---
title: Recommendations
description: AI-powered product recommendations to increase engagement and sales.
slug: recommendations
docKind: hub
hub: recommendations
---

Luigi's Box Recommendations is a powerful system designed to increase user engagement and sales by displaying relevant products. It utilizes AI-powered models trained on product catalog data and user behavior to deliver personalized and contextually appropriate suggestions. The models are trained on a per-customer basis to meet specific business goals, such as recommending complementary accessories or alternative items.

Luigi's Box offers several integration paths. For a fast frontend implementation, [Recco.js](/recommendations/recco-js/) gives you a complete widget. For full flexibility, [Recommender API](/recommendations/api/) lets you build the UI yourself. For scheduled offline scenarios, [Batch Publisher](/recommendations/batch-publisher/) generates recommendation batches for large user sets.

## Choose your integration path

<div class="choice-container">
  <a class="choice-card" href="/recommendations/recco-js/">
    <span class="choice-badge" data-recommended="true">Recommended for web</span>
    <h3>Recco.js</h3>
    <p>A frontend JavaScript library for recommendation widgets with built-in rendering, analytics, and storefront-friendly behavior.</p>
    <ul class="advantages-list">
      <li>Fastest way to ship recommendation widgets.</li>
      <li>Supports templates and carousel-like layouts.</li>
      <li>Handles the common storefront flow for you.</li>
    </ul>
  </a>
  <a class="choice-card" href="/recommendations/api/">
    <span class="choice-badge">Custom build</span>
    <h3>Recommender API</h3>
    <p>A flexible endpoint for teams that want to control rendering, request batching, and the surrounding business logic.</p>
    <ul class="advantages-list">
      <li>Full control over the recommendation experience.</li>
      <li>Fits custom storefronts and backend-driven flows.</li>
      <li>Supports contextual filtering and batching.</li>
    </ul>
  </a>
</div>

## Start here

<div class="lb-overview-links">
  <p>
    <strong>Still deciding which recommender to show?</strong>
    Start with <a href="/quickstart/recommendations/choosing-models/">Choosing recommendation models</a>.
  </p>
  <p>
    <strong>Want the fastest storefront widget?</strong>
    Continue with <a href="/quickstart/recommendations/integrating-reccojs/">Integrating Recco.js</a>.
  </p>
  <p>
    <strong>Need a custom widget or backend flow?</strong>
    Continue with <a href="/quickstart/recommendations/building-custom/">Building custom recommendations with the Recommender API</a>.
  </p>
</div>

## Core concepts

- [**Recommendation models:**](/recommendations/models/) The AI component that drives recommendations. Models can be content-based (using product data) or behavioral (observing user interactions like frequently bought together).
- [**Personalization:**](/recommendations/concepts/) By providing a `user_id` in the request, the model uses the user's profile to tailor results.
- [**Batching:**](/recommendations/concepts/) When displaying several recommenders on a single page, batch all requests into a single API call for better performance and automatic deduplication.
- [**Batch publishing:**](/recommendations/batch-publisher/) For offline scenarios like newsletters, generate personalized recommendation batches on a schedule.