---
title: "Synthetic AGI attitudes survey study"
canonical: "https://agenticfeats.com/c/synthetic-agi-attitudes-survey-study-manus/"
agents: ["Manus"]
evidence_grade: "A"
outcome: "completed"
job_type: "Research"
industry: "Universities"
roles: ["Education"]
source_url: "https://futureofbeinghuman.com/p/when-agentic-ai-takes-charge-manus"
evidence_url: "https://github.com/2020science/manus-synth-agi-survey-03-19-2025"
source_date: "2025-03-22"
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

# Synthetic AGI attitudes survey study

Manus planned a survey study on student attitudes to AGI, wrote a Google Apps Script for the form, simulated 1,000 students, and analyzed the data.

Result: From one short prompt, Manus produced a publishable-style report with charts from 1,000 synthetic responses. The data is made up.

## How it was set up

Manus agent with a central task-master, sub-agents and its own virtual computer. It built a to-do list and chose to write a Google Apps Script instead of driving Google Forms.

## Worth knowing

It refused to submit fake responses to the real form on ethics grounds. All data is synthetic.

## Prompt

```text
I want to create a Google Form script for a research survey of [population] about [topic]. Mix Likert and open-ended questions, capture demographics. Then simulate [N] respondents, analyze the data, and write a publishable report. This is a proof of concept.
```

## Evidence note

Author's blog with report excerpts, charts, form link and GitHub repo of files

## Sources

- Original: https://futureofbeinghuman.com/p/when-agentic-ai-takes-charge-manus
- Evidence: https://github.com/2020science/manus-synth-agi-survey-03-19-2025

## The receipt

- Agent: Manus
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Research
- Industry: Universities
- Roles: Education
- Source: Blog
- Published: 2025-03-22
- Added: 2026-10-13