---
title: "NSF project summary drafting"
canonical: "https://agenticfeats.com/c/nsf-project-summary-drafting-cursor/"
agents: ["Cursor"]
evidence_grade: "C"
outcome: "partial"
job_type: "Research"
industry: "Universities"
roles: ["Education"]
source_url: "https://forum.cursor.com/t/anyone-use-cursor-for-academic-research-writing/57393"
source_date: "2025-02-28"
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

# NSF project summary drafting

The author used Cursor in Agent mode with Claude 3.7 Sonnet and two rules files to draft an NSF Project Summary from two papers.

Result: The draft was usable but weaker than accepted NSF summaries; thinking mode helped, though it began hallucinating and misreading the sources.

## How it was set up

Cursor Agent mode, claude-3.7-sonnet, one rules file for NSF requirements, one for academic writing, section markdown files, and a reference folder with two papers as text.

## Worth knowing

The writing rule was not reliably picked up unless @-mentioned. Thinking mode was needed, and the output still needed heavy critique.

## Evidence note

Author's forum post describing the experiment; screenshot of the folder setup only

## Sources

- Original: https://forum.cursor.com/t/anyone-use-cursor-for-academic-research-writing/57393

## The receipt

- Agent: Cursor
- Evidence: Claim (grade C, claim only)
- Outcome: Partial
- Job type: Research
- Industry: Universities
- Roles: Education
- Source: Blog
- Published: 2025-02-28
- Added: 2026-10-13