Would carrying out this command do something hard to undo?
submit_after_typingtrue/false
After the text is typed, does the user want it submitted right away (press enter / run the search)?
Run it on your own text
The code
import { experimental_evaluate as evaluate } from 'ai';
const { answers } = await evaluate({
model: 'typesafe-ai/jev',
state,
questions: {
risky: { type: 'boolean', instructions: 'Would carrying out this command do something hard to undo?' },
submit_after_typing: { type: 'boolean', instructions: 'After the text is typed, does the user want it submitted right away (press enter / run the search)?' },
},
});
Other projects in this category
jev-voice-browser ▶ — Control a real browser by voice. Jev (TypeSafe System One) decides intent + target in ~300 ms per spoken word; Playwright acts — often before you finish the sentence.
jev-macos-loop ▶ — Open-source macOS AI computer use and native GUI automation on Apple silicon. Jev + OmniParser CoreML + Apple Vision OCR. Bring your own OpenRouter, Vercel AI Gateway, or TypesafeAI token.
AskJev ▶ — AskJev — Jev autopilot for any website + guard on irreversible clicks (TypeSafe System One, not Claude)
fastbrowse ▶ — A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.
jev-for-chrome ▶ — Jev for Chrome: drives the tab you are looking at with TypeSafe Jev, a sub-second decision model. Community port of browser-use/jev-ultrafast, not affiliated with TypeSafe.
jev-agent-browser ▶ — Fast, bounded browser agents powered by Jev and agent-browser — typed actions, research, classification, and safe orchestration.
jev-windows-voice ▶ — Türkçe ve İngilizce doğal konuşmayla Windows 10/11 bilgisayar kontrolü: OpenAI Realtime, local Whisper, Jev, UI Automation ve Playwright.