitHub Copilot: First model switch inside Copilot Chat, and what it taught us
-
The Cartography of Hours: Mapping Your Day Like an Explorer Instead of Surviving Like a Castaway
-
Local LLMs with Ollama: Air-gapped development as a serious practice, not a demo
-
Quiet Confidence as the Strongest Authority
-
Agentic coding: First PR an agent opened that we merged without edits
-
From Side Hustle to Stability: Crafting MRR and ARR Through Focused Projects
-
MCP servers: What the protocol gave us and what our product still had to
-
The Power of the Daily Shutdown Ritual: Why Ending Your Workday Right Makes Tomorrow Easier
-
AI coding workflows: First retrospective on what AI did and did not change
-
Gigabyte M32U Reviewed: A 4K Monitor That Teaches Subtle Skills
-
Prompt engineering for code: First prompt rot we detected, and the lessons from it
-
Artificial Intelligence vs. Privacy – The Debate on Ethics and Regulation of Generative Models
-
Cline and Roo Code: Quiet pleasure of reading every tool call
-
AI in Small Businesses – Tips for Implementation Without Big Budgets
-
JetBrains AI Assistant: Early taste tests: JetBrains AI versus the newcomers
-
AI in Finance – How Banks and Fintechs Use Generative AI for Fraud Detection
-
Windsurf: Windsurf setting that changed how we reviewed code
-
Traveling with EVs – How New Fast-Charging Stations Near Airports Are Changing Trip Planning in the UK
-
Cursor: Pricing tier choices with incomplete information
-
AI Agent Security – Risks and Best Practices for Implementing Autonomous Agents
-
Google Gemini: First real comparison we ran between Gemini and the rest
-
How Teachers Use ChatGPT – A Review of 'AI for Teachers' Trends and Their Impact on Education
-
ChatGPT Codex: Choosing Codex for upgrades, humans for design
-
AI Adoption in APAC: Why 70 % of Workers Use Generative AI and What It Means for Enterprises
-
Claude Code: Slash commands as the first real team workflow
-
Charging from Street Lamps – How the UK’s Lamp Post Chargers Are Powering a New Kind of Mobility
-
GitHub Copilot: When to lean on Copilot CLI instead of the IDE extension
-
Electromobility in Europe – Why BEVs Make Up 23% of Registrations and the Fastest-Growing Markets You Should Watch
-
Local LLMs with Ollama: Pairing Ollama with Continue for a first private IDE setup
-
Renewables in Asia – The APRESA Program and Southeast Asia’s Race for 50 % Clean Power by 2035
-
Agentic coding: Cost-per-merged-change metric we invented out of necessity
-
The Future of Robotics – What the Global Research Conference on Robotics and AI 2025 Revealed
-
MCP servers: First MCP server a security review actually approved
-
Mastering QA Automation with Playwright: A Deep Review and Strategy Guide
-
AI coding workflows: Diff as primary artefact, chat as exhaust, a first lesson
-
Apple 2030 – The Impact of Apple’s Solar and Wind Projects on European Energy
-
Prompt engineering for code: How we measured prompt quality before we had metrics
-
ChatGPT and Beyond – Why Conversational AI Dominates Search Trends and How to Use It Effectively
-
Cline and Roo Code: First month of honest logs from an open-source agent
-
AI Note-Taking – A Review of the New Wave of Tools for Automatic Information Capture and Summarization
-
Work Headphones Buying Guide: Do You Really Need Them?
