miniAssistant vs Trifecta

* Works with the LM Studio API, OpenAI (GPT), Anthropic (Claude), and Apple Intelligence! * The LM Studio tab connects to any OpenAI-compatible API. * Each provider is tuned individually, including a high precision mode to control thinking level. * Personalize the prompt to tailor the app to your own needs. * Function calling is available for calendar events, reminders, notifications, web search and page fetching, location data, on-device memory, knowledge base search, image generation, and user interaction. * For example, you can summarize, add, and edit your schedule in natural language. * Add your own documents and let the AI search them (RAG). * Change the background using images from your Photos library. * You can ask AI to set notifications and list reserved notifications. By default, the app opens the conversation by listing today's remaining calendar events — or tomorrow's, if none are left. This behavior can be customized in your language on the settings panel. You can instruct the LLM in natural language, for example: "Search the next US holiday and add it to my calendar". The app automatically replies in your device's default language. [Note] * This app is provided free of charge for research purposes. * Use it at your own risk, and do not rely on it for critical or high-stakes decisions. * The current time on your device is sent as the initial user prompt, and your device's language setting is sent as the system prompt. * When function calling is enabled, the app sends data from your device to the AI you selected. This may include calendar events, location data, saved notes, and excerpts from documents you have added to the RAG knowledge base. * Image generation is available with OpenAI models only. * API usage fees apply when you use OpenAI or Anthropic models with your own API key. * The software is provided "as is," and the author assumes no responsibility for its performance. * This app is a technical demonstration of LLM usage and should not be used for critical decisions, including business or medical purposes. * The content of AI-generated responses depends on the model you select. * AI may generate incorrect responses, and their accuracy is not guaranteed. [Safety Measures] * You are asked to confirm after every five consecutive function calls. * In Safe Mode, adding or editing a calendar event requires your confirmation through the standard iOS interface. * Deleting a calendar event always requires your confirmation, whether or not Safe Mode is enabled. * Location access is managed by the standard iOS permission system, and only approximate location data is used. [Apple Intelligence Limitations] * Requires an Apple Intelligence–compatible device running iOS 26 or later. * Limited context window: enabling many tools can exceed it, causing the model to skip tool calls and hallucinate. Disable tools you don't need. * Safe Mode is always on for calendar operations. * Tool calling stops with an error after 20 consecutive calls.

Most habit apps measure motion. Trifecta measures whether you're getting better at the things that actually decide outcomes. The whole app rests on one idea: success ≈ Judgment × Time × Luck Each of the three habits trains one of those variables — ten minutes a day, total. No feeds, no coins, no levels. Just the loop that compounds. PREDICTION JOURNAL — sharpen your judgment (3 min) Write a falsifiable prediction with a confidence level and one line on why. On the due date you score it right or wrong. Memory rewrites itself; ink doesn't. Over weeks you learn exactly where your judgment is trustworthy and where it reliably fails. KILL LIST — win by subtraction (5 min) Each evening, name the one thing that, if it vanished, nothing important would break. When the same time-waster appears three times in a week, the app flags it: KILL IT. The very successful win by cutting, not adding. DAILY EXPOSURE — widen your luck (2 min) Luck has a surface area: what you do times how many people know about it. Once a day, do one outward act — message, publish, ship, or ask. One tap to log it. THE CALIBRATION CHART The most important screen in the app. It plots your stated confidence against your real hit rate. If your "70% sure" calls come true 40% of the time, you're overconfident — and now you know by how much. The feedback loop almost no one ever gets. BUILT TO GET OUT OF YOUR WAY • Open, log, and close in under 60 seconds • One screen per habit, one action per screen • Two gentle reminders a day, then silence — no other notifications, ever • Forgiving streaks, because perfectionism kills habits • A Graveyard of everything you've killed • An exposure history that shows your luck surface growing PRIVATE BY DESIGN • 100% local — your data stays on your device • No account, no sign-up, no email • No ads, no tracking, no social feed • One-tap export to plain JSON The anti-trap rule, baked in: keep the system stupid simple. Fancy dashboards are procrastination wearing a productivity costume. Internal, internal, external. Are my bets right? Are my hours on the right bets? Can the world find my bets? Ten minutes a day. Start your first prediction. SUBSCRIPTION DETAILS - Auto-renewable subscription available through In-App Purchase - Removes ads and unlocks all premium features - Subscription charged to iTunes account at confirmation of purchase - Automatically renews unless auto-renew is turned off at least 24 hours before current period ends - Manage subscriptions and turn off auto-renewal in iTunes Account Settings after purchase - No cancellation of current subscription during active period EULA : https://www.apple.com/legal/internet-services/itunes/dev/stdeula/