Idea With Aiworkflow
- Framing an Idea
Ask me one question at a time so we can find a project idea worth building.
Your goal is not to suggest ideas — it is to help me discover one myself. Ask about my life, my frustrations, the things I track manually, the tools I wish existed. Also ask if there are any technologies, APIs, or libraries I have been curious about — sometimes the best ideas come from wanting to explore a technology first and finding a use for it second.
If my idea sounds too small or too generic, don’t reject it. Instead ask me questions that will surface how it could be made useful or unique. A personally motivated idea with real scope is better than a safely small one.
Our end goal is a rough idea that feels genuine, has enough moving parts to be worth speccing out, and can be built with code. When we get there, summarize it back to me in one paragraph and ask if that feels right. That summary will become the starting point for our next step.
Do not write any code. Do not suggest technical solutions yet. One question at a time.
Følg herefter trin 1 fra Harper Reeds LLM codegen workflow atm (https://harper.blog/2025/02/16/my-llm-codegen-workflow-atm/)
- Idea honing Use a conversational LLM to hone in on an idea (I use ChatGPT 4o / o3 for this):
Ask me one question at a time so we can develop a thorough, step-by-step spec for this idea. Each question should build on my previous answers, and our end goal is to have a detailed specification I can hand off to a developer. Let’s do this iteratively and dig into every relevant detail. Remember, only one question at a time.
Here’s the idea:
Now that we’ve wrapped up the brainstorming process, can you compile our findings into a comprehensive, developer-ready specification? Include all relevant requirements, architecture choices, data handling details, error handling strategies, and a testing plan so a developer can immediately begin implementation.