Giskard
Safety & Evaluation
Overview
Giskard is an AI testing and LLM security platform that provides automated vulnerability scanning, red teaming, and guardrails for AI models. It helps organizations identify and mitigate security risks in LLM applications through automated testing that simulates adversarial attacks, detects prompt injection vulnerabilities, and evaluates model robustness. The platform offers Giskard Guards for production deployment, continuous monitoring of model behavior, and compliance reporting to help teams ensure their AI systems are safe and compliant.
- Pricing model
- Free
- Deployment
- SaaS (vendor-hosted), Self-hosted / on-premises, API / SDK
- Regions served
- Global
- Categories
- Language (LLM / NLP), Free, Model evaluation, Software & technology, Safety & Evaluation, API / SDK, Self-hosted / on-premises, AI & agent security, MLOps & model tooling, Predictive / classical ML, Freemium, SaaS (vendor-hosted), Agentic / autonomous, Enterprise / custom quote
- Last updated
- 2 October 2026
- Published
- 2 October 2026
Use cases
Deployment options
Data sources & provenance
Where this information came from, how it was checked and when it was last looked at. “Last updated” records a change to the record — it does not mean the record was verified.
- Data quality
- Data quality: Editorially Reviewed
- Primary source
- giskard.ai
- Sources cited
- 2
- Last reviewed
- 27 September 2026
- Last updated
- 2 October 2026
Spotted something out of date?
Anyone can suggest a correction — you don't need an account. An editor checks every suggestion against the sources before the record changes.