Casco Launches: Agentic Red Teaming for AI agents and Apps

Casco recently launched!

‍

^{"Casco validates security, safety, and accuracy of AI apps and agents."}

‍

^{TL;DR: Casco prevents AI agents and apps from messing up by evaluating them for security, safety, and accuracy.}

‍

https://youtu.be/SWPnB-GADdE

‍

Founded by Rene Brandel & Ian Saultz

As founding members of the Generative AI team at AWS (Lead Engineer + Security, Head of Product), they witnessed the evolving landscape of AI agents and applications. They identified emerging security gaps as traditional security practices struggled to keep pace with this new paradigm.

Recognizing the critical need to secure AI systems, they decided to build Casco. Their mission is to empower builders to innovate confidently, knowing their AI systems are secure.

‍

The Problem

Companies building AI agents and apps face a disproportionate amount of cybersecurity threats that put their business at risk. 73% of enterprises experienced at least one AI-related security incident (that they know of) in the past 12 months, with the average incident cost amounting to $4.8m. It takes 40% longer for companies to identify and address these AI-related incidents.

Existing solutions do not work for these companies:

1. Automated scans yield low-quality, noisy security findings.
2. Thorough security evaluations are cost-prohibitive to most companies.
3. New AI attack vectors are emerging faster than companies can adapt.

‍

Their Solution: Casco’s supervised, agentic red-teaming

Casco proactively uncovers critical vulnerabilities before attackers do. Here’s how:

1. Sophisticated, AI-Driven Attack Simulation: Casco uses advanced techniques, just like an expert human red teamer, to devise and execute multi-step attacks against your AI agents and apps.
2. Human-Validated Expertise: The AI evaluations are supervised and validated by their team, ensuring high-fidelity findings. They have built and secured AI systems, applications, and cloud infrastructure at AWS, Microsoft, and the US government.
3. Actionable, Compliance-Ready Reports: Casco provides comprehensive reports with reproduction steps, risk explanations, and remediation guidance, aiding compliance with SOC 2, NIST AI RMF, EU AI Act, and ISO 27001.

‍

Learn More

‍

^{🌐 Visit casco.com to learn more.}

^‍

^{🤝  Is your AI agent or app secure? Book a Demo to secure your AI systems}

^‍

^{👣 Follow Casco on LinkedIn & X.}

‍