> ## Documentation Index
> Fetch the complete documentation index at: https://icrl.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Preference Learning Demo

> ICRL adapts to user styles — terse expert vs detailed learner vs executive summary

## Overview

The preference learning demo shows ICRL's ability to learn and adapt to individual user preferences, communication styles, and working patterns over time. Vanilla LLMs treat every user the same; ICRL can match verbosity, format, depth, and tone to each user's past approved interactions.

## The Problem

Every user has different preferences:

* **Verbosity**: Some want detailed explanations, others want terse commands
* **Format**: Some prefer bullet points, others want prose
* **Depth**: Some want "just tell me what to do", others want "explain why"
* **Tone**: Some prefer formal, others casual

Vanilla LLMs treat every user the same. You end up repeatedly saying *"Be more concise"* or *"Give me the command, not the explanation"*.

## How ICRL Solves This

ICRL stores successful interactions that reflect your preferences. Over time:

1. **Learns your style** from past interactions you approved
2. **Retrieves preference-matched examples** for similar requests
3. **Adapts responses automatically** without re-prompting

## Demo Structure

<Tree>
  <Tree.Folder name="examples/preference_learning_demo" defaultOpen>
    <Tree.File name="README.md" />

    <Tree.File name="setup_demo.py" />

    <Tree.File name="run_demo.py" />

    <Tree.Folder name="user_profiles" defaultOpen>
      <Tree.File name="expert_terse.json" />

      <Tree.File name="learner_detailed.json" />

      <Tree.File name="manager_summary.json" />
    </Tree.Folder>

    <Tree.Folder name="scenarios" defaultOpen>
      <Tree.File name="seed_interactions.json" />

      <Tree.File name="test_requests.json" />
    </Tree.Folder>
  </Tree.Folder>
</Tree>

## User Profiles

| Profile              | Style                 | Wants                               | Example                                          |
| -------------------- | --------------------- | ----------------------------------- | ------------------------------------------------ |
| **Expert Terse**     | Minimal explanation   | Commands, code snippets             | "How do I rebase?" yields `git rebase -i HEAD~3` |
| **Learner Detailed** | Thorough explanations | Why things work, pitfalls, examples | Full explanation with diagrams                   |
| **Manager Summary**  | High-level overview   | Impact, timeline, risks, decisions  | "Rebasing reorganizes commit history..."         |

## Running the Demo

From the project root:

```bash theme={null}
cd examples/preference_learning_demo

# 1. Setup — seeds trajectories for each user profile
uv run python setup_demo.py

# 2. Run the comparison test
uv run python run_demo.py

# 3. View detailed evaluation
uv run python evaluate_responses.py
```

## Expected Results

| User Profile     | ICRL Score | Vanilla Score | Improvement |
| ---------------- | ---------- | ------------- | ----------- |
| Expert Terse     | \~90%      | \~40%         | +50%        |
| Learner Detailed | \~85%      | \~50%         | +35%        |
| Manager Summary  | \~85%      | \~30%         | +55%        |

## Prerequisites

* `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` set
* `uv run` from project root, or `python` with `PYTHONPATH` including `src/`

## Key Insight

This demo proves ICRL's value for **personalization** where:

* One size doesn't fit all
* User preferences are implicit in past interactions
* The same question should have different "right" answers for different users