-
JetBrains AI Assistant: First CI run with Junie as a contributor
-
Generative AI and Creativity – How 81 % of European Teens Use Artificial Intelligence to Boost Creativity
-
The Keyboard That Whispers: A Guide to Quiet Keyboards Programmers (and Their Cats) Actually Need
-
Windsurf: First MCP server we plugged into Windsurf
-
Build Less, Charge More: The Lost Art of Feature Pruning
-
Cursor: Undoing Cursor changes on purpose, a first discipline
-
ASUS ProArt PA32DC Reviewed: The OLED Monitor That Demands Subtle Skills
-
Google Gemini: When to ask Gemini and when to open the logs yourself
-
The Power of Monotasking in an Age of Constant Distraction
-
ChatGPT Codex: First time we stopped Codex mid-task and why
-
The Decision Fatigue Tax - Why Pre-Making Choices Saves Your Future Self from Collapse
-
Claude Code: When headless Claude Code became part of our CI
-
The Case for Monotasking in a World Obsessed with Multitasking
-
GitHub Copilot: Measuring Copilot adoption without lying to ourselves
-
The Calendar as a Fortress: Why Blocking Time Is the Ultimate Productivity Multiplier
-
Local LLMs with Ollama: Offline code reviewer that survived a flaky Wi-Fi week
-
The 90-Minute Sprint: How Working in Rhythmic Blocks Unlocks Your Best Output
-
Agentic coding: Long-running agent that finally paused itself
-
The Calendar as a Compass: Why Planning Your Week Beats Chasing Your Day
-
MCP servers: Observability gaps that bit us exactly once
-
The Art of Context Parking: How to Pause Without Losing Your Mind (or Your Momentum)
-
AI coding workflows: Acceptance tests first, agents second, as a beginner mantra
-
Intelligent Test Automation: From Fragile Scripts to Strategic Quality
-
Prompt engineering for code: Style guides for both humans and models, a beginner attempt
-
Inbox Freezing: How to Stop Email from Hijacking Your Productivity
-
Cline and Roo Code: Running Cline against a local LLM for the first time
-
Apple’s Studio Display Reviewed Through the Lens of Patience and Precision
-
Context Switching Is Killing Your Focus
-
JetBrains AI Assistant: When Junie finished the task we had been avoiding
-
AOC CU34G2X Reviewed: An Ultrawide That Teaches Subtle Skills
-
Windsurf: Beginner comparison: Windsurf, Cursor, VS Code Agent
-
Why macOS Is the Productivity Platform You Never Fully Learned to Use
-
Cursor: MCP inside Cursor as an early glimpse of the toolbelt
-
Google Gemini: Writing Mermaid diagrams Gemini could then critique
-
Turning macOS Into Your Productivity Playground
-
ChatGPT Codex: Budgeting Codex tasks when usage was still a black box
-
The Real Reason macOS Can Be Your Most Productive Workspace
-
Test Matrix - Pairwise Enhanced
-
Claude Code: Turning a chaotic commit history into a tidy narrative
-
The Quiet Productivity Secrets Hidden Inside macOS
-
GitHub Copilot: Premium request debate, before anyone had real data
-
The macOS Playbook for Peak Productivity
-
Local LLMs with Ollama: Caching embeddings locally for a beginner RAG
-
The Mac as a Productivity Machine You Haven’t Fully Unlocked
-
Agentic coding: How a junior engineer earned their first autonomous task
-
The Hidden Depths of Productivity on macOS
-
MCP servers: Versioning MCP servers like APIs, a first-year habit
-
macOS as the Quiet Engine of Productivity
-
AI coding workflows: Choosing boredom over brilliance in the first year
-
macOS and the Subtle Science of Getting Things Done
-
Prompt engineering for code: When a prompt quietly became a feature spec
-
macOS and the Subtle Science of Getting More Done
-
Cline and Roo Code: Memory banks as a beginner experiment in agent continuity
-
macOS and the Subtle Craft of Getting Things Done
-
JetBrains AI Assistant: Pairing Code With Me with AI Assistant for remote review
-
macOS and the Quiet Revolution of Everyday Productivity
-
Windsurf: Pausing Cascade versus pausing yourself
-
macOS and the Invisible Hand of Productivity
-
Cursor: When agent mode decided to write tests we never wrote
-
macOS and the Hidden Craft of Working Smarter
-
Google Gemini: Verbosity we trimmed in month two
-
macOS and the Discipline of Effortless Productivity
-
ChatGPT Codex: Diff-first review habit we learned from Codex
-
macOS and the Craft of Working Smarter
-
