Why Does Claude Act Like It's Never Met You Before?
Teach Claude Once with Context
Claude acts like it’s never met you before because, by default, it doesn’t carry your personal context from one chat to the next. The fix is to teach it your basics once, so you stop re-explaining the same things every week.
What this post does
This post should make the problem feel familiar first: the endless loop of re-briefing, re-prompting, and repeating yourself. It then turns that pain into a simple habit — teach Claude once, then let that context shape future answers.
Freebie
Use these three copy-paste prompts today:
Act as my specialized consultant. Here is my context: [paste context]. From now on, whenever I ask for help, synthesize your answer through the lens of this context.Before you execute any task, tell me what you need to know about my constraints or preferences to get this right on the first try.I keep re-explaining myself to AI. First, ask me the 5 most important things you should remember about how I work, what I care about, and what I need.The AI broken down
Claude “forgets” you because each new conversation starts without the background you have in your head. It can remember some things over time, I think it’s always better to have a document of your contextual requirements around, so that if you use other LLMs, it can transfer easily. That means your role, tone, audience, preferences, and repeated constraints all have to be rebuilt from scratch unless you store them in a way Claude can reuse.
A better mental model is this: instead of explaining yourself forever, you’re creating a short briefing that Claude can use every time. It’s the difference between giving directions once and having to redraw the map for every trip.
A simple way to start is to list the three things you explain most often. For many people, that will be tone, audience, and format. Once you write those down, you’ve already built the core of your first Skill.
Reader action
Write down 3 things you re-explain to Claude every single week. That list becomes the raw material for tomorrow’s setup.
Context. The perfect descriptor for improved communication with Clyde, ooops, I mean Claude. (I call him Clyde because it reminds me that he's not the bright human he sometimes seems to be. No, he's read more than I have by a jugful, but he doesn't have the human reflexes I do. He is learned, but not conscious.
Phillip Alcock has posted a useful way of making a semi-permanent record of the things Clyde needs to respond more precisely. It's sorta like the model knows you better because you've dated for maybe a month now, so you can move on to maybe holding hands once in a while, if you are old-fashioned like me.
Im now calling my Claude Clyde 🤣 brilliant. Try writing context on a single document, even just to explain how you might research something, and then I normally ask AI to convert it to custom instructions. So it stays like that for a project.