We are building the first collaborative & open-source Quality Testing platform for AI models.
We help organizations increase the efficiency of their AI development workflow, eliminate risks of AI biases and ensure robust, reliable & ethical AI models.
We help organizations increase the efficiency of their AI development workflow, eliminate risks of AI biases and ensure robust, reliable & ethical AI models.
Location: France, Ile-de-France, Paris
Employees: 1-10
Total raised: $1.59M
Founded date: 2021
Investors 1
| Date | Name | Website |
| 23.01.2023 | Elaia Part... | elaia.com |
Funding Rounds 1
| Date | Series | Amount | Investors |
| 15.12.2022 | - | $1.59M | - |
Mentions in press and media 14
| Date | Title | Description |
| 16.03.2026 | OpenClaw can bypass your EDR, DLP and IAM without triggering a single alert | An attacker embeds a single instruction inside a forwarded email. An OpenClaw agent summarizes that email as part of a normal task. The hidden instruction tells the agent to forward credentials to an external endpoint. The agent complies — ... |
| 24.02.2026 | How to test OpenClaw without giving an autonomous agent shell access to your corporate laptop | Your developers are already running OpenClaw at home. Censys tracked the open-source AI agent from roughly 1,000 instances to over 21,000 publicly exposed deployments in under a week. Bitdefender’s GravityZone telemetry, drawn specifically ... |
| 10.05.2025 | The Tightrope of AI Responses: Balancing Brevity and Accuracy | In the world of artificial intelligence, brevity is a double-edged sword. Recent findings from Giskard, a Paris-based AI testing firm, reveal a troubling trend: asking AI for short answers can lead to a cascade of inaccuracies. This phenome... |
| 09.05.2025 | Why Asking AI for Short Answers Could be a Big Mistake | Ask an AI a question, and it will give you an answer, even if it has to make one up. That’s the warning from a new AI benchmark, which has discovered that some of the most popular LLMs around can be prone to giving confident, but entirely i... |
| 10.12.2024 | The Rise of AI Companions: Transforming Data Workflows and 3D Modeling | In the world of technology, change is the only constant. Recently, two significant innovations have emerged, reshaping how we interact with data and 3D modeling. KNIME's K-AI and Microsoft's Trellis are at the forefront of this transformati... |
| 09.12.2024 | KNIME Releases AI Companion to Drive Smarter Collaboration with AI | KNIME, the open source data analytics and AI company, is announcing the launch of its AI companion – K-AI – to all users. With K-AI, users can co-create powerful data workflows with AI. K-AI will answer questions, make recommendations, and ... |
| 07.11.2024 | Оценка LLM: комплексные оценщики и фреймворки оценки | В этой статье подробно описываются сложные статистические и предметно-ориентированные оценщики, которые можно использовать для оценки производительности крупных языковых моделей. В ней также рассматриваются наиболее широко используемые фрей... |
| 14.11.2023 | Giskard’s open-source framework evaluates AI models before they’re pushed into production | Giskard is a French startup working on an open-source testing framework for large language models. It can alert developers of risks of biases, security holes and a model’s ability to generate harmful or toxic content. While there’s a lot of... |
| 09.11.2023 | There’s something going on with AI startups in France | Last night, Motier Ventures held a tech meetup focused on AI startups featuring some of the most hyped tech startups in the French tech ecosystem: Dust, Finegrain, Gladia, Mistral AI and Scenario — all of them are portfolio companies of Mot... |
| 04.08.2023 | Тотальное доминирование с AI. Стратегия, инструменты | Генеративный ИИ и ChatGPT вывели дискуссии об искусственном интеллекте на новый уровень, привлекая внимание как предпринимателей, так и глав государств. Лидеры бизнеса и топ-менеджмент должны быть в курсе трендов и отслеживать сферы примене... |
Show more