--- title: "AI agents for education: 11 real examples" canonical: "https://agenticfeats.com/roles/education/" receipts: 11 shown: 6 page: 1 pages: 1 --- > From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt # AI agents for education: 11 real examples Agentic Feats lists 11 sourced examples of AI agents in education work; 6 link the artifact; most common agent: Claude Code (3). Newest first. ## Feats, newest first - [Gatsby lesson plan spreadsheet](https://agenticfeats.com/c/gatsby-lesson-plan-spreadsheet-claude-computer-use.md) (Claude computer use; Claim; 2026-10-13): Claude with Computer Use downloaded The Great Gatsby, researched lesson plans and standards, and filled a spreadsheet on its own. Result: Ethan Mollick received a finished Gatsby lesson plan spreadsheet for high schoolers with no obvious errors, after delegating and walking away. - [Compiling a course list](https://agenticfeats.com/c/compiling-a-course-list-operator.md) (Operator; Claim; 2026-10-13): OpenAI's Operator browsed the author's online course site and compiled a list of courses with fees and descriptions while they got coffee. Result: Operator returned the requested list of courses, fees and descriptions without further input, saving the author a few minutes of manual admin work. - [NSF project summary drafting](https://agenticfeats.com/c/nsf-project-summary-drafting-cursor.md) (Cursor; Claim; 2026-10-13): 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. - [School financials from ProPublica](https://agenticfeats.com/c/school-financials-from-propublica-operator.md) (Operator; Numbers; 2026-10-13): Operator searched ProPublica Nonprofit Explorer for independent schools and logged their financial data into a Google Sheet; o1 then built a dashboard. Result: Operator collected data for about 25 of 100 schools before the author stopped it; o1 then built a working chart dashboard from that data. - [Synthetic AGI attitudes survey study](https://agenticfeats.com/c/synthetic-agi-attitudes-survey-study-manus.md) (Manus; Shown; 2026-10-13): 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. - [Canvas LMS tool via MCP](https://agenticfeats.com/c/canvas-lms-tool-via-mcp-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude Code co-developed a Canvas LMS MCP server with an educator who is not a developer, covering courses, grading, analytics, and student data anonymization. Result: A roughly 3,000-line open-source Canvas tool built in four months. It cut a 45-minute weekly student check to a 2-minute conversation with Claude. - [Interactive course website from prompts](https://agenticfeats.com/c/interactive-course-website-from-prompts-manus.md) (Manus; Shown; 2026-10-13): Manus AI built a full AI-business course from one prompt, deployed it as a live website, then added quizzes, games, and embedded videos. Result: Three prompts produced a live interactive course website with modules, quizzes, and videos; the author also reports a 318-page ebook from further prompts. - [UNESCO education data spreadsheet](https://agenticfeats.com/c/unesco-education-data-spreadsheet-chatgpt-agent.md) (ChatGPT agent; Shown; 2026-10-13): 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. - [Annotated bibliography on big data](https://agenticfeats.com/c/annotated-bibliography-on-big-data-chatgpt-agent.md) (ChatGPT agent; Shown; 2026-10-13): ChatGPT Agent searched academic databases, filtered peer-reviewed open-access papers, and compiled an annotated bibliography on big data in education and healthcare decision-making. Result: It produced a review-ready draft with citations and a gaps synthesis in under ten minutes, versus half a day by hand. - [Course modernization with agent fleets](https://agenticfeats.com/c/course-modernization-with-agent-fleets-claude-code.md) (Claude Code; Shown; 2026-10-13): Claude Code turned course evaluations into tracked GitHub issues, then ran agents to rebuild assignments, exams and about two dozen slide decks. Result: Roughly two dozen decks were rebuilt into Quarto reveal.js with speaker notes and refresh checklists, and the approach was reused for two more courses. - [Research workflow with Claude Code](https://agenticfeats.com/c/research-workflow-with-claude-code.md) (Claude Code; Claim; 2026-10-13): Claude Code with MCP servers handles literature search, Zotero notes, Gmail alert newsletters, and codebase questions for a hydrology researcher. Result: The author reports faster literature search, Zotero notes written automatically, and accurate answers about the ATS hydrology codebase through a custom ats-mcp server.