Jill Watson prompt-engineering personalization module integrated with the RAG pipeline

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description

A modular personalization component for the Jill Watson virtual teaching assistant that encodes learner attributes in an engineered prompt conditioning the underlying LLM at runtime. The article states it is "integrated with Jill Watson's retrieval-augmented generation (RAG) pipeline and course-specific knowledge base, allowing personalization to modify the form and presentation of responses while preserving grounding in retrieved instructional content." It enables "scalable personalization without modifying or retraining the underlying LLM" and is designed for integration into the deployed Jill Watson architecture.

Design Implications

Context

Requirements

• Learner preferences must be updatable through the Jill Watson interface and incorporated into prompts at runtime
• A course-specific knowledge base and RAG pipeline must supply the shared instructional content

Constraints

• The module personalizes response form and presentation, not the retrieved content itself
• Deployment integration is targeted for Spring 2027 with a Georgia Tech pilot in Summer 2027

Target Learners

• students in courses using the Jill Watson AI teaching assistant across institutions

Learning Goals

• course-grounded question answering tailored to individual learner preferences and question complexity

Claims

• Prompt Personalization Measurable Response Variation [+M]
• Semantic Grounding With Surface Variation [+M]

Related Designs

Examples

-

Key Sources

• Saptarshi Basu, Sandeep Kakar, Ashok Goel. (2026). A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching Assistant. https://arxiv.org/abs/2609.03402

Page metadata

Field	Value
type	design
id	jill-watson-prompt-personalization-module
title	Jill Watson prompt-engineering personalization module integrated with the RAG pipeline
description	A modular personalization component for the Jill Watson virtual teaching assistant that encodes learner attributes in an engineered prompt conditioning the underlying LLM at runtime.
status	review
generated	by process:settle-candidates on 2026-10-11
trust	unverified — no one has confirmed this page's content
sources	1 — saptarshi-basu-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.