Claude Code: First time Claude Code said no to a bad instruction
-
macOS and the Art of Working Without Friction
-
GitHub Copilot: Discovering Copilot Edits and rethinking the pull request
-
PlayStation 5 Pro Review
-
Wrist Taken Hostage by the Mouse: How to Choose a Quality Work Peripheral
-
Local LLMs with Ollama: Moment a local 7B beat the cloud on a real task
-
HP Z32k G3 Reviewed: A 4K Monitor That Teaches Patience and Precision
-
Agentic coding: Case for suggest-only agents in safety-critical code
-
The Silent Cost of Notifications
-
MCP servers: First sandboxing policy we wished we had started with
-
The Browser Tab Trap: How Context Switching Kills Focus and How to Escape It
-
AI coding workflows: Shutdown routine that made AI-heavy days survivable
-
The Power of Time Boxing: Why Containing Your Tasks Unlocks Explosive Focus
-
Prompt engineering for code: Diffing prompts without a system, and the system that followed
-
The Overlooked Power Of Authentication In $1K MRR Apps
-
Cline and Roo Code: Picking models per task with almost no data, and learning fast
-
Reading the Room as a Subtle Skill
-
JetBrains AI Assistant: AI Assistant versus plain inspections on the same codebase
-
The Portfolio of Hours: How to Invest Time Like Capital and Build a Life of Compounded Meaning
-
Windsurf: First atomic commit authored entirely by Cascade
-
The Architecture of Hours: Designing Your Time Like a Master Builder
-
Cursor: First week we stopped fighting Cursor and let it drive
-
The Symphony of Hours: Conducting Your Time Instead of Being Drowned in Noise
-
The Theatre of Hours: Directing Your Day as a Stage Performance
-
Mind Map–Driven Testing: Charting the Untamed Terrain of Software Quality
-
Google Gemini: Mixing AI Studio and Code Assist without losing context
-
The Elasticity of Hours: How to Stretch Time Without Breaking It
-
ChatGPT Codex: When Codex rewrote code we did not ask it to
-
The Supply Chain of Hours: Managing Time as Logistics Instead of a Countdown
-
Claude Code: Running Claude Code on a legacy repo nobody wanted to touch
-
Timeboxing for Humans: Build Short, Sharp Sprints That Actually Ship
-
GitHub Copilot: First .github/copilot-instructions.md that actually shipped
-
Chrono-Navigation: Steering Through Time Like a Sailor, Not a Factory Worker
-
Local LLMs with Ollama: Local evaluations that predicted our first cloud regression
-
The Quiet Conductor of Chaos
-
The macOS Advantage: How Apple’s Desktop Turns Everyday Work Into Flow
-
Agentic coding: Short loops as the winning rhythm, discovered through long ones
-
How Audiobooks Became the Jet Fuel of Personal Growth and Time-Saving Mastery
-
MCP servers: Why we promoted an internal wiki to an MCP resource
-
The Quiet Power Of Small Software
-
AI coding workflows: Time-boxing agent loops before they ate the afternoon
-
Adaptability Without Chaos
-
Prompt engineering for code: Prompt library we started in a shared Markdown file
-
How Whispered Skills Move Mountains
-
Cline and Roo Code: First audit trail that made a security lead smile
-
Narrative Time: How Storytelling Can Reshape the Way You Manage Your Days
-
JetBrains AI Assistant: Beginner workflow with Junie, ADRs, and module scope
-
The Monotask Revolution: Winning Back Focus in an Age of Fractured Attention
-
Windsurf: Writing our first Cascade-friendly task spec
-
The Theatre of Time: Directing Your Day as a Stage Play
-
Cursor: Indexing hiccups on a monorepo larger than the demo
-
The Architecture of Hours: Designing Time Like a Building Instead of Letting It Crumble
-
Google Gemini: IAM audits with Gemini: the day it noticed what we missed
-
Observation as the Subtle Skill That Outsmarts Speed
-
ChatGPT Codex: Scoping tasks to finish in a single pass, a beginner lesson
-
The Dark Art of Crafting a Subscription Onboarding Flow That Actually Converts
-
Claude Code: Hooks as a cheap gateway drug to workflow automation
-
GitHub Copilot: Why @workspace changed how we wrote issues
-
The Subscription Blueprint for Building Revenue That Lasts
-
Local LLMs with Ollama: Quantisation choices with incomplete information
-
How a Micro-SaaS Tool Can Become Your Gateway to MRR and ARR
-
Agentic coding: First rollback plan we actually used
-
The Myth of Multitasking
-
