Weekly Prompts.04: Automated workflows and vetting literary agents

This week’s prompting took me a few steps deeper into a pair of topics: autonomous AI and literary agent research.

The highlight of the week was a very impressive table of literary agent information from Copilot (see prompt #3).

This week’s prompts include:

1. Learning the steps of automated prompt engineering (Grade: A)

2. URLs for list of literary agents (D)

3. Literary agent deep research (A)

4. Conducting an economic research study (A)

5. Finding tutorials about AutoGPT (B)

---

Prompt: Learning the steps of automated prompt engineering

Please outline the steps for me to learn how to do automated prompt engineering. I am looking for a step by step list (or lists) that will be hands on direction. Please refer to the following article for what I mean when I say “automated prompt engineering”.

— article START —

[ex. Automated Prompt Engineering (APE) is a technique to automate the process of generating and refining prompts for a Large Language Model (LLM) to improve the model’s performance on a particular task. It uses the idea of prompt engineering which involves manually crafting and testing various prompts and automates the entire process. As we will see it is very similar to automated hyperparameter optimisation in traditional supervised machine learning.]

 — article END —

I haven’t used it much yet, but Claude’s outputs were inline with my limited understanding and also thorough. The 12-item list I was given was very action-forward and was very easy to follow up on.

Grade: A

Prompt: URLs for list of literary agents

Please find me the URL for each of the following literary agents page on the website Manuscript Wishlist (https://www.manuscriptwishlist.com/). Provide me the list of URLs in a one-column table. You need to provide me each url as the raw URL text. 

For example, when I include the agent "Dani Segelbaum", I expect you to provide me the URL: "https://www.manuscriptwishlist.com/mswl-post/dani-segelbaum/" 

-- literary agents START -- 

[Includes agent name, agency name] 
Elyse Baker The Baker Agency 
Brianne Thomas HG Literary 
Reiss Grendell Gray Partners 
Christi Grebo Jane Rosen Agency 

-- literary agents END --

I eventually got a list of five URLs in the format I wanted them. But teeth were pulled. I actually think some part of this was a UX miss on Copilot’s part.

Grade: D

Prompt: Literary agent deep research