agent-observability-session-classify

Official

Classify session satisfaction in Datadog Agent Observability traces.

Authordatadog-labs
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill analyzes Datadog Agent Observability traces to classify whether a user's intent was satisfied, providing insights into the effectiveness of AI agent interactions.

Core Features & Use Cases

  • Session Classification: Identify if a user's intent was met in a session or trace.
  • Mode Detection: Classify based on session_id, trace_id, or ml_app mode.
  • Content Retrieval Cascade: Retrieve and analyze conversation content and metadata from the session or trace.
  • RUM Behavioral Signals: Utilize Real User Monitoring data to confirm classification.
  • Audit Trail Signals: Analyze the audit trail for server-confirmed effects of the assistant's actions.
  • Use Case: Use this Skill to evaluate the success of an AI agent's interaction with a user, providing feedback for improvement.

Quick Start

Classify the satisfaction of a session with session_id 'abc-123'.

Dependency Matrix

Required Modules

pupdatadog-api

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agent-observability-session-classify
Download link: https://github.com/datadog-labs/agent-skills/archive/main.zip#agent-observability-session-classify

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.