MCP servers: Composing agents over a tiny catalogue of shared tools
-
macOS and the Invisible Architecture of Productivity
-
AI coding workflows: Rescue patterns discovered after the first agentic disaster
-
BenQ PD3220U Reviewed: A Display That Rewards Subtle Skills
-
Prompt engineering for code: Few-shot examples drawn from our own first PRs
-
The Two-Minute Momentum Rule: Why Small Wins Crush Procrastination
-
Cline and Roo Code: Cline tool manifests we shared with colleagues over lunch
-
The Ritual of the Shutdown: How Ending Your Day Intentionally Creates Tomorrow’s Success
-
JetBrains AI Assistant: First inspection the agent actually listened to
-
The Case for Single-Tasking: Why Doing One Thing at a Time Outperforms All Productivity Hacks
-
Windsurf: Windsurf defaults we kept and the ones we overrode
-
Resilient Test Management: Building Trust In Software Delivery
-
Cursor: Composer for the first multi-file refactor we trusted
-
Google Gemini: First migration we ran through a single long prompt
-
How to Manage Queues So Your SaaS Doesn't Lose Money
-
ChatGPT Codex: First Codex PR that shipped without a human touch
-
The Subscription Mindset That Turns Fluctuation Into Fortune
-
Claude Code: Cost spike that taught us to checkpoint
-
The Database Index That Pays Your Rent
-
GitHub Copilot: Copilot Chat in the terminal versus the editor, a first look
-
How to Build Recurring Revenue Without Chasing Your Tail
-
Local LLMs with Ollama: Thermal limits on the first serious local code session
-
The Chessboard of Hours: Mastering Strategic Time Management
-
Agentic coding: Guardrails before autonomy, learned the expensive way
-
The Kitchen of Hours: Cooking Time into Meaningful Productivity
-
MCP servers: First auth model we picked, and later regretted
-
The Theatre of Hours: Directing Time Like a Master of the Stage
-
AI coding workflows: Scorecard that replaced vanity metrics in month three
-
The Bandwidth Economy: Managing Time by Managing Cognitive Throughput
-
Prompt engineering for code: Role prompts the first time we stopped cosplaying with them
-
The Measured Brilliance of JBL Tour One M2
-
Cline and Roo Code: Roo modes that encoded our first team conventions
-
The Symphony of Hours: Conducting Your Day Like an Orchestra Instead of a Stopwatch
-
JetBrains AI Assistant: Refactoring across types with AI Assistant and not losing sleep
-
The Marketplace of Minutes: Trading Time as if It Were Currency
-
Windsurf: What the first long Cascade session actually cost
-
Directing the Play of Hours: How Theatre Teaches Us to Master Time
-
Cursor: Tab predict surprises that made us rewrite comments
-
The Garden of Hours: Cultivating Time Like Soil Instead of Grinding Through It Like Machinery
-
Google Gemini: Gemini CLI as a weekend scripting partner
-
Hearing What Others Don’t Say
-
ChatGPT Codex: Parallel tasks and the temptation to scope too wide
-
The Subscription Mindset: Building MRR and ARR Through Small but Mighty Products
-
Claude Code: Sub-agents the first time they saved an afternoon
-
GitHub Copilot: Early art of rejecting suggestions without hurting velocity
-
The One-Page Plan: Why Writing It Down Every Morning Outperforms Fancy Productivity Systems
-
Local LLMs with Ollama: Private RAG pipelines, assembled out of a weekend of curiosity
-
ViewSonic VP3881 Reviewed: An Ultrawide That Rewards Subtle Skills
-
Agentic coding: Planning outputs as the real product of the initial turn
-
The Rule of Three: How Limiting Daily Goals Creates Exponential Productivity
-
MCP servers: Early protocol tour, done with a plain JSON-RPC client
-
The City of Hours: Urban Planning as the Secret Blueprint for Time Management
-
AI coding workflows: Pair-with-AI rituals for a team that had never tried them
-
The Architecture of Hours: Designing Time Like a City Instead of Living in Random Construction Sites
-
Prompt engineering for code: Structured outputs, discovered the hard way
-
The Silent Revenue Killer Of Authentication
-
Cline and Roo Code: Plan mode as a cheap insurance policy from day one
-
How To Build A Membership Community That Actually Pays For Itself
-
JetBrains AI Assistant: Structural search as the hidden rail for early prompts
-
Single-Threading Your Brain: Why Doing One Thing at a Time Is the Last Competitive Advantage
