Back to evaluations
Public evaluation

Forecasting Task

The evaluation checks the agent's ability to generate valid forecasting code and execute it in E2B to produce a growth report.

Evaluation type
task based
Challenge
TikTok Shop Growth Strategist with OpenAI Agents SDK and E2B
Difficulty
Intermediate
Rigor
Unspecified
Open linked challenge

Evaluation overview

How the linked challenge is judged: tasks, benchmarks, and criteria count.

Tasks
1
Benchmarks
0
Criteria
0

Task templates

Inputs and expected outputs.

Task 1

Forecasting Task

Agent must write and execute code to calculate Q1 growth from raw sales data

Input format

CSV of sales data for TikTok Shop

Output format

Percentage growth figure and prediction graph