When starting a greenfield project, do you take the time to write things down sketching out the domain, architectural direction, and key trade-offs to clarify your thinking upfront, or do you prefer to let the design emerge incrementally as you vibe code?
I chat with Claude about viability, capability, existing solutions, alternative approaches, etc.
This helps me get an idea of what we’re doing. I get pushback and have to be clear and Opus is good at asking questions.
Then I get it to write a set of documents for Claude Code describing the vision, the solution, the technical choices, the testing plan, the validation approach, how to share with colleagues, future ideas and a table of contents.
Great approach, since you are following a pre-defined set of approaches, have you thought of building an agent for it? or do you have a prompt which helps you with getting the relevant answer?
I have a projects folder in the app which has a set of instructions - bot mostly what documents to follow. It works well enough but you're right, I should push it a bit more.
It's great that we can iterate on the solutions and they become general.
This helps me get an idea of what we’re doing. I get pushback and have to be clear and Opus is good at asking questions.
Then I get it to write a set of documents for Claude Code describing the vision, the solution, the technical choices, the testing plan, the validation approach, how to share with colleagues, future ideas and a table of contents.
reply