Attention: You are using an outdated browser, device or you do not have the latest version of JavaScript downloaded and so this website may not work as expected. Please download the latest software or switch device to avoid further issues.
| 23 Jul 2025 | |
| Community News |
UNESCO has released a Red Teaming Playbook developed in partnership with Dr. Rumman Chowdhury and Humane Intelligence. Designed for policymakers, educators, civil society groups, and organisations, the Playbook offers a hands-on guide to testing generative AI models for bias, stereotypes, and potential harm - especially those that may enable technology-facilitated gender-based violence (TFGBV).
Grounded in a real Red Teaming exercise held at UNESCO, the resource empowers communities to explore AI risks in a safe, structured way. By actively uncovering vulnerabilities in AI systems, users play a vital role in shaping more ethical, inclusive, and accountable technology.
Whether you're an educator, advocate, or developer, this Playbook is a tool to support AI for social good, putting safety, inclusion, and transparency first reports UNESCO.
Download UNESCO's Red Teaming Artificial intelligence for social good - The PLAYBOOK here
