Teaching a 9B model to investigate production alerts
Learn how we fine-tuned Qwen3.5-9B into a specialized agent for change attribution that achieved 87% of GLM-5.3’s Recall@5 roughly 5% of the investigation cost.
Blog
Learn how we fine-tuned Qwen3.5-9B into a specialized agent for change attribution that achieved 87% of GLM-5.3’s Recall@5 roughly 5% of the investigation cost.
Learn how Datadog built Mambark, a small state-space model that scores every security event and enables heavier AI agents to investigate only the events that matter.
Datadog has acquired Adaptive ML, a platform for building, owning, and deploying specialized AI agents and models.