dt-obs-problems

DAVIS problem analysis including root cause identification, impact assessment, and correlation with other telemetry. Use when querying or investigating detected problems. Trigger: "active problems", "root cause analysis", "problem impact", "affected users", "list problems", "P-12345 details", "recurring problems", "problem history", "problem trending", "blast radius", "which entity caused the problem", "problems affecting Kubernetes", "problems by service". Do NOT use for explaining existing que

120stars26forksUpdated 8/13/2026

Developer Tools #dynatrace #incident-response #root-cause-analysis #observability #dql

Security Assessment

Safe(95/100)

Security Score95/100

About dt-obs-problems

The dt-obs-problems skill guides an agent through analyzing Dynatrace Davis AI-detected problems — automatically correlated health and resilience issues that aggregate related alert, warning, and info-level events and expose root-cause and impact insights. It solves the problem of investigating incidents in Dynatrace by codifying the correct fields, status values, and DQL query patterns for triaging active problems, finding root causes, and spotting recurring issues.

The skill covers three main use cases: active problem triage (listing and prioritizing open problems by category and user impact), root-cause investigation (identifying the root-cause entity and blast radius for a specific display ID like P-12345678), and problem trending (analyzing frequency, recurring root causes, and resolution times over time). It documents event kinds and categories (AVAILABILITY, ERROR, SLOWDOWN, RESOURCE, CUSTOM), the problem lifecycle (ACTIVE to CLOSED), and a table of common field-name mistakes with the correct event.* field names. Reference files add detailed correlation patterns — joining problems with logs, Davis events, and deployment events using smartscape.affected_entity.ids, timeline analysis around problem start times, and cross-problem entity analysis — along with impact analysis, problem merging, and trending guides.

It targets SREs, incident responders, and observability engineers who investigate Dynatrace-detected problems. Typical uses include triaging what is broken right now, tracing a problem back to its causing entity, correlating a problem with the error logs and deployments that surround it, and identifying entities that appear across multiple problems. It is read-only DQL analysis guidance.

FAQ

What are Dynatrace problems?

Automatically detected software and infrastructure health issues that correlate related alert, warning, and info-level events across services, infrastructure, frontend apps, and user sessions, identify root causes via Smartscape dependency analysis, and assess business impact by tracking affected users and services.

How do I look up a specific problem?

Query fetch dt.davis.problems and filter on display_id (e.g. display_id == "P-12345678"), then read fields such as smartscape.affected_entity.ids, root_cause_entity_id, and dt.davis.event_ids.

What are the most common field-name mistakes?

Using title instead of event.name, status instead of event.status, severity instead of event.category, and start instead of event.start. The skill provides a correction table and the valid status values ACTIVE and CLOSED.

Can it correlate a problem with logs or deployments?

Yes. Reference patterns use smartscape.affected_entity.ids (and classic affected_entity_ids) in subqueries to fetch error logs from impacted entities, retrieve underlying Davis events, and check whether a problem correlates with a recent DEPLOYMENT event within a time window.

When should I not use this skill?

It is not for explaining existing queries, product documentation questions, generic log searching, distributed tracing, or host-level resource monitoring.