-
Windsurf: Moment Windsurf made a skeptical reviewer pause
-
Acer Predator X38 Reviewed: An Ultrawide Monitor That Tests Your Subtle Skills
-
Cursor: Agent mode as a faster, more honest pair programmer
-
The Silent Scheduler: How a Smart Calendar Assistant Can Earn $1K MRR
-
Google Gemini: Multimodal debugging with a single screenshot
-
The Checkout Page Is Your Silent Salesperson
-
ChatGPT Codex: Sandbox surprises in the first month of Codex
-
The Art of Saying No Without Burning Bridges
-
Claude Code: Planning mode as the training wheels we kept
-
Samsung Odyssey G9 Reviewed: The Monster Monitor That Tests Your Subtle Skills
-
GitHub Copilot: When inline completion earned its place in the daily loop
-
MSI Summit MS321UP Reviewed: A Monitor That Rewards Subtle Skills
-
Local LLMs with Ollama: Picking a local model for code without benchmarks to lean on
-
The Art of Strategic Silence: Why Muting Notifications is the Ultimate Productivity Hack
-
Agentic coding: Budgets as the first feature any agent had to have
-
The 90-Minute Sprint: How Ultradian Rhythms Redefine Productivity
-
MCP servers: Exposing read-only resources before we dared expose actions
-
The Discipline of the Done List: Why Tracking Completed Work Matters More Than Adding Tasks
-
AI coding workflows: Small reversible steps as a rhythm we borrowed from elsewhere
-
The Calendar Gap Method: How Strategic White Space Turns Busyness Into Real Productivity
-
Prompt engineering for code: Learning that acceptance criteria beat cleverness
-
The Architecture of Hours: Designing Time That Withstands Pressure and Creates Beauty
-
The Hidden Power of Automation in Building a $1K MRR Application
-
Cline and Roo Code: Bring-your-own-key in the early days of model pricing
-
The Marketplace of Minutes: Trading Time as Currency Instead of Counting It
-
JetBrains AI Assistant: Junie arrives: the first autonomous task we trusted
-
The Silent Power of Instrumentation in SaaS
-
Windsurf: Flows as a new way to carry intent across files
-
The Overlooked Revenue Catalyst Of Proper Error Handling
-
Cursor: Writing a .cursorrules file that did not embarrass us
-
The Labyrinth of Hours: Escaping Dead Ends in Daily Time Management
-
Google Gemini: Gemini Code Assist versus the API, a first year comparison
-
The Subtle Art of Keeping Your Queues From Bankrupting You
-
ChatGPT Codex: Writing AGENTS.md for a team that had never used agents
-
The Kitchen of Hours: Cooking With Time Instead of Burning It
-
Claude Code: Writing your first CLAUDE.md and learning what to leave out
-
The Cartography of Hours: Mapping Your Days to Navigate Toward Meaning
-
GitHub Copilot: Teaching Copilot your repository one readme at a time
-
The Hidden Power of Schema Migrations in Keeping SaaS Revenue Alive
-
Local LLMs with Ollama: First week running Ollama on a work laptop
-
The Chessboard of Hours: Playing Time Like a Grandmaster Instead of a Pawn
-
Agentic coding: First overnight agent run we dared to approve
-
The Symphony of Hours: Conducting Time as a Masterpiece Rather Than a Mess
-
MCP servers: First MCP server that earned its keep
-
The Garden of Hours: Cultivating Time Like Soil, Seeds, and Seasons
-
AI coding workflows: First weekly review that made AI-assisted work sustainable
-
The Architecture of Hours: Designing Time That Stands the Test of Life
-
Prompt engineering for code: First prompts we wrote that still pass review a year later
-
Patience as the Subtle Strategy of Power
-
Cline and Roo Code: First open-source agent we actually trusted
-
The Ecosystem of Hours: Cultivating Balance in a World of Endless Demands
-
JetBrains AI Assistant: AI Assistant day one in a JetBrains shop
-
The Architecture of Hours: How Designing Your Day Like a Building Creates Stability and Flow
-
Windsurf: First look at Cascade after a year of Cursor
-
Riding the Ocean of Hours: How to Surf Time Without Wiping Out
-
Cursor: First hour inside Cursor after years of VS Code
-
The Psychology Of Speed In Subscription Apps
-
Google Gemini: First million-token prompt we actually sent
-
The Unlikely Path To $1K MRR With A Simple SaaS App
-
ChatGPT Codex: First Codex task that opened a real pull request
-
Kill the Dead Weight Why Simplifying Your API May Be the Shortcut to $1K MRR.
