---
title: "UNESCO education data spreadsheet"
canonical: "https://agenticfeats.com/c/unesco-education-data-spreadsheet-chatgpt-agent/"
agents: ["ChatGPT agent"]
evidence_grade: "A"
outcome: "partial"
job_type: "Research"
roles: ["Education"]
source_url: "https://datacamp.com/tutorial/chatgpt-agent"
evidence_url: "https://chatgpt.com/s/6880dcdff5b08191b3736d97abd1056f"
source_date: "2025-07-24"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# UNESCO education data spreadsheet

ChatGPT Agent pulled UNESCO student-teacher ratio and teaching staff data and built a multi-tab spreadsheet in a single 14-minute run.

Result: The Agent worked for 14 minutes on the UNESCO task; the author tested it against o3-pro and ran four other work-style tasks.

## How it was set up

ChatGPT Agent on a paid plan, using its virtual computer with browser, terminal, code execution, and file system.

## Worth knowing

The author reports weaker results on the image collage and Lego parts tasks, which needed manual fixes or only partly worked.

## Prompt

```text
Pull the latest data from [data source] on [metric] for [groups]. Build a spreadsheet with one tab per [group], listing [columns]. Add a summary tab with the best and worst [metric] values, sorted. Keep [naming field] consistent across tabs.
```

## Evidence note

Tutorial with screenshots and a shared ChatGPT conversation link; text excerpt cuts off before outputs.

## Sources

- Original: https://datacamp.com/tutorial/chatgpt-agent
- Evidence: https://chatgpt.com/s/6880dcdff5b08191b3736d97abd1056f

## The receipt

- Agent: ChatGPT agent
- Evidence: Shown (grade A, artifact linked)
- Outcome: Partial
- Job type: Research
- Roles: Education
- Source: Blog
- Published: 2025-07-24
- Added: 2026-10-13