Security

Case Study

Case Study: 12-Person Startup Cuts PR Cycle Time with AI Review

How a seed-stage team added an AI code reviewer on every PR — blocking security patterns, surfacing nits, without replacing human approval.

Interview

How do you defend a production LLM application against prompt injection attacks?

Tests whether you treat LLM security as layered engineering, not a single prompt trick.

Interview

Design a gateway that screens LLM traffic for prompt injection and unsafe tool use.

Tests security architecture for AI platforms — increasingly required for enterprise AI gateways.

Directory

Abnormal AI

Behavioral AI email security platform that detects phishing, business email compromise, and account takeover from anomalous activity.

Directory

CrowdStrike Charlotte AI

Generative AI analyst for the CrowdStrike Falcon platform, answering security questions and automating detection triage and response.

Directory

Darktrace

Self-learning AI security platform that models normal network behavior to detect and autonomously respond to novel cyber threats.

Directory

Dropzone AI

AI SOC analyst that autonomously investigates security alerts end to end, producing decision-ready reports for human review.

Directory

Guardrails AI

Open-source Python framework that validates LLM inputs and outputs using a hub of reusable validators.

Directory

HiddenLayer

Security platform for AI systems that detects adversarial attacks, scans models for tampering, and protects deployed ML assets.

Directory

Lakera

AI security platform guarding LLM applications against prompt injection and data leakage; makers of the Gandalf game.

Directory

NeMo Guardrails

NVIDIA's open-source toolkit for adding programmable safety rails to LLM conversational systems using Colang.

Directory

Private AI

Toronto company that detects and redacts PII in text, audio, images, and documents so sensitive data stays out of LLMs.

Directory

Prompt Security

Enterprise platform securing GenAI use with prompt injection defense, data leak prevention, and shadow AI visibility.

Directory

Protect AI

AI security platform for model scanning, LLM red teaming, and runtime guardrails; acquired by Palo Alto Networks.

Directory

SentinelOne Purple AI

AI security analyst in the SentinelOne Singularity platform that translates natural-language questions into threat hunts and triage.

Directory

Snyk

Developer security platform using DeepCode AI to find and auto-fix vulnerabilities in code, dependencies, containers, and IaC.

Directory

Vectra AI

AI-driven detection and response platform that finds attacker behavior across network, identity, and cloud with prioritized signals.