AgentBnB: A Browser-Based Cybersecurity Tabletop Exercise with Large Language Model Support and Retrieval-Aligned Scaffolding

TL;DR

AgentBnB is a browser-based cybersecurity tabletop exercise platform that leverages large language models and retrieval-augmented scaffolding to provide scalable, on-demand, and cognitively targeted training for cybersecurity professionals.

Contribution

It introduces a novel, scalable, browser-based TTX system integrating LLM teammates with retrieval-augmented hints, enhancing traditional exercises with AI support and scaffolding.

Findings

Participants preferred the agent-based version over physical decks.

The system is viewed as more scalable and repeatable.

Early results show potential despite small sample size and scope.

Abstract

Traditional cybersecurity tabletop exercises (TTXs) provide valuable training but are often scripted, resource-intensive, and difficult to scale. We introduce AgentBnB, a browser-based re-imagining of the Backdoors & Breaches game that integrates large language model teammates with a Bloom-aligned, retrieval-augmented copilot (C2D2). The system expands a curated corpus into factual, conceptual, procedural, and metacognitive snippets, delivering on-demand, cognitively targeted hints. Prompt-engineered agents employ a scaffolding ladder that gradually fades as learner confidence grows. In a solo-player pilot with four graduate students, participants reported greater intention to use the agent-based version compared to the physical card deck and viewed it as more scalable, though a ceiling effect emerged on a simple knowledge quiz. Despite limitations of small sample size, single-player focus, and narrow corpus, these early findings suggest that large language model augmented TTXs can provide lightweight, repeatable practice without the logistical burden of traditional exercises. Planned extensions include multi-player modes, telemetry-driven coaching, and comparative studies with larger cohorts.