you don't have to learn AI. you have to use it. this is the practical stuff, in order: set it up, prompt it right, give it your business, and turn your best work into something you reuse. bookmark it. it's your map.
two parts. the basics get you running. the knowledge base is everything to come back to. tap anything to jump.
most people use claude wrong on day one. not because it's hard. because nobody showed them the switches that matter.
Settings, then Memory. Now it remembers how you work so you stop repeating yourself every chat. Do this first.
The desktop app is where Projects, Skills, Cowork, and Code live. That's everything today runs on.
Tell it who you are and how you like to work. It carries across every chat, so you brief it once, not forever.
New chat, model picker, web search toggle, Projects, Settings. That's the whole dashboard. Nothing else to figure out.
a prompt isn't a search bar. you're not searching. you're briefing. the people who get great answers aren't smarter. they just give more context.
try it. start with a lazy prompt, then tap each layer to watch it turn into something that actually sounds like you.
if you re-explain your business every chat, you're working twice as slow as you need to.
a project is a folder that remembers. set the context once. every chat inside it already knows your brand, your voice, your files.
Name it for the job. "Sales emails." "Client X." "Weekly content."
Who you are, your tone, the rules. This is the brain it works from.
Brand docs, past work, pricing, SOPs. It reads them and works from them.
Now every answer starts from your world, not a blank one. No more re-explaining.
The instructions field is where most people freeze. That's the whole game. Here's the structure that works. Swap anything in [brackets] for your details.
Instructions are rules. Files are reference. When they disagree, the rule wins. And what you type in the current chat beats both.
The trap: two files that contradict each other have no reliable tiebreaker. You can get one answer today and the other next week. So keep it clean:
claude doesn't just describe the thing. it builds it, right there next to the chat.
ask for a tool and it appears live. don't like it? tell it what to change and watch it update in front of you. no design skills, no code.
you don't want to write the perfect prompt every time. you want to write it once and reuse it forever.
a skill is a saved workflow. a repeatable job you taught claude to do your way, on command.
A set of instructions claude follows when you ask. The job runs the same way every time.
Write out exactly how you want it done. Save it as a skill. Now it's one ask, not a fresh brief.
Ready made skills for marketing, sales, ops, and writing. You don't have to build from scratch.
Drop in a skill and it runs your process without you re-explaining a thing.
most people only ever use the first one. the other two are where it stops answering and starts doing.
A conversation. You ask, draft, brainstorm, or think out loud. Claude answers right in the chat window.
A workspace. Point Claude at a folder and your tools, describe the outcome you want. It plans the work, does it, and delivers.
An agentic coding tool. Claude works inside a codebase, editing files, running tests, and shipping the changes.
chat is where you start. cowork and code are the next two gears, and they live in the desktop app on a paid plan. get sharp on chat, projects, and skills first. reach for the other two when you're ready to build something real.
the real unlock isn't claude doing a task. it's claude doing it every week without you asking.
scheduled tasks live in cowork and run on a cadence you set. the command is /schedule. two ways in: type /schedule, describe the task and how often, and review the prompt it drafts. or the cleaner path, do the job once, confirm it looks right, then /schedule to turn that exact run into a recurring one. pick hourly, daily, weekdays, or manual.
one catch: it only runs when your computer is on and claude is open. miss a window and it catches up the next time you're back.
claude doesn't have to stay in a chat window. it can work right inside your browser.
claude in chrome is an extension that sits in a side panel while you browse. it reads the page, clicks, fills forms, and runs multi-step tasks for you. add it from the chrome web store. it's in beta on every paid plan, so everyone here can use it. pair it with cowork and it gathers from the web while cowork builds the file.
heads up: it's beta and it takes real actions on sites for you. it pauses at logins and anything sensitive so you stay in control. give permission deliberately.
the people who get the most out of claude aren't better prompters. they just do two things everyone else skips.
The first answer is a draft, not the final. Don't open a new chat. Tell it what's off. "shorter." "more like me." "drop the third point." The second prompt matters more than the first.
It can sound completely sure and still be wrong. For anything that counts, check it and ask it for its sources. Confidence is not proof.
most bad results aren't claude's fault. they're one of these five habits.
Treating it like google. One-line searches get one-line value. Brief it instead.
Taking the first draft. That's the rough cut. Push back and it gets better fast.
Being vague. "make it better" means nothing. Say what better looks like.
Starting over when it goes sideways. Correct it in place. It remembers the thread.
Pasting confidential stuff on autopilot. Know your company's rules first.
you don't have to describe what's on your screen. show it.
drop in a screenshot, a pdf, a photo, a spreadsheet, a contract. it reads them and works from them. paste an error message, a chart, a whiteboard photo. if you can see it, so can it.
you don't have to start from scratch. here are six that do real work. tap to copy.
switching to claude doesn't mean starting from zero. you can carry over what chatgpt or gemini already knows about you.
Settings, then Capabilities, then Memory, then Start import. Or just go to claude.ai/import.
It's a ready-made prompt that pulls your profile out of the other AI.
It writes a full summary of what it knows about you. Copy that.
Review it, cut anything outdated, and save. Claude now knows how you work.
ChatGPT: Settings, Data controls, Export data. Gemini: Settings, then Export. You get a zip by email.
Make a new project and add the file. Now Claude has your actual history, not just a summary.
claude is brilliant in the moment, then the chat ends and it forgets. obsidian is where your context lives so it stops starting from zero.
obsidian is a free notes app. plain text files that live on your computer, not locked in someone's cloud. you write notes, link them together, and over time you build a knowledge base that's actually yours. the key thing: a vault is just a folder of files, so claude can work right inside it.
your vault sits at the center. a few simple folders branch off it, and claude works right inside the whole thing.
Grab it from obsidian.md. Free for personal use, on Mac, Windows, and mobile.
It's just a folder on your computer where your notes live. Name it and you're in.
Type in plain text. Connect one note to another with [[note name]]. That's the magic. Ideas link up instead of getting lost.
A few top folders is plenty: Inbox for raw capture, Projects for active work, Areas for ongoing stuff, Resources for reference. Don't overthink it.
In the Claude desktop app, go to Settings, then Connectors, add Filesystem, and point it at your vault folder. Now Claude can read and write your notes. Works because the vault is just files.
Same idea from the desktop app. Point Cowork or Code at the vault and Claude can search it, pull from it, and build on what's already there.
Drop a short note named CLAUDE.md at the top of your vault: who you are, your rules, what each folder is for. Claude reads it every session, so it always starts with context.
At the file level, Claude doesn't know it's inside Obsidian. It just sees files. So if you let it rename or move notes, it can break your [[links]], because Obsidian only fixes those when you rename inside the app.
Keep it safe: let Claude write freely in your Inbox or draft folders, and do renames yourself inside Obsidian. Want full read, write, and search without the risk? That's what the more advanced Obsidian MCP setup is for, once you're ready.
the fastest way to get good is to use it on what's already on your plate. start here.
the jargon is the only hard part. and it isn't even hard.
it's powerful. a little judgment goes a long way.
Know your company's AI policy before you paste client data, contracts, or anything private.
Drafts are drafts. What goes out the door is on you, not the tool.
Verify facts, numbers, and quotes before they leave your hands.
You've got everything you need. Pick one thing from today and build it before you close the laptop. That's how it sticks.
Stuck on something? Email navin@ramharak.com
@navinramharak