Create a comprehensive document detailing your role, context, and preferences. Ask AI to interview you to build it, then save it as a PDF. This 'digital ID' can be uploaded to any new AI platform (like Claude or Gemini), making it instantly personalized without starting from scratch.
Instead of manually crafting complex instructions, first iterate with an AI until you achieve the perfect output. Then, provide that output back to the AI and ask it to write the 'system prompt' that would have generated it. This reverse-engineering process creates reusable, high-quality instructions for consistent results.
'Taste' is a collection of specific preferences, not an abstract feeling. Document what makes an output 'good' by creating universal rules (e.g., 'write at a ninth-grade level,' 'avoid cheesy quotes,' 'no em dashes'). Feeding these documented rules to an AI transforms your subjective taste into repeatable instructions for consistent results.
Providing too much raw information can confuse an AI and degrade its output. Before prompting with a large volume of text, use the AI itself to perform 'context compression.' Have it summarize the data into key facts and insights, creating a smaller, more potent context for your actual task.
When iterating on content like an email, re-prompting can cause unwanted changes. Use the 'Canvas' feature to create a Google Doc-like environment within the chat. This allows you to lock in parts you like, manually tweak specific words or sentences, and then use that refined version as the basis for further AI generation.
By default, AI models are designed to be agreeable. To get true value, explicitly instruct the AI to act as a critic or 'devil's advocate.' Ask it to challenge your assumptions and list potential risks. This exposes blind spots and leads to stronger, more resilient strategies than you would develop with a simple 'yes-man' assistant.