#Guardrails
6 articles with this tag
AI Agents Don't Always Follow Rules
Talha Sheikh from Checkout.com discusses the unreliability of AI coding agents and the critical need for verification layers and guardrails to ensure dependable AI outputs.
Claude's Corner: Salus (YC W2026), The Bouncer Your AI Agents Desperately Need
AI agents are confidently doing the wrong thing at scale. Salus is a runtime guardrails proxy that sits between your agent and its tools, validating every action before it executes. Here's what they built, how it works, and whether you could clone it.
IBM's Tejas Kumar on 'AI Harnesses'
IBM's Tejas Kumar explains the concept of AI harnesses, detailing their types (Eval and Agent) and key components like tools, models, context management, and guardrails.
Context-Aware AI Safety Tested
New research from Mozilla evaluates how context-aware AI safety guardrails perform across different languages and domains, particularly in humanitarian use cases.
Testing AI Guardrails Across Languages
Researchers tested context-aware AI guardrails across English and Farsi in humanitarian scenarios, finding nuanced performance differences and highlighting the need for language-specific safety evaluations.
Multilingual LLM Guardrails Tested
Researchers tested how LLM guardrails perform across languages and policy phrasings, revealing significant variations that impact AI safety assessments.