Skip to main content
Back to challenges
Challenge

Build an AI-Powered YouTube Recommendation Filter

Develop a generative AI agent that analyzes YouTube video recommendations using Claude Sonnet 4 and filters out distracting pop-ups based on user preferences. The agent will leverage LangGraph for workflow management, employing a graph-based approach to track user feedback and refine filtering criteria. Implement an adaptive thinking budget to optimize resource allocation and handle varying levels of user input complexity.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

This challenge involves building a Claude Sonnet 4-powered agent with LangGraph for intelligent YouTube recommendation filtering.

Delivery guide

How work is evaluated

Evaluation

Evaluation will focus on the accuracy of the filter, efficiency of resource usage, and user-friendliness of the interface.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Learning goals

What you should walk away with

  • Develop a LangGraph workflow for processing YouTube recommendation data.

  • Implement an adaptive thinking budget to optimize resource usage.

  • Implement a Claude Sonnet 4-based agent for analyzing recommendation pop-ups.

  • Integrate user feedback to refine filtering criteria.

Resources and assets

Reference links and supporting material

Dataset notes

Sample data for 1 tasks

Challenge setup

Evaluation will focus on the accuracy of the filter, efficiency of resource usage, and user-friendliness of the interface.

Challenge input

A list of YouTube recommendation pop-ups (textual representation).

Agent execution

No agent tool is listed for this challenge.

Evaluated output

A filtered list of recommendations, with distracting pop-ups removed.

Evaluation checks
  • No evaluation checks are configured.
Configured evaluation evidence
  • Accuracy target: 0.9
Configured runtime
  • Python execution harness

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

No tool records are attached.

Evaluation contract

  • No evaluation checks are configured.

Metrics

  • Accuracy ยท Target 0.9

Workflow tasks

  1. Task 1

    Input: A list of YouTube recommendation pop-ups (textual representation).

    Output: A filtered list of recommendations, with distracting pop-ups removed.

    Execution harness: Python

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build an AI-Powered YouTube Recommendation Filter