-
Claude Code: First week of Claude Code at the terminal
-
Anticipation as the Subtle Skill of Foresight
-
GitHub Copilot: First honest week with GitHub Copilot on a real codebase
-
Local LLMs with Ollama: Teaching a team to trust a model they own end to end
-
Agentic coding: What agentic coding taught us about how we really work
-
The AirPods Max 2024 and the Subtle Art of Listening
-
MCP servers: First comparison between MCP and home-grown tool plumbing
-
Bowers & Wilkins PX8: A Symphony Wrapped in Leather and Carbon Fibre
-
AI coding workflows: What we retired because an agent finally did it well
-
How macOS Turns Everyday Tasks Into Invisible Productivity
-
Prompt engineering for code: Prompt engineering as writing, not programming
-
How macOS Turns Everyday Work Into Effortless Flow
-
Cline and Roo Code: Teaching juniors by pairing on Cline sessions
-
How To Master Productivity On macOS Without Drowning In Apps
-
JetBrains AI Assistant: Writing specs tight enough for Junie to execute cleanly
-
How To Master Productivity On macOS Without Losing Your Sanity
-
Windsurf: Retrospective after our first Windsurf-heavy sprint
-
How To Turn macOS Into A Productivity Machine That Works With You
-
Cursor: Teaching Cursor the house style without a wall of prose
-
How To Unlock Hidden Productivity On macOS
-
Google Gemini: Gemini for Workspace as the quiet engineering multiplier
-
macOS and the Art of Productive Flow
-
ChatGPT Codex: Pairing Codex with tight acceptance criteria for the first time
-
Eizo FlexScan EV3895 Reviewed A Professional Ultrawide That Rewards Subtle Skills
-
Claude Code: First pass at measuring Claude Code against ordinary coding
-
Building A Micro SaaS That Actually Pays Rent
-
GitHub Copilot: Small refactor Copilot did not quite nail, and why it mattered
-
From Chaos To Clarity: The Test Manager’s Playbook
-
Local LLMs with Ollama: First honest benchmark between local and cloud models
-
From Scripts To Strategy: The Hidden Power Of Intelligent Test Automation
-
Agentic coding: Retrospective after our first week of full agentic coding
-
How macOS Quietly Becomes the Most Powerful Productivity Tool You Own
-
MCP servers: Testing MCP servers with the same rigor as customer-facing APIs
-
I Became a Test Manager in One Product Cycle — Here’s the Roadmap I Wish I’d Had
-
AI coding workflows: When taking the keyboard back was the real productivity move
-
Test Manager From A To Z
-
Prompt engineering for code: Honest taxonomy of prompts, as discovered in practice
-
The $1k MRR Blueprint No One Talks About
-
Cline and Roo Code: Plan mode budget that caught a runaway loop early
-
The Hidden Architecture Of Great Test Automation
-
JetBrains AI Assistant: First safe refactor that felt genuinely new
-
The Hidden Architecture Of Test Management
-
Windsurf: Onboarding a new hire with Windsurf already installed
-
The Hidden Leverage of Orchestrated Agents
-
Cursor: First code review after a heavy Cursor day
-
The Invisible Architecture Of Quality
-
Google Gemini: First attempt at Vertex evaluations for code tasks
-
The Quiet Return of the Walkman
-
ChatGPT Codex: Measuring what Codex actually merged, not what it attempted
-
The Subtle Art Of Building Test Automation That Actually Works
-
Claude Code: Learning to pause the agent on purpose
-
The Unsung Alchemists of Tech: An International Testers Day Review
-
GitHub Copilot: Onboarding a junior engineer with Copilot already in the seat
-
Turning A Tiny App Into A $1K MRR Machine
-
Local LLMs with Ollama: Cost-per-token in wall time, discovered by accident
-
When I Put Down The Mouse: Lessons In Keyboard Accessibility
-
Agentic coding: Deliberate agent downtime as an early productivity discovery
-
When Tests Write Themselves: The Secret To Smarter Case Optimization In Java
-
MCP servers: Teaching the team MCP through a single example server
-
WWDC 2025: In anticipation of a revolution
-
AI coding workflows: Daily checklist that outlasted two tool migrations
-
Writing Test Automation Code That Doesn’t Hate You Back
-
Prompt engineering for code: Shorter prompts after a month of deliberately deleting words
-
Cline and Roo Code: What closed-source agents still did better, and where they did not
-
JetBrains AI Assistant: Teaching Junie through existing Markdown docs
-
Windsurf: Write mode restraint in the first month of use
-
Cursor: Learning to write intent in comments, not in chat
-
Google Gemini: Honest cost of long-context prompts in a small team
-
ChatGPT Codex: Small playbook that made Codex predictable
-
Claude Code: Moment Claude Code beat a human reviewer on taste
-
GitHub Copilot: First model switch inside Copilot Chat, and what it taught us
-
Local LLMs with Ollama: Air-gapped development as a serious practice, not a demo
-
Agentic coding: First PR an agent opened that we merged without edits
-
MCP servers: What the protocol gave us and what our product still had to
-
AI coding workflows: First retrospective on what AI did and did not change
