Analyzes GenAI observability signals from customer applications using DQL.
npx skills add https://github.com/mf-dynatrace/dt-mcp-workspace --skill dt-obs-genai
Please help me install this Agent Skill. Skill: dt-obs-genai Source: https://github.com/mf-dynatrace/dt-mcp-workspace/tree/main/skills/dt-obs-genai Command: npx skills add https://github.com/mf-dynatrace/dt-mcp-workspace --skill dt-obs-genai
This Skill provides in-depth analysis of AI Observability signals from customer GenAI applications, using DQL to identify and address issues with golden signals, LLM signals, token and cost analytics, agent signals, conversation analytics, guardrails, and evaluation quality.
Use the dt-obs-genai skill to analyze the token usage by model for the last 24 hours.
High-intent search queries and answers about installing and using this skill.
To analyze GenAI observability signals for token consumption and cost spikes, you can use DQL to read OpenTelemetry GenAI spans and LLM evaluation bizevents. This identifies highest-spend model-provider combinations and estimates costs based on token usage.
Monitoring LLM performance and provider latency with DQL involves analyzing LLM signals from GenAI applications. It tracks model performance, provider latency, and token consumption to help identify bottlenecks in your LLM operations.
Tracking agent signals like tool usage and step latency in GenAI applications requires analyzing observability data with DQL. It detects failing agents, loop or runaway conditions, and maps Smartscape topology for your agents.
Yes, you can use DQL to monitor guardrails and safety evaluations for LLM responses. It analyzes observability signals to track blocked and truncated responses, content filtering, and overall safety evaluations.
Yes, GenAI observability analysis requires OpenTelemetry GenAI spans and LLM evaluation bizevents. The Skill reads these observability signals using DQL to identify golden signals, agent signals, and evaluation quality metrics.
To assess conversation analytics and cost per conversation for GenAI apps, analyze observability signals with DQL. It evaluates conversation sessions, calculates session error rates, and determines the cost per conversation.
henrikrexedIntegrate OpenTelemetry with Dynatrace using DQL queries and dashboard-as-code.
Cure-Consulting-GroupManage LLM operations with prompt versioning, evaluation pipelines, cost controls, guardrails, and RAG monitoring.
mqzkimVisualize execution flows, replay sessions, and detect loops in AI agent debugging.
Arize-aiCapture AI application traces, evaluations, and prompts with OpenTelemetry.
