- Home
- LLM Evaluation Tools
- Giskard
Giskard
Europe
What it is
Giskard is a platform for finding vulnerabilities in AI agents before they reach production. Its listed coverage includes prompt injection, data disclosure, inappropriate content, hallucinations, contradictions and omissions. After an assessment, it provides a structured report with a deploy-or-fix verdict, ranked vulnerabilities and functional scenarios; passing agents can receive a Giskard Label. The Hub tests conversational text-to-text agents that are reachable through an API endpoint using a black-box approach. Giskard describes a remediation process in which its team qualifies findings, discusses severity, prioritizes issues, opens tickets in the customer’s workflow and reruns tests to check fixes. The Enterprise plan lists more than 50 automated adversarial probes, evaluation datasets and RAG quality metrics, plus human review interfaces. It also lists on-premise, private cloud and SaaS deployment. Giskard states that it offers EU or US data residency, encryption and access controls, and lists GDPR, SOC 2 Type II and HIPAA compliance. The free plan includes a local open-source library, basic vulnerability scanning, basic RAG evaluation and community support.
For and against
For
- Assessment reports include a deploy-or-fix verdict and ranked vulnerabilities.
- Hub supports black-box testing through an API endpoint.
- Enterprise lists more than 50 adversarial probes.
- Enterprise includes human review interfaces.
- Free plan includes local deployment and community support.
Against
- Hub supports conversational text-to-text agents accessible through an API endpoint.
- The free plan's vulnerability scan is described as basic.
- Free-plan maintenance is best-effort.
The verdict
Giskard combines agent assessments with structured findings and a stated remediation workflow. The free plan provides a starting set of scans and evaluations, while broader evaluation and support features are listed for Enterprise.
Who it suits
It suits teams assessing conversational AI agents for safety and quality issues before production. Enterprise features are aimed at organizations seeking expanded evaluations, deployment choices and dedicated support.
Plans and prices
Open-source
Local Python deployment · 7 security-risk categories · 5 quality-generation scenarios · code-only reporting
Read 21 Oct 2026 · giskard.ai
Free
Open-source library · Local deployment · Basic LLM vulnerability scan using adversarial techniques from 2024 · Basic RAG evaluation report using correctness metrics
Read 3 Oct 2026 · giskard.ai
Professional
Agent auditing · 50+ adversarial probes · customizable evaluations · human review
Read 21 Oct 2026 · giskard.ai
Enterprise
For production LLM deployments · AI agent security red-teaming · AI agent quality evaluation · Integrations and collaboration
Read 3 Oct 2026 · giskard.ai
On the record
- API and SDK
- Giskard publishes an official Python SDK for the Giskard Hub API in its public GitHub organization.github.com · read 21 Oct 2026
- Assessment report
- After an assessment, Giskard provides a structured report with a deploy-or-fix verdict, ranked vulnerabilities, functional scenarios, and a Giskard Label if the agent passes.giskard.ai · read 3 Oct 2026
- Behavioral checks
- The Python library provides pytest-native scenarios and checks that can be written in Python or natural-language rules judged by an LLM.docs.giskard.ai · read 21 Oct 2026
- Black-box operation
- The Hub tests an agent without requiring knowledge of its internal components or access to end-user production data.giskard.ai · read 21 Oct 2026
- Collaboration
- Hub includes shared workspaces, annotation workflows, role-based access control, dataset versioning and configurable alerting.docs.giskard.ai · read 21 Oct 2026
- Company
- Giskard says it was founded in Europe in 2021 by co-founders with experience building AI systems at Dataiku and Thales.giskard.ai · read 3 Oct 2026
- Company founding
- LinkedIn lists the company as founded in 2021 and headquartered in Paris.linkedin.com · read 21 Oct 2026
- Company size
- LinkedIn lists Giskard as privately held with 11–50 employees.linkedin.com · read 21 Oct 2026
- Compliance
- The site states end-to-end encryption at rest and in transit and lists GDPR, SOC 2 Type II, and HIPAA compliance.giskard.ai · read 3 Oct 2026
- Custom evaluations
- Professional includes domain-specific dataset generation, fine-grained RAG metrics, customizable checks and interoperability with other evaluation platforms.giskard.ai · read 21 Oct 2026
- Deployment
- The Enterprise plan lists on-premise, private cloud, and SaaS deployment options, and the FAQ says its team can help install Hub on-premise for sensitive workloads.giskard.ai · read 3 Oct 2026
- Documentation depth
- Documentation includes installation, checks, scans, API references, migration guidance, examples, a glossary and community Discord support.docs.giskard.ai · read 21 Oct 2026
- Enterprise probes
- The Professional offering lists more than 50 automated adversarial probes, including multi-turn attacks.giskard.ai · read 21 Oct 2026
- Enterprise security controls
- The Enterprise plan lists SSO, role-based access controls, versioning with audit trails, and scheduled email alerts.giskard.ai · read 3 Oct 2026
- Evaluation features
- The Enterprise plan lists domain-specific evaluation dataset generation, fine-grained RAG quality metrics, customizable metrics, and human-in-the-loop review interfaces.giskard.ai · read 3 Oct 2026
- Funding
- Giskard says it raised a €1.5 million 2022 round led by Elaia with Bessemer and angel participation, followed by a €3 million European Commission investment in 2023.giskard.ai · read 21 Oct 2026
- Hub coverage
- Giskard Hub supports text-processing agents including RAG chatbots and JSON-based agent workflows through an API endpoint.giskard.ai · read 21 Oct 2026
- Human review
- Professional provides collaborative human-in-the-loop review interfaces for evaluation results.giskard.ai · read 21 Oct 2026
