Agentic AI and Automation Cybersecurity and Penetration Testing Service

The agency is seeking an agentic artificial intelligence and automation cybersecurity and penetration testing service to strengthen its defensive cybersecurity posture. Traditional cybersecurity approaches rely heavily on manual processes and struggle to scale against an evolving threat landscape, expanding attack surfaces, and AI-enabled adversaries. To solve this persistent shortage of skilled cybersecurity personnel, the agency requires a collaborative, multi-agent framework that mimics the workflow of a human cybersecurity team to execute complex, multi-step tasks autonomously. The scope of work covers a team of specialized AI agents configured with specific tools, knowledge, and roles to execute complex cybersecurity workflows. These workflows must include vulnerability research, which involves conducting deep-dive analysis on specific vulnerabilities using Retrieval Augmented Generation against a corpus of Common Vulnerabilities and Exposures, Common Platform Enumerations, and technical documentation. The agents must also perform cyber analysis by interpreting raw data from scans and tests to identify and prioritize defensive actions and vulnerabilities using vulnerability databases and threat intelligence feeds. Eligible bidders must be onshore organizations based solely in the United States. The agency requires the selected vendor to perform all work offsite. The agency is currently looking for proposals to determine the budget and has not disclosed specific evaluation criteria or key dates in the initial request.