Project Case Study
Projects
Multi-Agent AI · CybersecurityCompleted
NestAI
An award-winning secure-code analysis CLI where adversarial Red and Blue AI agents evaluate software, a controller verifies findings, and the system generates a consolidated security report. Placed second out of 32 teams.
Overview
NestAI is a secure-code analysis CLI built for a KSU AI Club hackathon. It uses adversarial agents to challenge and verify security findings before reporting them.
Problem
Security reviews often produce disconnected findings without a consistent way to challenge, verify, and prioritize them.
Architecture
- 01
Source input
- 02
Red Agent
- 03
Blue Agent
- 04
Controller verification
- 05
HTML security report
What I Built
- Orchestrated three specialized AI agents for offensive analysis, defensive review, and finding verification
- Generated consolidated HTML security reports with severity-ranked findings and risk scoring
- Placed second out of 32 teams in the KSU AI Club hackathon
Technical Challenges
Multiple agents can repeat, contradict, or overstate findings unless evidence is normalized before prioritization.
Stack
PythonMulti-Agent SystemsOpenAI APISecurity AnalysisCLI
Validation / Testing
- Agent-output schema checks
- Finding deduplication review
- Report generation checks
Current Status
Completed
Completed