Insights
Quick Learnings on AI Safety
Category
Testing Before Trusting: The Red-Teaming Process Behind aprendIA's Safe Deployment
aprendIA: AI-Powered Support for Teachers in Resource-Constrained Settings
Dungeons & Dragons Character Sheets for AI Evaluators: Building AI Evaluators That Know Why a Response is Good
Beyond Awareness: How Personalized Information Empowers Refugees to Recognize Exploitation and Seek Help
Conserving Token Usage and Reducing AI Inference Costs in Production
A Practical Approach to Humanitarian AI Safeguarding and Guardrails
Behind the Scenes: Orchestrating AI for Humanitarian Response
Executive Summary: Signpost AI Information Assistant Pilot Project
Training AI for Trust: Insights from Cuéntanos El Salvador's Chatbot Journey
[BtB | PO Diary] Reflections from A Protection Officer
New Year, New Horizons: Signpost AI’s Vision for 2025
Transparency and Accountability in AI: A Panel Discussion
Gratitude and Innovation: AI for Humanitarian Aid
AI with a Human Touch: The Power of Human-in-the-Loop
Beyond the Code: Our Protection Team’s Commitment to Transparency
Signpost AI Chat Pilot: Using the AI Tool
Signpost AI Chat Pilot: A Roadmap
Top Prompting Rules for a Humanitarian Chatbot
[BtB | PO Diary] Wk 6: Building Trust & Managing Expectations