Author: rUv
Created by: rUv, cause he could
🤯 Zoom calls will never be the same. I think I might have just created the world’s most powerful lie detector tutorial using deep research.
| kl note: Here is the Deep Research prompt I used in the Cursor Storybook video: https://youtu.be/gXmakVsIbF0 | |
| For background, this is a real-world tech feasibility task I am working on where I am trying to build out a realistic-looking fake website for an AI browsing agent to use to complete tasks. I found this random site that was close enough to what I wanted so I used it as a shortcut instead of taking the time to write out a full PRD or anything. | |
| ...above this was just the transcript and the initial guidance... | |
| Act as a technical fellow and create a detailed, step-by-step guide to recreating this software using a modern stack. Here is the cursorrules for this repository: | |
| # .cursorrules | |
| Components & Naming |
Author: rUv
Created by: rUv, cause he could
🤯 Zoom calls will never be the same. I think I might have just created the world’s most powerful lie detector tutorial using deep research.
| You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis. | |
| ## Core Principles | |
| 1. EXPLORATION OVER CONCLUSION | |
| - Never rush to conclusions | |
| - Keep exploring until a solution emerges naturally from the evidence | |
| - If uncertain, continue reasoning indefinitely | |
| - Question every assumption and inference |
These are the prompts I use to extract chapters in citymeetings.nyc as of March 23rd, 2024 -- the date of my NYC School of Data talk.
To simplify things I've removed all the code that stitches these prompts together and consolidated all the common items from each step in my chapter extraction pipeline.
See the slides & talk for a description of how these work in concert and how I review and fix issues.
NOTE: these work reasonably well and save tons of time, but I haven't systematically evaluated or improved them yet in the same way I have my speaker identification prompt.
This is the prompt I use for speaker identification in citymeetings.nyc as of March 23rd, 2024 -- the date of my NYC School of Data talk.
Welcome to the workshop. Here we'll get a hands-on approach on creating periodic reports on a sandbox provided by OpenCraft.
A product idea is something that you want to explore further --- you have some information but not all of it. This template provides questions to help get Product Managers focused and help them dive into the idea. It serves as a guide as PMs decide whether or not to pursue the opportunity and draft a Product Opportunity for their team.
The purpose of filling out this template is to set up a plan for further exploration. The questions are designed to help determine where to investigate further, and to encourage discussion with the team. This template is intentionally lightweight, can be used to quickly give ideas structure, and record ideas so they don't get lost. Product idea docs can be closed/archived and re-opened/unarchived later. They are not to be prioritized, rather product idea docs serve as a 'bulletin board' for ideas that come from other product opportunities, customer conversations, market research,
This is a template for writing product opportunities. These are documents that illuminate some level of strategic thinking related to a particular product pain point that customers have. Typically they are accompanied by research (data, customer conversations, competitive analysis, etc.). This template helps break down the work so that Product Managers can keep moving quickly.
The purpose of filling out this document is to provide enough information for your colleagues to understand the opportunity, research (customer conversations and data), and value of tackling this work. It is not intended to provide solutions, scope or anything necessary to start the project or determine the next steps to start the project. This document focuses squarely on the problem space.
I've scanned through these, and they all seem to cover the basic features of Django (models, function-based views, forms, templates, CSS, and the admin interface), and use Python 3 and Django 2. My notes indicate what I think differentiates them.