Generative AI Agents for Instructional Co-design: A Sequential Agent-Based Approach Using a Low-Code/No-Code Platform

doi:10.1007/978-3-031-98281-1_25

Generative AI Agents for Instructional Co-design: A Sequential Agent-Based Approach Using a Low-Code/No-Code Platform

2026-01-01

0

PRE

AI

Ioannis Hatzilygeroudis

K

Konstantinos Siozopoulos

DOI：10.1007/978-3-031-98281-1_25

Original

Original request for help

Save

Abstract

En 中文

This paper explores how a Low-Code/No-Code (LCNC) platform can be used by non-technical users, such as educators, to design and deploy a Sequential Agent-Based Generative AI System to facilitate instructional design. The system deploys an LLM-based sequential workflow of AI agents to support educators in the first three stages of the ADDIE instructional design model: Analysis, Design, and Development. It follows a co-design, Human-In-The-Loop (HITL) approach, where AI agents guide instructional designers on needs analysis, content validation and generation, while allowing user intervention. The system also explores the role of self-checking agents for fact-checking, bias detection, and instructional quality review, based on specific prompts. However, the identified potential remains theoretical, requiring empirical validation through user testing to assess usability, effectiveness, and adoption by non-IT users.

Keywords:

Generative AI

AI Agents

Low-Code/No-Code

Instructional Design

Citizen Development

Human-In-The-Loop

AI in Education

Flowise

LangChain

LangGraph

Fact-checking

Bias detection

Generative AI Agents for Instructional Co-design: A Sequential Agent-Based Approach Using a Low-Code/No-Code Platform

Abstract

Journal

Organization