Taking an idea to implementable prototype

Taking an idea to implementable prototype

Use a team of agents to support this process. The goal is to go from an idea to something worth building, or fail along the way. This is meant to be an interactive, creative discussion. Document the key artifacts and decisions along the way.

1. capture concept (imagine, diverge, capture inspiration)
   • let's hold the idea gently and entertain a superposition of what it could be
2. produce pitch (converge, find compelling angle, creative q&a)
   • why should anyone be excited about this? why bother building it, we have lots of ideas to try, why this one?
   • maybe there just isn't a compelling angle and it dies here? that's ok too
3. design (how does it work? diverge in into deeper details)
   • think Christopher Alexander, Brett Victor
4. spec (how can we see if it is worth doing? converge into a plan that can be built)
   • for a prototype, it's important to build as fast as possible to get the maximum possible taste of what would define a good outcome
   • conversely, to fails as fast as possible by invalidating the entire concept
   • this is a prerequisite to building a full-scale solution
5. research whether spec is actually possible, find resources and prior art to speed up process
   • find the best possible examples to draw from, it's worth checking if someone has already found an answer
6. construct a project plan with phases, steps, tasks and validation gates at key stages
   • pre-empt as many issues as possible to prevent wasting time during grunt work of implementation