PRISM refracts what you ask into its component pieces — objective, platform, constraints, style — then recombines them into an engineered prompt tuned to the exact AI you'll run it on. Then refine it in plain language until it's right.
Your request is split into what you want, the tools to use, and how to phrase it.
The prompt is written to fit your target model and tuned to where you'll run it.
It shows the reasoning behind the prompt, plus which tools to run it with and why.
Tell PRISM what to change in plain words. It rewrites in place and keeps a history of your revisions.
PRISM · prompts engineered by decomposition
built entirely in your browser by PRISM's own engine — no keys, no network, works offline
Pick where you'll run it. The architect then opens styled like that model's own app — and writes the prompt in its native conventions.
Describe what you want a prompt for. PRISM breaks it into what you want, the tools to use, and how to phrase it — then writes a sectioned prompt.