Tool
Datadog is a cloud monitoring and observability platform for collecting and analyzing metrics, traces, logs, and related data across infrastructure, applications, networks, containers, databases, and cloud environments. It provides infrastructure monitoring, application performance monitoring, log management, dashboards, alerting, incident management, security monitoring, synthetic monitoring, and user-experience monitoring. The platform is used to identify broken or correlated systems and investigate operational issues, although the video notes that observability alone does not necessarily establish root cause. Datadog also offers AI features, including investigation, remediation, agent observability, and an MCP server.
14 uses taken from transcripts — each links to the moment in the video.
Used as an observability tool to identify broken or correlated systems, but not necessarily determine root cause.
The company providing observability and monitoring products discussed in the talk.
Used to inspect logs and search for the root cause of a production bug.
Provided usage data and telemetry through an MCP server so Claude could identify the highest-impact user journeys.
Downstream observability target the gateway telemetry can be exported to
Downstream data source the investigation agent can consult for extra evidence
The observability backend demonstrated in the workshop, where OpenTelemetry traces of agent behavior — inputs, outputs, system prompts, tool calls, and costs — are inspectable down to individual user interactions.
Incident and monitoring event source for triggering agents; also the example of least-privilege failure when a code review agent co-located on a VM gains access to it.
The observability platform whose bills Grepr's customers want to cut — cited in a sales story where a 90% saving on the Datadog bill was the thing buyers immediately wanted.
Production monitoring watched by a dedicated agent during agentic deployments to detect regressions and trigger reverts.
Skill to pull application metrics, logs and APM traces into the reviewer agent's context
Observability platform where LLM-generated, self-improving monitors are created
Alerts and logs associated with issues during triage investigation
Observability platform cited as where cost dashboards were built but ignored
15 in the library.