Work

Ample: A Multi-Agent AI Tool for Rich, Curriculum-Aligned Essay Feedback

Year: 2025

Type: article

Abstract: Ample is an innovative AI-powered essay feedback tool currently in development, designed to support students’ writing through rich, personalised, curriculum-aligned feedback. Ample uses a multi-agent architecture, with agentic Retrieval-Augmented Generation (RAG) to evaluate essays against mark schemes, assessment objectives, exemplar feedback, and syllabus content. The presentation outlines some of the design choices and challenges in developing Ample, as well as discussing how to ensure that it is calibrated against real teacher feedback.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.17290246

Author: Balderson, Simon

Language: English

Topic: Artificial Intelligence in Education

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: green

OpenAlex ID: W7084912243

FWCI:

Cites:

Cited by:

Related to: