Tag

#llm

The Skills I Actually Kept: My Claude Code Skills, and What I Use vs Build
AI Coding

The Skills I Actually Kept: My Claude Code Skills, and What I Use vs Build

The Claude Code skills I actually kept — article drafting, a full deploy pipeline, design-system contracts, self-testing — and the one rule I use to decide when to reuse a pre-built skill versus write my own: who's going to maintain it in six months.

· 8 min read
UI Thrashing: The Reset Protocol That Actually Works
AI Coding

UI Thrashing: The Reset Protocol That Actually Works

When AI-driven UI coding turns into an endless loop of micro-tweaks, don't negotiate with the model — kill the session, max the thinking effort, resend everything, and let it plan without more questions.

· 2 min read
Claude Chat, Claude Co-Work, or Claude Code: How to Know Which One You Actually Need
AI Coding

Claude Chat, Claude Co-Work, or Claude Code: How to Know Which One You Actually Need

The three tiers of working with AI — Claude chat, Claude co-work, and Claude Code — and the exact signal that tells you when it's time to move up a level.

· 4 min read
One Button, No Subscription: How I Stopped Losing My Best Ideas
AI Coding

One Button, No Subscription: How I Stopped Losing My Best Ideas

A physical single-button voice recorder turns my runs, my commute, and my meetings into first drafts — no subscription, and a human review still gates everything before it ships.

· 2 min read
When GSD Became the Bottleneck, I Built Something Lighter
AI Coding

When GSD Became the Bottleneck, I Built Something Lighter

GSD asks a lot up front and forgets what it asked — great for serious multi-phase builds, terrible for rocket-ship mode. Here's the lightweight way of working I reach for instead: high effort, a two-item plan, round-based questions, big-bang execution, and two skills that auto-run the UAT.

· 3 min read
MCP, Skills, Commands, Agents: A Product Manager's No-BS Guide to AI Buzzwords
AI Coding

MCP, Skills, Commands, Agents: A Product Manager's No-BS Guide to AI Buzzwords

A product manager's plain-language explanation of MCP, Skills, Commands, and Agents — revisited with the repo habits that came out of actually living with them: a docs folder as memory, granular Skills over plugins, CLI over MCP where it counts, and picking a model per task.

· 9 min read
My AI Coding Stack: A Practical Guide to Using ChatGPT, Cursor, Claude Code, and Lovable
AI Coding

My AI Coding Stack: A Practical Guide to Using ChatGPT, Cursor, Claude Code, and Lovable

An evolving, practical AI coding stack — ChatGPT, Cursor, Claude Code, and Lovable — updated with how I now default to the Claude Code CLI, route Opus, Sonnet, and GPT to different jobs, and why I dropped Fable.

· 8 min read
The Skill That Stops Claude From Forgetting Your Tasks
AI Coding

The Skill That Stops Claude From Forgetting Your Tasks

A new skill that turns a raw, unstructured brain-dump into a forced checklist of tasks for Claude — and makes it report back exactly what it did.

· 5 min read
Please Stop Comparing LLMs With One-Shot Prompts
AI Takes

Please Stop Comparing LLMs With One-Shot Prompts

One-shot prompt comparisons between LLMs are everywhere right now, and they're useless. The problem isn't the model — it's that nobody bothered to write a spec.

· 2 min read
Fable vs. Opus: My Token-Budget Verdict
AI Coding

Fable vs. Opus: My Token-Budget Verdict

I burned through two paid Max accounts in three days switching to Fable. Here's why I went back to Opus, and where Sonnet actually wins.

· 2 min read
Write Your Acceptance Criteria Before You Let AI Touch the Code
AI Coding

Write Your Acceptance Criteria Before You Let AI Touch the Code

A short AI-coding tip: write your acceptance criteria and tests during the plan, before any code gets written — so you never miss a requirement, and AI can test itself.

· 1 min read
Let AI Test Its Own Work: A UAT Loop With Claude Code and Playwright
AI Coding

Let AI Test Its Own Work: A UAT Loop With Claude Code and Playwright

The practice I use to have Claude Code test its own work with a UAT file, Playwright, and per-persona .env credentials — then ask it to fix what it finds and retest, almost on its own.

· 7 min read
One Database, One Repo: Why Multi-Repo Hurts AI Coding
AI Coding

One Database, One Repo: Why Multi-Repo Hurts AI Coding

A multi-repo split I made for scalability reasons turned into duplicated code and handover files. My rule now: one database, one repo, period.

· 2 min read
Stop Prompting in English If It's Not Your Language
AI Coding

Stop Prompting in English If It's Not Your Language

Prompting an LLM in English when it's not your native language adds a translation layer between your thinking and the model — switch to your own language and that layer disappears.

· 1 min read
What If AI Sat in the Middle of Every Conversation?
AI Takes

What If AI Sat in the Middle of Every Conversation?

A WhatsApp voice message and an old failed startup called Alfred got me thinking: what if AI sat between every sender and every receiver, translating each message into the style the other person actually wants?

· 5 min read
Context Is Everything: Keeping AI Coding Agents From Losing the Plot
AI Coding

Context Is Everything: Keeping AI Coding Agents From Losing the Plot

Why saturating a coding agent's context window quietly wrecks its output, and the docs/backlog/handover system I use to give agents real memory across a multi-repo project.

· 5 min read
LLMs Don't Hallucinate — You Just Don't Ask Them to Show Their Work
AI Coding

LLMs Don't Hallucinate — You Just Don't Ask Them to Show Their Work

The reframe that changed how I use AI for anything serious: it's not that the LLM hallucinates, it's that you never asked it to expand its context and prove its work. Here's why it happens — limited context, embeddings picking the closest match instead of the exact truth — and the two-step trick that kills most of it: expand the context, then demand proof for every sentence.

· 3 min read
Permission Modes for AI Coding: Bypass, Auto-Edit, and Planning
AI Coding

Permission Modes for AI Coding: Bypass, Auto-Edit, and Planning

Bypass, auto-edit, and planning are three different gears in Claude Code, not one setting — and knowing when to shift into planning is what saved a deploy bug I couldn't fix any other way.

· 4 min read
Why AI Won't Save Us All (And Why That's Not What You Think)
AI Takes

Why AI Won't Save Us All (And Why That's Not What You Think)

AI hype hides the hard work of real products; designers, PMs, and engineers are still needed because making something great is the difficult 90 percent.

· 3 min read
When ChatGPT Is Not Enough: How I Planned an XTerra with AI
AI Coding

When ChatGPT Is Not Enough: How I Planned an XTerra with AI

Planning an XTerra triathlon revealed why ChatGPT struggles with long projects, and how moving to Claude Code with files and MCP fixed memory and dates.

· 3 min read
AI Won't Replace You (Unless You Allow It To)
AI Takes

AI Won't Replace You (Unless You Allow It To)

Treating AI as a collaborative companion rather than a one-shot replacement, and recognizing its limits to work faster and stay ahead.

· 2 min read
Schools Are Missing the Biggest Opportunity AI Has Ever Given Us
AI Takes

Schools Are Missing the Biggest Opportunity AI Has Ever Given Us

A personal argument that schools should embrace AI to personalize learning for each child, using a five-step study framework as an example.

· 3 min read