General Analysis
Early-stage but with a striking, independently observable proof point (its adversarial agent extracted $10M+ in fabricated perks from 50 live customer-service AI agents); one of the more concretely demonstrated AI red-teaming claims reviewed.
Visit Website ↗ + Add to CompareInnovation Matrix Assessment
Raised $10M seed (announced 2026-04-29) led by Altos Ventures with 645 Ventures, Menlo Ventures, and Y Combinator participating.
Already engaged with enterprise customers in support and finance whose products serve hundreds of millions of users, per the company.
Seed round closed 2026-04-29 with a well-known multi-stage investor syndicate for an AI-agent-security specialist.
Positions agentic-AI red-teaming and interpretability as a distinct discipline from conventional AppSec/pentesting tooling.
The reported live exploit of 50 customer-service AI agents (extracting $10M+ in fabricated perks in minutes) is a concrete, if company-reported, demonstration of real capability.
Agentic AI deployment is accelerating rapidly across enterprises, making adversarial testing of AI agents an increasingly urgent CISO concern.
Why CISOs Should Care
General Analysis provides adversarial evaluation and defensive tooling -- run-time guardrails, red-teaming frameworks, interpretability, and observability -- to help enterprises find and fix failure modes in agentic AI systems before attackers do.
What Makes It Different
Treats securing AI agents as a distinct technical discipline from traditional cybersecurity, built by AI researchers (ex-Cohere, NVIDIA, Harvard AI safety, Caltech ML) rather than a security team bolting AI features onto legacy tooling.
The Matrix Verdict
52/100 — INCREMENTAL INNOVATOR
Early-stage but with a striking, independently observable proof point (its adversarial agent extracted $10M+ in fabricated perks from 50 live customer-service AI agents); one of the more concretely demonstrated AI red-teaming claims reviewed.
Editorial Note: Claims vs. Verified Findings
Seed funding and founder background verified via BusinessWire and citybiz. The $10M live customer-service-agent exploit demo is a company-reported case study, not an independently audited figure.
Sources
Alternatives to General Analysis
Adaptive Security
AI-driven platform that simulates deepfake, voice, and multichannel social-engineering attacks to train and test organizations against next-generation phishing.
Quilr
Early-stage agentic AI security startup building a 'Service-as-Software' platform to guard against human-related breaches and secure AI agent…
Zenity
Governance and security platform for AI agents and low-code/no-code development, securing agent identity, permissions and behavior across the…
Tenzai
An agentic AI penetration testing startup building autonomous 'AI hackers' to find and validate exploitable vulnerabilities at a…
Reco
Reco secures the "agentic ecosystem" — mapping what AI agents can access across SaaS and enterprise apps, detecting…
Charm Security
Agentic AI workforce that investigates and intervenes on scams and fraud in real time, reading manipulation and intent…