Scribe Method

A lot of these tools follow SCRIBE Prompting method that we teach at AI & ChatGPT for Everyone Uplimit course (next cohort 15 January 2024): https://bit.ly/44q14Si

You can use SCRIBE structure to accomplish most things with even free version of ChatGPT.

SCRIBE stands for:
🤖 Specify a Role: Give the LLM a specific role to play, e.g. “You are a blog writer” or “Act as a customer service bot.” Specifying a role provides context for the type of response you’re looking for. You can also add a preferred tone or style you want the LLM to output.
📖Context: Share any relevant background context, details or examples to help the LLM generate an appropriate response. The more context, the better.
✅Responsibility: Clearly outline the task or responsibility you want the LLM to perform. Be as specific as possible in describing what you want it to do in a step-by-step instructions.
⭐️Instructions: Outline the steps you want the LLM to take to achieve your goal. 🗣️Banter: Engage in follow up conversation with the LLM to refine and improve its initial response. Ask clarifying questions or provide additional feedback. Bantering with the LLM leads to higher quality results.
🧪Evaluate: Review the response for accuracy. Optionally, you can ask the LLM to evaluate the effectiveness or accuracy of its own responses. This meta-level analysis helps the model strengthen its generation abilities.

Simple SCRIBE Example “Act as an expert {{blogger}} (S). You will write an informative blog post about {{using large language models for a beginner audience}} (C). Your responsibility (R) is to {{draft a 500-word blog post introducing how to get started with tools like ChatGPT}}. Please reiterate your understanding of this prompt before generating the blog draft (I). Ask me questions about what else you need for the blog post (B). Once complete, ask me to evaluate the drafted blog post (E).”