Definition
On-Device AI
Model inference that runs locally on your phone instead of sending data to a cloud server. Savva supports airplane mode verification so users can confirm queries never leave the device.
From the episode “The Truth About Lying to Your Doctor”Hear it on the podcast1 episode
Learn the language of AI-native founders
Every week: the new terms, tools, and workflows founders are using, straight from the podcast.
Related terms in AI Fundamentals
Non-deterministic outputAI that can return different answers to the same input. A dealbreaker for fields like finance and accounting that need identical, repeatable results every time.Non-Deterministic SoftwareSoftware whose outputs cannot be precisely predicted from a given set of inputs. Unlike deterministic programs (if X then always Y), AI systems produce probabilistic outputs that may vary given identical inputs — because they generate based on statistical patterns rather than explicit rules. The core challenge for AI deployment in high-stakes, safety-critical, and regulated applications: you can estimate what an AI agent will do, but you can't lock it in the way traditional software guarantees outputs. More advanced models become less deterministic over time, not more.NondeterministicAI that can produce different outputs for the same input, which is exactly why it is kept away from final claim decisions.OCR (Optical Character Recognition)Technology that converts images of text, including handwritten annotations, into machine-readable text. Critical for legal work, where documents often include handwritten notes and stamped modifications.Open sourceSoftware whose source code is freely available for anyone to view, use, modify, and share.Open source / open weightsModels you can download, run, and keep, with no provider able to revoke access.Open source modelsAn AI model whose weights, code, and details of its training data are released so anyone can run, inspect, modify, and build on it.Open weights and open source modelsModels whose parameters are published, so anyone can run and fine-tune them in their own environment.