skills.rest
delta-and-beta
delta-and-betaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

strategist-recommendations

Design and deploy personalized item recommendation strategies for Braze campaigns and Canvases.

Updated Apr 6, 2026
Search Tags:#personalization#recommendations#catalogs#braze#connected-content#fallback-strategy#amazon-personalize
One-click install
npx skills add https://github.com/delta-and-beta/braze-agency --skill strategist-recommendations
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: strategist-recommendations
Source: https://github.com/delta-and-beta/braze-agency/tree/main/skills/strategist-recommendations
Command: npx skills add https://github.com/delta-and-beta/braze-agency --skill strategist-recommendations

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill helps teams choose, design, and operationalize personalized item recommendation strategies for Braze campaigns and Canvases, resolving uncertainty about when to use rules-based logic, Braze-native AI recommendations, or third-party engines and how to integrate them reliably into messaging workflows.

Core Features & Use Cases

  • Strategic decision framework: compares rules-based Liquid recommendations, Braze AI Item Recommendations, and external ML services to match approach to catalog shape, signal volume, and editorial constraints.
  • Integration patterns: documents Connected Content, Catalogs, and API-driven storage patterns for external recommendation outputs (e.g., Amazon Personalize, Dynamic Yield, Certona, Movable Ink, FullStory).
  • Operational guidance: training timelines, fallback planning, analytics to monitor precision and coverage, and testing patterns for post-action discovery, cross-sell/up-sell, and re-engagement flows.
  • Real-world example: how to wire an AI recommendation to a post-viewing in-app Canvas using a linked catalog, event mappings, Liquid templating, and a most-popular fallback when user history is insufficient.

Quick Start

Ask the strategist-recommendations skill to recommend an approach for a catalog-backed e-commerce campaign, including fallback logic, training timeline considerations, and which integration pattern to use.

Frequently Asked Questions about strategist-recommendations

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up personalized item recommendations in Braze campaigns?▼

Personalized item recommendations in Braze are deployed by linking a catalog, selecting a recommendation logic, mapping events to profiles, and applying Liquid templating to surface items dynamically within email, in-app, or Canvas messaging flows.

How does Connected Content work with Amazon Personalize for Braze recommendations?▼

Connected Content integrates external recommendation engines by calling an API endpoint from Braze, fetching personalized item IDs from Amazon Personalize or similar services, and rendering them via Liquid templating against a linked Braze catalog.

What's the best fallback strategy for Braze AI Item Recommendations?▼

A robust fallback strategy uses most-popular or editorially curated items when user history is insufficient, ensuring messaging coverage is maintained even when the personalization model lacks enough behavioral signal for a specific profile.

Do I need a Braze catalog for AI Item Recommendations?▼

Yes, a linked Braze catalog is required to associate item metadata with recommendation outputs, enabling Liquid templating to render item details like titles, images, and prices dynamically within the message body.

How long does it take to train Braze AI Item Recommendations models?▼

Training timelines for Braze AI Item Recommendations depend on catalog size and signal volume, requiring sufficient user interaction data before the model can generate accurate personalized item suggestions for campaign deployment.

Related Skills

Explore More Marketing & Sales Skills→
delta-and-betadelta-and-beta

engineer-user-data

Design and enforce Braze user data collection and lifecycle workflows.

Community
Advanced
gorgiasgorgias
2

shopping-assistant-performance

Analyze Shopping Assistant revenue, conversion, and recommendation metrics from Gorgias MCP data.

Official
Intermediate
delta-and-betadelta-and-beta

strategist-personalization

Orchestrate Braze personalization with Liquid templating, Connected Content, and promotion codes.

Community
Advanced
delta-and-betadelta-and-beta

strategist-dynamic-content

Design dynamic content personalization strategies for Braze campaigns.

Community
Intermediate