-
Prompt engineering for code: First prompt rot we detected, and the lessons from it
-
Cline and Roo Code: Quiet pleasure of reading every tool call
-
JetBrains AI Assistant: Early taste tests: JetBrains AI versus the newcomers
-
Windsurf: Windsurf setting that changed how we reviewed code
-
Cursor: Pricing tier choices with incomplete information
-
Google Gemini: First real comparison we ran between Gemini and the rest
-
ChatGPT Codex: Choosing Codex for upgrades, humans for design
-
Claude Code: Slash commands as the first real team workflow
-
GitHub Copilot: When to lean on Copilot CLI instead of the IDE extension
-
Local LLMs with Ollama: Pairing Ollama with Continue for a first private IDE setup
-
Agentic coding: Cost-per-merged-change metric we invented out of necessity
-
MCP servers: First MCP server a security review actually approved
-
AI coding workflows: Diff as primary artefact, chat as exhaust, a first lesson
-
Prompt engineering for code: How we measured prompt quality before we had metrics
-
Cline and Roo Code: First month of honest logs from an open-source agent
-
JetBrains AI Assistant: First CI run with Junie as a contributor
-
Windsurf: First MCP server we plugged into Windsurf
-
Cursor: Undoing Cursor changes on purpose, a first discipline
-
Google Gemini: When to ask Gemini and when to open the logs yourself
-
ChatGPT Codex: First time we stopped Codex mid-task and why
-
Claude Code: When headless Claude Code became part of our CI
-
GitHub Copilot: Measuring Copilot adoption without lying to ourselves
-
Local LLMs with Ollama: Offline code reviewer that survived a flaky Wi-Fi week
-
Agentic coding: Long-running agent that finally paused itself
-
MCP servers: Observability gaps that bit us exactly once
-
AI coding workflows: Acceptance tests first, agents second, as a beginner mantra
-
Prompt engineering for code: Style guides for both humans and models, a beginner attempt
-
Cline and Roo Code: Running Cline against a local LLM for the first time
-
JetBrains AI Assistant: When Junie finished the task we had been avoiding
-
Windsurf: Beginner comparison: Windsurf, Cursor, VS Code Agent
-
Cursor: MCP inside Cursor as an early glimpse of the toolbelt
-
Google Gemini: Writing Mermaid diagrams Gemini could then critique
-
ChatGPT Codex: Budgeting Codex tasks when usage was still a black box
-
Claude Code: Turning a chaotic commit history into a tidy narrative
-
GitHub Copilot: Premium request debate, before anyone had real data
-
Local LLMs with Ollama: Caching embeddings locally for a beginner RAG
-
Agentic coding: How a junior engineer earned their first autonomous task
-
MCP servers: Versioning MCP servers like APIs, a first-year habit
-
AI coding workflows: Choosing boredom over brilliance in the first year
-
Prompt engineering for code: When a prompt quietly became a feature spec
-
Cline and Roo Code: Memory banks as a beginner experiment in agent continuity
-
JetBrains AI Assistant: Pairing Code With Me with AI Assistant for remote review
-
Windsurf: Pausing Cascade versus pausing yourself
-
Cursor: When agent mode decided to write tests we never wrote
-
Google Gemini: Verbosity we trimmed in month two
-
ChatGPT Codex: Diff-first review habit we learned from Codex
-
Claude Code: First time Claude Code said no to a bad instruction
-
GitHub Copilot: Discovering Copilot Edits and rethinking the pull request
-
Local LLMs with Ollama: Moment a local 7B beat the cloud on a real task
-
Agentic coding: Case for suggest-only agents in safety-critical code
-
MCP servers: First sandboxing policy we wished we had started with
-
AI coding workflows: Shutdown routine that made AI-heavy days survivable
-
Prompt engineering for code: Diffing prompts without a system, and the system that followed
-
Cline and Roo Code: Picking models per task with almost no data, and learning fast
-
JetBrains AI Assistant: AI Assistant versus plain inspections on the same codebase
-
Windsurf: First atomic commit authored entirely by Cascade
-
Cursor: First week we stopped fighting Cursor and let it drive
-
Google Gemini: Mixing AI Studio and Code Assist without losing context
-
ChatGPT Codex: When Codex rewrote code we did not ask it to
-
Claude Code: Running Claude Code on a legacy repo nobody wanted to touch
-
GitHub Copilot: First .github/copilot-instructions.md that actually shipped
-
Local LLMs with Ollama: Local evaluations that predicted our first cloud regression
-
Agentic coding: Short loops as the winning rhythm, discovered through long ones
-
MCP servers: Why we promoted an internal wiki to an MCP resource
-
AI coding workflows: Time-boxing agent loops before they ate the afternoon
-
Prompt engineering for code: Prompt library we started in a shared Markdown file
-
Cline and Roo Code: First audit trail that made a security lead smile
-
JetBrains AI Assistant: Beginner workflow with Junie, ADRs, and module scope
-
Windsurf: Writing our first Cascade-friendly task spec
