---
title: "Feedback to a better local model"
lesson_id: "01"
---

# Feedback to a better local model

- **Lesson ID:** 01
- **Goal:** Draw the feedback to synthetic data to LoRA to Core AI loop. Separate Foundation Models from Core AI. Deny hot-swap LoRA.
- **Human lesson:** [01-the-loop.html](01-the-loop.html)

## Prerequisites

- Comfort with on-device Apple AI names, and the writing-style LoRA course if possible.

## Inputs, outputs, and artifacts

- **Inputs:** Product feedback.
- **Outputs:** The four-step loop.
- **Artifacts:** Progressive `.flow` diagrams.

## Agent build steps

1. Grow the loop one box at a time.
2. Separate Foundation Models from Core AI.
3. State there is no documented hot-swap LoRA.
4. Link the writing-style LoRA course and the names course.

## Constraints

Keep the language simple, friendly, and literal. iOS 27 and macOS 27 only. No quizzes, Mermaid, or em dashes. Do not invent API names. Mark sketches as sketches and tell the reader to confirm them in the Xcode 27 SDK.

## Key concepts

- Users show where the feature fails. That signal can improve the next shipped model.
- The path is signal, synthetic data, LoRA, merge, `coreai.llm.export`, `.aimodel`.
- There is no documented hot-swap LoRA on Core AI.
- Feedback improves the next baked file, not the live system model.

## Takeaways

- Do not fine-tune Apple's system model in this course.
- A better adapter is a new bake plus a new app release.
- Keep Foundation Models and Core AI as separate products in your design.

## Acceptance checks

- All four loop steps are named.
- Hot-swap LoRA is denied.
- Sibling links, progressive `.flow` diagrams, and an Agent brief link are present.
- [ ] Proceed to [lesson 02 brief](02-collect-signals.llms.md).