@ArizePhoenix: Phoenix now supports Google's Agent Development Kit for Java.
Summary
Phoenix now supports Google's Agent Development Kit for Java, enabling tracing and enrichment of OpenTelemetry spans without modifying agent code.
View Cached Full Text
Cached at: 09/15/26, 11:51 PM
Phoenix now supports Google’s Agent Development Kit for Java. https://t.co/XIgcaAhXVR
Google ADK tracing for Java - Phoenix
Source: https://arize.com/docs/phoenix/integrations/java/google-adk/google-adk-tracing Instrument Google ADK for Java with OpenInference and export traces to Phoenix.
Google ADK creates OpenTelemetry spans. The OpenInference Java agent enriches those spans and sends them to Phoenix without changes to your agent code.
Prerequisites
- Java and Gradle
- AGemini API key
- The shaded OpenInference ADK Java agent JAR
Run the example
ThePhoenix exampleincludes the ADK agent, OpenTelemetry configuration, and Gradle launch task. Set the path to your shaded OpenInference agent JAR, then run it:
Open Phoenix and select thegoogle\-adk\-javaproject.
Instrument your application
Register a global OpenTelemetry SDK with an OTLP exporter and theopeninference\.project\.nameresource attribute. Do this before constructing any ADK object because ADK captures the global OpenTelemetry instance when its telemetry class loads. The following is taken from the example’sWeatherAgent\.java:
Launch your application with the shaded agent JAR:
For Phoenix Cloud or an authenticated deployment, followConnect your app to Phoenixto configure the endpoint and headers.
Resources
Similar Articles
@ArchiveExplorer: Google just killed the agent framework industry. ADK 2.0: Open-source. Free. Better than $50K enterprise tools. What it…
Google released ADK 2.0, an open-source, code-first Python framework for building AI agents with graph-based orchestration and agent-to-agent delegation, aiming to replace expensive enterprise agent frameworks.
@googledevs: Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and pr…
Google announces the official launch of Managed Agents in the Gemini API, enabling agent development with zero infrastructure overhead. The article also highlights AGENTS.md, an open format for providing context to AI coding agents, adopted by over 60k open-source projects.
@googledevs: Most agent demos are stateless. Ask → answer → context gone. Production agents need to run for days — pausing, resuming…
Google Devs introduces Agent Factory series with ADK 2.0 and Gemini 3.5 Flash, demonstrating how to build production-grade stateful agents that can run for days, featuring insights on skills, MCP, and code review strategies from engineers like Rohde Davis.
@googledevs: Keep your agent's context lean without sacrificing expertise. Learn how Agent Skills in Genkit Go package specialized k…
Google's blog post introduces Agent Skills support in Genkit for Go, demonstrating how progressive disclosure lets agents load specialized knowledge on demand to reduce token usage and improve reliability.
@googledevs: Agent and Model Evaluations in Gemini Enterprise Agent Platform are now Generally Available (GA)! Measure, test, and mo…
Google announces GA of Agent and Model Evaluations in Gemini Enterprise Agent Platform, enabling consistent measurement and monitoring of AI agents in dev and production with pre-built metrics, adaptive rubrics, simulators, and online monitors.