Create a custom GPT that learns your specific standards for quality work. By providing 'before' and 'after' examples, you can train an AI to act as a coach, giving your team instant, high-quality feedback that clones your expert eye.
with Claire Vo
Create a simple two-column document or PDF. In the first column, place examples of work that miss the mark (the 'before'). In the second column, place the revised versions that meet your standards of excellence (the 'after'). This document will be the training data for the AI.
Upload your PDF of examples to ChatGPT and use a simple prompt to ask the AI to identify the principles you're using to evaluate the work. This allows the AI to discover patterns in your feedback that you might not have articulated yourself.
Here are some examples of slides. In one column the slides are not good. And in the other column I have edited them and made them good. Can you help me articulate the principles I am using to determine what is good and bad based on these examples? Use these examples.Engage in a back-and-forth conversation with the AI to refine the initial list of criteria. Use prompts to push the AI for more detail and add your own context about what's most important, creating a comprehensive and robust rubric.
Be 100 times more specific.Instead of writing the instructions for your custom GPT from scratch, ask the AI to write them for you based on the refined criteria. Define your goal and tell the AI its job is to create the prompt for the GPT.
My job is to create a GPT that can evaluate slide decks for people on my team based on my specific criteria that I care about. It's really important to me that this GPT explains the criteria, why it matters, and gives the user specific feedback on how to improve. YOUR job is to write the prompt for it.Go to the GPT creator in ChatGPT and paste the AI-generated instructions into the 'Instructions' field. Give your GPT a name (e.g., 'Deck Doctor'), test it by uploading a sample document, and then share it with your team so they can get instant feedback.
Follow Sahil Lavingia's method for delegating small but impactful maintenance tasks, like fixing an internal Slack report, to the AI agent Devin. This workflow shows how to use simple, clear prompts to fix code and update system prompts without distracting your engineering team.
Learn Gumroad CEO Sahil Lavingia's process for rapidly prototyping a UI with v0, then using the AI agent Devin to autonomously code, implement, and submit the feature for review, turning a multi-day task into a one-hour workflow.
Improve your writing in real-time by using ChatGPT as a first reader. Get instant feedback on structure, clarity, and flow as you write, allowing you to polish your work section by section.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.