I built this after watching a marketing team retype the same prompt for the fourth time that week, each time slightly differently, and ship the version with the previous client's name still in it.
The thing that surprised me building it: the hard part isn't storage, it's the blanks. A prompt in a doc has no concept of a variable, so every reuse means editing the text by hand — which is exactly where mistakes get published. Making the changing parts into labelled fields means the prompt itself is never edited, so it can't be edited wrong.
Honest about where it isn't for you: if you keep five prompts and use AI occasionally, a pinned chat is genuinely fine. This earns its place when prompts become daily work and more than one person runs them.
Happy to answer anything — and I'd genuinely like to hear what you've been using instead.
Hi PH 👋
I built this after watching a marketing team retype the same prompt for the fourth time that week, each time slightly differently, and ship the version with the previous client's name still in it.
The thing that surprised me building it: the hard part isn't storage, it's the blanks. A prompt in a doc has no concept of a variable, so every reuse means editing the text by hand — which is exactly where mistakes get published. Making the changing parts into labelled fields means the prompt itself is never edited, so it can't be edited wrong.
Honest about where it isn't for you: if you keep five prompts and use AI occasionally, a pinned chat is genuinely fine. This earns its place when prompts become daily work and more than one person runs them.
Happy to answer anything — and I'd genuinely like to hear what you've been using instead.