-
Cursor: Indexing hiccups on a monorepo larger than the demo
-
Google Gemini: IAM audits with Gemini: the day it noticed what we missed
-
ChatGPT Codex: Scoping tasks to finish in a single pass, a beginner lesson
-
Claude Code: Hooks as a cheap gateway drug to workflow automation
-
GitHub Copilot: Why @workspace changed how we wrote issues
-
Local LLMs with Ollama: Quantisation choices with incomplete information
-
Agentic coding: First rollback plan we actually used
-
MCP servers: Composing agents over a tiny catalogue of shared tools
-
AI coding workflows: Rescue patterns discovered after the first agentic disaster
-
Prompt engineering for code: Few-shot examples drawn from our own first PRs
-
Cline and Roo Code: Cline tool manifests we shared with colleagues over lunch
-
JetBrains AI Assistant: First inspection the agent actually listened to
-
Windsurf: Windsurf defaults we kept and the ones we overrode
-
Cursor: Composer for the first multi-file refactor we trusted
-
Google Gemini: First migration we ran through a single long prompt
-
ChatGPT Codex: First Codex PR that shipped without a human touch
-
Claude Code: Cost spike that taught us to checkpoint
-
GitHub Copilot: Copilot Chat in the terminal versus the editor, a first look
-
Local LLMs with Ollama: Thermal limits on the first serious local code session
-
Agentic coding: Guardrails before autonomy, learned the expensive way
-
MCP servers: First auth model we picked, and later regretted
-
AI coding workflows: Scorecard that replaced vanity metrics in month three
-
Prompt engineering for code: Role prompts the first time we stopped cosplaying with them
-
Cline and Roo Code: Roo modes that encoded our first team conventions
-
JetBrains AI Assistant: Refactoring across types with AI Assistant and not losing sleep
-
Windsurf: What the first long Cascade session actually cost
-
Cursor: Tab predict surprises that made us rewrite comments
-
Google Gemini: Gemini CLI as a weekend scripting partner
-
ChatGPT Codex: Parallel tasks and the temptation to scope too wide
-
Claude Code: Sub-agents the first time they saved an afternoon
-
GitHub Copilot: Early art of rejecting suggestions without hurting velocity
-
Local LLMs with Ollama: Private RAG pipelines, assembled out of a weekend of curiosity
-
Agentic coding: Planning outputs as the real product of the initial turn
-
MCP servers: Early protocol tour, done with a plain JSON-RPC client
-
AI coding workflows: Pair-with-AI rituals for a team that had never tried them
-
Prompt engineering for code: Structured outputs, discovered the hard way
-
Cline and Roo Code: Plan mode as a cheap insurance policy from day one
-
JetBrains AI Assistant: Structural search as the hidden rail for early prompts
-
Windsurf: Moment Windsurf made a skeptical reviewer pause
-
Cursor: Agent mode as a faster, more honest pair programmer
-
Google Gemini: Multimodal debugging with a single screenshot
-
ChatGPT Codex: Sandbox surprises in the first month of Codex
-
Claude Code: Planning mode as the training wheels we kept
-
GitHub Copilot: When inline completion earned its place in the daily loop
-
Local LLMs with Ollama: Picking a local model for code without benchmarks to lean on
-
Agentic coding: Budgets as the first feature any agent had to have
-
MCP servers: Exposing read-only resources before we dared expose actions
-
AI coding workflows: Small reversible steps as a rhythm we borrowed from elsewhere
-
Prompt engineering for code: Learning that acceptance criteria beat cleverness
-
Cline and Roo Code: Bring-your-own-key in the early days of model pricing
-
JetBrains AI Assistant: Junie arrives: the first autonomous task we trusted
-
Windsurf: Flows as a new way to carry intent across files
-
Cursor: Writing a .cursorrules file that did not embarrass us
-
Google Gemini: Gemini Code Assist versus the API, a first year comparison
-
ChatGPT Codex: Writing AGENTS.md for a team that had never used agents
-
Claude Code: Writing your first CLAUDE.md and learning what to leave out
-
GitHub Copilot: Teaching Copilot your repository one readme at a time
-
Local LLMs with Ollama: First week running Ollama on a work laptop
-
Agentic coding: First overnight agent run we dared to approve
-
MCP servers: First MCP server that earned its keep
-
AI coding workflows: First weekly review that made AI-assisted work sustainable
-
Prompt engineering for code: First prompts we wrote that still pass review a year later
-
Cline and Roo Code: First open-source agent we actually trusted
-
JetBrains AI Assistant: AI Assistant day one in a JetBrains shop
-
Windsurf: First look at Cascade after a year of Cursor
-
Cursor: First hour inside Cursor after years of VS Code
-
Google Gemini: First million-token prompt we actually sent
-
ChatGPT Codex: First Codex task that opened a real pull request
-
Claude Code: First week of Claude Code at the terminal
-
GitHub Copilot: First honest week with GitHub Copilot on a real codebase