Large language models (LLMs) now power customer support chatbots, internal developer assistants, and code-generation tools. These systems generate mountains of unstructured telemetry like prompts, responses, tool calls, and routing metadata where safety failures often hide in plain sight. The core challenge is not a lack of data, but a lack of structure: safety signals are […] The post Monitoring LLM Safety with BERTopic: Clustering Failure Modes for Actionable Insights appeared first on IEEE Computer Society.