My Role
Founder, security product designer, and full-stack engineer
All Projects
Live productFlagship case study
Aegis Intelligence
Autonomous AI PenTesting Assistant
Penetration-testing evidence arrives as disconnected scans and notes, making it difficult to explain which weaknesses form a credible attack path.
Interactive preview
Full demoWhat I Built
Autonomous AI-powered penetration testing assistant that converts raw reconnaissance data into structured, actionable threat intelligence in real time. Ingests outputs from Nmap and Gobuster, performs live OSINT enrichment, and automatically maps potential vulnerabilities, misconfigurations, and attack paths.
Evidence
Working interface, documented system behavior, and implementation-level decisions.
Technical Architecture
From system input to explainable output.
The control gate is shown as a first-class stage, not an afterthought added around the workflow.
Technical Decisions
- Built an autonomous assistant that ingests raw Nmap and Gobuster output and converts it into structured, prioritised threat intelligence in real time.
- Parsed scanner output into a normalised host, port, service, and version model, so downstream reasoning works on data rather than on text.
- Built the React and TypeScript interface around an engagement workflow: scope, findings, evidence, and remediation, in the order a report is written.
Security Considerations
- Built an autonomous assistant that ingests raw Nmap and Gobuster output and converts it into structured, prioritised threat intelligence in real time.
- Mapped findings to likely attack paths, chaining a misconfiguration or outdated service into the next step an attacker would take.
- Built the React and TypeScript interface around an engagement workflow: scope, findings, evidence, and remediation, in the order a report is written.
Outcome & Evidence
- Ranked findings by exploitability and blast radius rather than raw CVSS, so the report leads with what actually matters in this environment.
Generative AIOSINTCybersecurityReactTypeScript
Working product
Try the interactive demo.
The product experience is part of this case study. Explore it here, reset its state, or switch viewport sizes without leaving the project page.
aegis-intelligence.zainkhalilkhan.com
This is the actual deployed application, embedded live from aegisintelligence.org. If it doesn't load below (some browsers block third-party embeds), open it directly.
Loading live application...
Client-side sandbox. State is in memory and nothing is sent to a server.
Next Case Study