Label each part when you paste two messages into the AI
When you paste someone else's message and your own notes into one chat, give each part a label and put the task on its own line, so the AI does not mix them up.
Why it matters
Paste a friend's message and your own notes as one block, and the AI can mix up who said what.
Anthropic's prompting docs say: "Wrapping each type of content in its own tag (for example, <instructions>, <context>, <input>) reduces misinterpretation."
In a normal chat, plain labels do the same job: say what each part is, then say the task.
Do this
- Put a label line before the other person's text, for example "Maya's message:".
- Put a second label line before your own notes, for example "My plan:".
- End with the task on its own line: "Task: write the group message from my plan."
- Read the reply and check it used your plan, not the other message.
A template to paste into any AI chat
Their message: <paste it here> My plan: <paste your notes here> Task: write the reply from my plan.
One thing to keep in mind: Labels tell the AI what each part is, not what to do with it. Without the task line at the end, it still has to guess what you want.
The book club, the names and the times in the video are an example. The docs describe Claude and XML tags; the video uses plain labels in a chat. Source: Anthropic: Prompting best practices, "Structure prompts with XML tags".
Ask me anything about AI and cloudA paid call on your own setup: your agents, your bill, your plan.Book a call →