Use this local preview to turn a plain-English app description into a starter jso.config.json. The browser version uses deterministic rule-based mapping — matching keywords like "react", "node", "license", "balanced", "maximum". The authenticated preset-suggest API can use an account OpenAI or Claude key for provider-backed recommendations with the same response shape.
Local preview. The mappings below are hand-written rules so you can try the workflow without a provider key. Provider-backed responses are more nuanced — the assistant reads your description, asks clarifying questions when ambiguous, and surfaces trade-offs the rule-based version flattens.
Add your AI key or
compare managed AI plans.
Describe your app
Generated jso.config.json
Detected signals
- (type a description and click Generate)
How provider-backed preset suggestions improve on this
The rule-based mapping catches obvious keywords and produces a reasonable starting config, but it does flatten nuance. Three concrete examples of what provider-backed review can do differently:
- "Protect the license-check function strongly." Rule-based version sets
FlatTransform: true globally. Provider-backed review asks for the function name (or infers it from the surrounding description) and recommends an @virtualize marker on just that function, leaving the rest of the bundle on balanced — smaller output, faster runtime.
- "Performance matters most." Rule-based version drops to a
standard preset. Provider-backed review reads the rest of the description (is it a marketing widget or a payment flow?) and chooses between standard and balanced accordingly, naming the trade-off out loud.
- Ambiguous descriptions — "obfuscate my JavaScript." Rule-based version defaults to balanced. Provider-backed review asks what frameworks you use, how performance-sensitive your hot paths are, and what code is high-value, then produces a config informed by the answers.
The promise of provider-backed assistance is honest reasoning about trade-offs, not just keyword matching. The rule-based preview is useful for quick starts; the deeper feature is the conversation.