Who it is forA personal finance or product developer who wants a chat answer that is a calculator the user can adjust, not a static table.
The problemA loan or split answer in text cannot be adjusted, so users ask again for each change.
The outcomeA chat answer with sliders that recalculate a payment schedule or a split that adds up to the cent, plus a copy button.
What you need first
- Node 24
- An OpenUI Cloud (Gateway) key in THESYS_API_KEY, or any OpenAI-compatible API key set through LLM_BASE_URL, LLM_API_KEY and LLM_MODEL
- Optional: Ollama and enough memory for a local model (the README recommends 32 GB or more for the default)
Steps
- Run
npm run devafter setup and open http://localhost:3000 - Ask for a loan calculator with a slider for the amount and rate
- Check that the answer binds the sliders to $variables and uses @Payment for the monthly amount
- Ask for a bill split and check that @Allocate is used so the parts add up to the total
Prompt for your agent
In thesysdev/open-intelligent-ui, read the function list in src/lib/functions/ and confirm @Payment and @Allocate exist. Then send the request "Make a loan calculator with sliders for amount and rate" to the running chat and report which functions and Slider components the generated OpenUI Lang uses.
Caveat. The README says the model writes the UI, so the result depends on the model and is not a verified financial product; check the math before relying on it.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page