NativeX vs BDUI Go

NativeX is a visual playground for Apple's on-device intelligence — build prompt pipelines as a graph of cards, wire them together with variables, and run them right on your iPhone. Built for iOS engineers, prompt engineers, and the AI-curious: if you want to know what Apple's on-device model can actually do, this is the fastest way to find out. FREE AND PRIVATE Every run executes on the Apple foundation model that ships with your device. No account, no API key, no server: prompts, photos, and recordings never leave your iPhone, and inference costs nothing. LEARN THE REAL API Every card mirrors one Apple framework call and names the exact Swift symbol — LanguageModelSession, NLTokenizer, RecognizeTextRequest, SpeechTranscriber, etc. Configure it in the inspector, run it, read the output. What you learn transfers line-for-line to Xcode. BUILD PROMPT PIPELINES • Prompt groups assemble instructions, few-shot examples, history, and the curreturn into a single transcript • Guided generation: constrain output to JSON with registered schemas, or design your own schema on the fly — no rebuild • 17 native ops: tokenize, detect language, named entities, sentiment, OCR a photo, read a barcode, transcribe speech, speak text aloud, regex, JSON extraction, and more. Wait for more! • Human-in-the-loop pauses: type or dictate an answer mid-run EVALUATE LIKE A PRO — LLM OPS, ON-DEVICE NativeX brings the modern LLM-ops workflow — observability, datasets, evaluations — to the model in your pocket: • Run History logs every execution as a step-level trace — assembled prompt, output, timing, token estimates • Datasets batch-run a graph over a table of records, sequential or parallel • LLM-as-judge scoring runs on-device too • Re-run, reproduce, and compare past runs REQUIREMENTS NativeX runs the Apple Intelligence on-device model. That requires an iPhone 15 Pro or newer (A17 Pro chip or later) on iOS 26 or later, with Apple Intelligence enabled in Settings.

BDUI Go opens mobile apps that are described in JSON: their screens, navigation and API requests. Authors create these apps in the BDUI web dashboard and share a link or a QR code. You open it in BDUI Go, and the screens render natively on your iPhone. Each app opens inside BDUI Go, so there is nothing extra to install. When the author publishes an update, you get the new version without reinstalling anything or waiting for an App Store update. A JSON description is data, not code: it lists which components to show and which requests to make. BDUI Go renders it with native Compose Multiplatform components — no webview, no downloaded executables. TRY IT RIGHT AWAY — NO ACCOUNT NEEDED • Component showcase: every building block, rendered live from JSON • Currency rates: live exchange rates from the Frankfurter API, pull down to refresh • Weather: city search and forecasts from the Open-Meteo API • Sign-in demo: an app that signs in to an API and keeps the session fresh automatically More demos with QR codes — a tea shop, a live earthquake feed, a cafe menu — at https://bdui.io HOW IT WORKS 1. An author describes an app in JSON in the BDUI web dashboard and publishes it 2. They share a link or a QR code 3. You open it in BDUI Go — the screens render natively on your iPhone Authors can try changes on a separate test channel before publishing them, and roll back to any earlier version in one click. FEATURES • Native rendering — no webview • Offline cache: previously opened apps launch even without a network • Recents list, with any app pinned as the default one that opens on start • Request controls: authors can limit which hosts an app's API requests may reach • Built-in sign-in support for apps that use an API with tokens • Universal Links: https://bdui.io/a/… opens directly in BDUI Go PRIVATE BY DESIGN No accounts in the app, no ads, no analytics, no tracking. The camera is used only to scan QR codes, entirely on your device. Privacy policy: https://bdui.io/privacy CREATE YOUR OWN Describe an app in JSON — screens, navigation, API requests — publish it and share a link. The web dashboard is in early access: request access at https://bdui.io