Tutorials
26 posts in this category.
Plugins vs Skills in Claude: Not the Same Thing
A skill is one workflow. A plugin is a bundle of skills packaged together. Confuse them and every Cowork tutorial you watch will be twice as confusing as it needs to be.
Claude Runs Code For You (You Never Touch a Terminal)
The bash tool lets Claude write and execute code automatically. Data processing, file renaming, spreadsheet analysis. Developer-level automation, zero developer required.
Claude Projects: Separate Brains for Every Job
Running everything in one Claude conversation is chaos. Projects give each area of your life its own memory, instructions, files, and scheduled tasks.
Claude Builds Dashboards Inside Your Chat (Artifacts Explained)
Artifacts are interactive HTML pages, charts, and dashboards Claude builds right inside the conversation. Not paragraphs you have to read. Things you can actually use.
Make Claude Think 10x Harder With Extended Thinking
Extended thinking makes Claude pause and reason through complex problems step by step before answering. Most people never turn it on. That's a mistake.
Claude Can Search the Web Now. Use It Right.
Claude's training data has a cutoff date. Web search is how it stops guessing about last week. It pulls real articles, real data, and cites its sources.
What Multimodal Actually Means in Claude (Stop Typing, Start Showing)
Multimodal just means Claude can process more than text. Images, screenshots, PDFs, spreadsheets, code files. Stop describing things to your AI and start showing it.
Why Claude Forgets Mid-Conversation (And How to Stop It)
Ever had Claude forget something you said 20 minutes ago? That's not a bug. That's the context window, and once you understand it, you can stop it from biting you.
Claude Remembers Everything Now. Here's How.
Cowork's built-in memory system quietly stores your preferences, workflows, and business context from every conversation. You can even force it with three words.
CLAUDE.md vs Global Instructions: They Are Not the Same Thing
Confusing CLAUDE.md with global instructions will mess up your entire Claude setup. One is the project brain, the other is your permanent identity. Here's the split.
This One File Controls Everything in Claude
CLAUDE.md is a single markdown file that Claude reads before every conversation. Set it up once and Claude stops needing you to repeat yourself. Most people don't know it exists.
The First Claude Cowork Step Most People Skip
Most people open Cowork and start chatting immediately. Wrong move. The workspace folder is the foundation everything else sits on, and skipping it costs you later.
Every Claude Cowork Feature Explained in Plain English (All 20 of Them)
Skills, connectors, sub agents, MCP servers. Everyone throws these words around like you already know what they mean. You don't. Here's all 20 Cowork concepts, from the basics to the stuff that feels like an actual employee.
Why Your AI Seems to Forget Things
Loaded a ton of instructions into Claude and it started ignoring them? Your AI is not dumb. It is full. Here is the fix.
Your AI Will Fail Silently Unless You Do This
Scheduled AI tasks break, sometimes without telling you. Add a failure alert so you find out right away, not three weeks later.
Your AI Instructions Are Too Long
Most people write custom instructions as two paragraphs. Don't. Six lines beats two paragraphs every time. Here is the format.
Your AI Is Confident When It's Wrong
The scariest thing about AI is how sure it sounds when it is totally wrong. My fix: run it twice, with a second session checking the first.
Never Let Your AI Delete Anything
AI agents can delete your files. Flip one setting so it asks before acting. Takes 30 seconds and it saved me from losing a client file last week.
Your AI Can See Way More Than You Think
Gave your AI access to your whole Downloads folder? It can read everything in there. Scope it down to three folders max. Here is the setup.
The One File That Changes Everything With Claude
There is a file Claude reads every time you open it, and most people do not know it exists. It is called CLAUDE.md. Here is why it matters.
ChatGPT 90-Second Pro Setup
Most people jump straight into prompts and wonder why the answers are generic. Spend 90 seconds setting up a Project and every chat starts smart.
Stop Picking The Wrong ChatGPT Mode
If ChatGPT feels dumb or slow, you're probably in the wrong mode. Auto, Instant, Thinking, and Pro each behave differently. Here's when to use which.
The Art Of Crafting Perfect AI Prompts
Stop getting generic AI answers. Use the four-part formula that fixes almost every weak prompt: Role, Context, Command, Format.
How to Teach a 10-Year-Old to Wield AI Like a Tiny Tech Overlord
Yes, you can teach a 10-year-old to build AI agents with n8n and zero code. Here is the step-by-step plan, chaos included, snark very much intended.
Build Your First LLM App Without Losing Your Sanity
Build your first LLM app without the existential meltdown. A sarcastic step-by-step guide to picking a use case, stack, prompts, and shipping an MVP.
Large Language Models Explained, Now With 73% Less BS
Large language models explained in plain English: glorified autocomplete, transformers, probabilities, and why your chatbot is a confident BS machine.