Apr 14
Loading video player...
AI observability tools monitor metrics like uptime, latency and costs. But they don’t tell you enough about the quality of agentic outputs or how to take action to improve results. HumanSignal gives you a state-of-the-art interface for applying structured evaluation data to agentic traces from tools like Braintrust, LangChain,, Langsmith and more. In this video you’ll learn: What features are included in the HumanSignal labeling interfaces for agentic traces How to tag issues by category: Accuracy & Faithfulness, Tool & Retrieval, Reasoning & Planning, Response Quality, and Safety & Compliance How to annotate traces with severity levels and pass / fail states Where to find the templates and tutorials so you can get started in minutes Who this is for: AI/ML engineers and teams building LLM-powered agents who need a scalable, structured process for quality evaluation workflows. Quick start: docs.humansignal.com/tutorials