foundation-models

1# Foundation Models
2 
3Integrate Apple's on-device LLM into your apps for privacy-preserving AI features. Companion references: **safety-and-guardrails.md** (model limits, prompt design, the four-layer safety stack), **models-and-agents.md** (Private Cloud Compute, `LanguageModel` protocol, vision input, `DynamicProfile` agentic sessions — the iOS 27 wave), and **utilities-package.md** (Apple's open-source utilities package: OpenAI-compatible endpoints, just-in-time Skills, history compression).
4 
5## When This Skill Activates
6 
7- User wants AI text generation features
8- User needs structured data from natural language
9- User asks about prompting or LLM integration
10- User wants to implement AI assistants or agentic features (tool loops, multi-profile sessions)
11- User needs content summarization or extraction
12- User asks about Private Cloud Compute, guardrails, or model safety
13 
14## Model Fit — Check Before Building
15 
16The on-device model is ~3B parameters (2-bit quantized): built for **summarization, extraction, classification, tagging, revision, short chat** — not math, code generation, facts, or world knowledge (WWDC25 248). For capability boundaries, prompt-design rules, and the safety stack, read `safety-and-guardrails.md` first. For anything bigger, `PrivateCloudComputeLanguageModel` (32k context, reasoning) and third-party backends are in `models-and-agents.md`.
17 
18## Quick Start
19 
20### 1. Check Availability
21 
22```swift
23import FoundationModels
24 
25struct IntelligentView: View {
26…