Operations | Monitoring | ITSM | DevOps | Cloud

Using a drag-and-drop interface, engineering teams can create apps that support troubleshooting, improve day-to-day operations, and offer self-service access without leaving Datadog. With the new conversational AI feature, teams can turn an idea into a working app in seconds. Watch the video to see how it works..

Welcome to the AI research bites. This series of short and informative talks showcases cutting-edge research work from ServiceNow AI Research team. The AI Research Bites are open to all, especially those interested in keeping up with the fast-paced AI research community.

From our webinar: Scaling Autonomous Operations with Agentic AI Learn why manual service desks don’t scale and how autonomy actually works.

Jacky Leybman from PagerDuty and Kaninie Knight from Slack share how their integration streamlines incident response and real-time collaboration. This session highlights practical workflows and measurable gains – such as faster triage and lower MTTR – achieved by connecting on-call operations directly in Slack.

On this episode of Masters of Data, we unpack David's new white paper on AI governance for agentic systems. He explains model context protocol (MCP) as "APIs for agents", how AI systems talk and execute tasks. The catch? Autonomous agents are insider threats that move fast and cause serious damage. David introduces the Model Control Plane (MoCop), a twelve-pillar framework designed to prevent your AI from going rogue. We cover his roadmap for security leaders to build real controls and telemetry. His advice: treat agents like interns with root access. Get ahead of this before your agents do.

Autonomous operations are already here. Ask a question in Slack, and RITA resolves it instantly using your internal knowledge. No ticket. No waiting. That’s agentic AI.

In this demo, we use Kentik AI Advisor to troubleshoot a real-world BGP misconfiguration that brings down a peering session with a transit provider. You’ll see how AI Advisor works both as a dedicated page and as an in-portal overlay, using natural language to identify the affected interface, correlate SNMP and syslog data, and pinpoint a maximum-prefix issue as the root cause. Then we accelerate and standardize the workflow with custom network context and AI-powered runbooks, so every engineer can troubleshoot BGP alerts like an expert.