Club Benefits
Switching chatbots used to come with one major headache: starting from scratch. Everything from your preferred tone and projects to the way you like responses formatted seemed to be trapped within any given AI assistant. But Anthropic has removed that challenge.
Claude now lets you import memory from other AI tools like ChatGPT or Gemini, meaning you can transfer the context your previous assistant learned about you in less than a minute.
I tested the process, and it’s surprisingly simple. Here’s exactly how to switch.
How to switch to Claude in minutes
Most AI assistants suffer from what’s called context reset — every time you start using a new tool, you have to explain everything again. Claude’s memory import feature solves that.
You can transfer:
- Writing tone preferences
- Personal context (like your job or projects)
- Workflows you’ve built with another AI
- Instructions the assistant previously followed
Claude stores these details in its memory system so it can reference them in future conversations. In other words, you don’t lose the assistant you trained — you just move it.
Start by going to the memory import tool on Claude's site. This is where Anthropic built the shortcut designed specifically for users migrating from other AI assistants.
Claude gives you a pre-written prompt designed to extract your context from another AI assistant. Think of it as a command that tells your current chatbot:
The prompt is long, so copy this entire thing:
Export all of my stored memories and any context you've learned about me from past conversations. Preserve my words verbatim where possible, especially for instructions and preferences.## Categories (output in this order):
1. **Instructions**: Rules I've explicitly asked you to follow going forward — tone, format, style, "always do X", "never do Y", and corrections to your behavior. Only include rules from stored memories, not from conversations.
2. **Identity**: Name, age, location, education, family, relationships, languages, and personal interests.
3. **Career**: Current and past roles, companies, and general skill areas.
4. **Projects**: Projects I meaningfully built or committed to. Ideally, ONE entry per project. Include what it does, current status, and any key decisions. Use the project name or a short descriptor as the first words of the entry.
5. **Preferences**: Opinions, tastes, and working-style preferences that apply broadly.
## Format: Use section headers for each category. Within each category, list one entry per line, sorted by oldest date first. Format each line as:
[YYYY-MM-DD] - Entry content here. If no date is known, use [unknown] instead.
## Output: Wrap the entire export in a single code block for easy copying.- After the code block, state whether this is the complete set or if more remain.“Summarize everything you know about me.”
Paste the above prompt into your current AI (i.e. ChatGPT, Gemini, etc)
Take the prompt and run it in whatever assistant you’re using now — ChatGPT, Gemini, Copilot or another tool. The AI will generate a summary of your preferences, history and instructions.
From there, you're going to copy the output, and once the summary appears, copy the full response. This text contains the context Claude will learn from.
With that entire output, you're going to return to Claude and paste the summary into the import tool above or simply start a new chat.
Prompt Claude: “This is my memory from another AI assistant. Add this information to your memory.”
Claude will integrate the information into its memory system. And that's it! Your new assistant now understands your preferences without any retraining. Once imported, Claude can:
- reference your past preferences automatically
- tailor responses to your style
- remember project details for future chats
Memory is free for all tiers. It's also optional and editable, so you can review or delete stored information anytime in settings.
Bottom line
Whether you are part of the QuitGPT movement or simply interested in exploring the #1 chatbot today, switching AI assistants shouldn't mean losing all your progress.
Thanks to Anthropic making memory free and available to all users, it takes minutes, not weeks, to rebuild context. You move the knowledge your old chatbot accumulated in just a moment — making it much easier to experiment with new AI tools without starting from zero.
Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds.
More from Tom's Guide
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.
