FingerCAD vs Ari Helper

"FingerCAD" is the first CAD application for technical drawing with fingers assisted by computer for portable devices. With "FingerCAD" you can draw houses, bridges, planimetry of apartments, mechanical components, geometrical figures, everything that can be designed with a common PC CAD. Useful for the engineers on construction site, for architects, surveyors, designers, students etc.. The design possibilities with "FingerCAD" are endless and all this using only your portable device, during a travel or comfortably seated or standing at work. The ease of use makes it very useful and versatile. The final design can be saved using standard formats (ex. DXF) and can be sent via e-mail or printed. The zoom and pan, the customization of the drawing, the common cad tools, autosaving and the ability to continue operations even in subsequent sessions of use (at boot "FingerCAD" will load automatically the design saved in the previous session of use), possibility to add measurements and free text makes it truly unique. Each CAD object is treated as a separate object; You can then go back in time by removing the objects from last to first (also in next sessions of work), select and remove the undesired parts / incorrect objects. The "automatic acquisition of nearest vertices" facilitates the drawing of adjacent graphics objects and the function "2x" allows you to draw walls (double line) automatically (you can specify the thickness of the wall as desired). The three RGB components, alpha transparency, the freehand drawing, the ability to fill an object with colors, the color palette, the color picker, in addition to the common functions of a CAD give you the ability to add manual graphical effects at the overall design (also using freehand drawing). MODIFY, COPY AND MOVE for CAD objects (also from one layer to another one). AUTOMATIC CALCULATION OF THE MEASUREMENT OF THE AREA OF A GENERIC POLYGONAL 3D SURFACE. Virtual Reality Exploration: you can walk in the 3D model and observe it using first person view (Finger3D + FingerCAD). HIGH PRECISION OF DRAWING: using the “under finger dynamic drawing preview “ you can see exactly where for example the initial / final point of a line will be placed (observing the preview window that shows the area of drawing not visible under the finger). AUTO-PAN for work area: if you reach the border of the screen, FingerCAD shifts automatically the work area so you can continue to draw longest lines - you have not to use the "zoom out" to draw long lines. .OBJ 2D and 3D export routine: export the CAD design for 3D modeling softwares such as Finger3D, Blender, Maya 3D, etc... or print it using 3D printers DXF export/import for AutoCad, qCad, SolidWorks, LibreCAD, ... PDF export. File formats conversions: - from DXF to OBJ - from DXF to PDF - from DXF to IMAGE (JPG,PNG) 3D models can be displayed directly using the "FingerCAD 3D VIEWER". DROPBOX / iCloud Drive file sharing (IN and OUT) Ability to import DXF files from a WEB LINK and/or from an EMAIL ATTACHMENT. Ability to PRINT the design (using AirPrint). Other features: - CAD (computer assisted design) - Walls with adjustable thickness - Snap to control points - Free text - UNDO/REDO for the graphics objects, from last to first - Selection and ability to transform/move/delete selected objects - Autosave - Grid - Snap to grid - Adjustable grid - Labels indicating the finger position on the cad area - Many selectable unit of measurement - Design multi-layer and multi-floor - The selected objects can be moved or copied from one layer to another layer or from a floor to another floor - Preview of other layers in the current layer - Scale and rotate - Extend - Trim - Mirror - Send with an email the generated .dxf, .obj, .pdf files - Ability to share .dxf, .obj, .pdf with other installed apps - DXF part library (architecture, communication, electrical, electronics, mechanical, misc, processing, templates, zipf_libs)

Introducing Ari - Your Easy-to-Use AI Assistant! Meet Ari, your personal AI assistant, right on your device! Ari runs its models on the device itself, so it works entirely offline — no internet connection required. Your privacy is our priority – Ari doesn't collect any of your personal data. Start Ari anywhere with Siri and App Intents — just say "Ask Ari," speak your question, and hear the answer back. Power users get a full Shortcuts catalog: Ask Ari with any model (Apple Intelligence, local, or cloud), start chats, generate and edit images, analyze PDFs, speak replies, change settings, queue Code Session tasks on Mac, and dispatch prompts to other devices — all chainable in Shortcuts. Ari is on your wrist too: the Apple Watch app remote-controls Ari on iPhone. Dictate from the "Ask Ari" complication or Smart Stack, watch answers stream in, hear them spoken, and hand long replies to iPhone. Questions queue when the phone is away; private chats stay off the watch. Conversations show up in Spotlight — including by what's in their images. Ari reads text and objects in chat pictures on-device so you can search for "that screenshot with the receipt". Private media is never indexed. With Sensitive Content Warning on, flagged images blur behind "Show Anyway" (verified adults can opt out). More to love: Text-to-Speech (device voice or Ava); long-press to copy or retry across models; syntax highlighting with one-tap code copy; Previous Chats synced via iCloud. On Apple Intelligence (iOS 26 / macOS 26 and later), Ari uses the on-device foundation model by default — private, no API key, no network. Attach images: on iOS 27 and macOS 27 the model sees them directly; on OS 26 Ari describes them on-device with the Vision framework (text, tables, barcodes, subjects). Prefer full vision models? Pick one from the menu. Download on-device models with a tap — Google's Gemma 4 for chat, Stable Diffusion converted for Core ML for pictures — or import a model folder of your own. Self-host with Ollama or any OpenAI-compatible server (LM Studio, vLLM, llama.cpp, LiteLLM), or generate images with Draw Things over gRPC. New in Ari 7: Ari makes pictures and films, and repairs the ones you already have. Films is a studio — write a film as a list of shots, render them one at a time, keep the ones that work, and watch the cut come together in a player above the timeline. Pictures get a canvas editor: brush over a crease and heal it, paint a leash or a stranger out of the frame, or treat the whole photograph — repair, denoise, sharpen camera shake, colorize, upscale four times. Every restoration model runs on your device and downloads on first use rather than shipping in the app. Point the camera at something and ask about it. Look at Something sends the frame to whichever model you have selected — on-device, self-hosted or cloud — captions the answer under the picture and speaks it if you like. Talk to it and it listens, answers, then listens again. It sits beside the microphone, and goes on the Lock Screen, Control Center, the Action Button or Siri. Cloud providers with your own keys: OpenAI (GPT-6 and GPT-5 families plus GPT Image), xAI Grok (4.7 plus Grok Imagine), Anthropic Claude, Google Gemini (plus Nano Banana and Omni video), and AWS Bedrock. Image-capable models accept photos; import text and source files. Cloud use reminds you each provider's privacy policy applies. On Mac, open a Code Session on a project folder with Grok for agentic tools — read, edit, search, git, shell, browser, web, and MCP — so Ari's GUI agent matches a terminal coding agent. Note: For strongest privacy with iCloud sync, enable Advanced Data Protection. Without it, conversations stay limited to your iCloud account but are not fully end-to-end encrypted. Optionally powered by Gemma 4 (HuggingFace) for offline chat and image understanding. Download Ari and keep your AI assistant at your fingertips!