WorkflowFor DevelopersMachine Learning & AI Engineering

Recommendation System Builder.

When building a personalisation feature that must work even for new users with no history.

ChatGPT Β· Claude Β· GeminiΒ·AdvancedΒ·~1950 tokens
Curated by the AIPP team
Last updated 14 May 2026 Β· v3
recommendation-system-builder-4.md Β· 1950 words
You are a senior {{role}} brought in to help a developer or tech professional complete a {{use_case}} task.

# Context
- Pack: Developers & Tech Professionals
- Category: Machine Learning & AI Engineering
- Use case: Recommendation System Builder
- Source task:
  - Build a recommendation system for {{describe_what_is_being_recommended_products_content_users_to_fol}}. Data available: {{describe_user_interaction_data_item_features_user_features}}.
  - Step 1: algorithm selection (collaborative filtering, content-based, hybrid : recommend and justify).
  - Step 2: implementation code for candidate generation and ranking stages.
  - Step 3: offline evaluation (MAP@K, NDCG, coverage, diversity).
  - Step 4: online evaluation design (CTR, conversion rate A/B test).
  - Step 5: cold start strategy for new users and new items.

# Goal
Algorithm recommendation, candidate generation and ranking code, offline and online evaluation design, and cold start strategy.

# Constraints
- Treat this as a sequential workflow where each step builds on the previous step.
- Keep every step clearly labeled and easy to run separately if needed.
- Avoid generic filler, vague advice, and unsupported claims.
- Make the output specific, practical, and ready to use.

# Output
Algorithm recommendation, candidate generation and ranking code, offline and online evaluation design, and cold start strategy.

The variables to fill in

PlaceholderWhat to put thereExample
{{role}}Rolerecommendation systems engineer
{{use_case}}Your specific valuerecommendation system builder
{{describe_what_is_being_recommended_products_content_users_to_fol}}Describe what is being recommended products content users to folproducts
{{describe_user_interaction_data_item_features_user_features}}Describe user interaction data item features user featuresITEM FEATURES

How to customize this prompt

  1. Replace each {{double-curly}} with your real context.
  2. Adjust the constraints section to match your tone β€” formal, casual, blunt.
  3. If the engagement is recurring, change the duration line to mention milestones rather than days.
  4. Run it in your tool of choice. The output should be ready to paste with at most one small edit.

When to use

When building a personalisation feature that must work even for new users with no history.

PRO TIP

Two-stage retrieval (fast candidate generation + slower re-ranking) is the standard architecture for production recommendation systems at any meaningful scale.

Related prompts

Structured

Technical Problem Debugger

Debug this problem systematically. Identify the root cause, explain why it is happening, provide the fix, and explain how to prevent it in future.

Structured

System Design Advisor

Design the high-level architecture for this system. Cover components, data flow, scaling strategy, and key design decisions.

Structured

No-Code Tool Selector

Recommend the best no-code or low-code tool stack for the stated goal, with implementation guidance.

Structured

Data Analysis Prompt

Design the complete analysis approach for the stated question. Include the analytical method, the steps to execute it, and the format for presenting findings.

β˜… THIS PROMPT IS IN A PACK

The Developer Toolkit Pack

250 technical prompts for code review, documentation, architecture planning, debugging, test writing, API design, and career growth β€” built by developers for developers.

Browse more prompts β†’