DiscordSign up
SKILLS.SH

adk-observability-guide

Observability setup guide for ADK agents covering tracing, logging, analytics, and third-party integrations. Four observability tiers: Cloud Trace (always enabled, distributed tracing), Prompt-Response Logging (GenAI interactions to GCS/BigQuery), BigQuery Agent Analytics (structured agent events), and third-party platforms (AgentOps, Phoenix, MLflow, Weave, Arize, Monocle, Freeplay) Cloud Trace automatically configured in scaffolded projects and Agent Engine deployments; captures execution flow, latency, and errors via OpenTelemetry spans Prompt-Response Logging privacy-preserving by default (metadata only); controlled via OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT environment variable Includes troubleshooting table for common issues (missing traces, privacy misconfiguration, cost optimization) and reference files for Terraform infrastructure and BigQuery plugin setup

INSTALLATION
npx skills add https://github.com/google/adk-docs --skill adk-observability-guide
Run in your project or agent environment. Adjust flags if your CLI version differs.

SKILL.md

$2c

Tier

What It Does

Scope

Default State

Best For

Cloud Trace

Distributed tracing — execution flow, latency, errors via OpenTelemetry spans

All templates, all environments

Always enabled

Debugging latency, understanding agent execution flow

Prompt-Response Logging

GenAI interactions exported to GCS, BigQuery, and Cloud Logging

ADK agents only

Disabled locally, enabled when deployed

Auditing LLM interactions, compliance

BigQuery Agent Analytics

Structured agent events (LLM calls, tool use, outcomes) to BigQuery

ADK agents with plugin enabled

Opt-in (--bq-analytics at scaffold time)

Conversational analytics, custom dashboards, LLM-as-judge evals

Third-Party Integrations

External observability platforms (AgentOps, Phoenix, MLflow, etc.)

Any ADK agent

Opt-in, per-provider setup

Team collaboration, specialized visualization, prompt management

Ask the user which tier(s) they need — they can be combined. Cloud Trace is always on; the others are additive.

Cloud Trace

ADK uses OpenTelemetry to emit distributed traces. Every agent invocation produces spans that track the full execution flow.

Span Hierarchy

invocation

  └── agent_run (one per agent in the chain)

        ├── call_llm (model request/response)

        └── execute_tool (tool execution)

Setup by Deployment Type

Deployment

Setup

Agent Engine

Automatic — traces are exported to Cloud Trace by default

Cloud Run (scaffolded)

Automatic — otel_to_cloud=True in the FastAPI app

GKE (scaffolded)

Automatic — otel_to_cloud=True in the FastAPI app

Cloud Run / GKE (manual)

Configure OpenTelemetry exporter in your app

Local dev

Works with make playground; traces visible in Cloud Console

View traces: Cloud Console → Trace → Trace explorer

For detailed setup instructions (Agent Engine CLI/SDK, Cloud Run, custom deployments), fetch https://adk.dev/integrations/cloud-trace/index.md.

Prompt-Response Logging

Captures GenAI interactions (model name, tokens, timing) and exports to GCS (JSONL), BigQuery (external tables), and Cloud Logging (dedicated bucket). Privacy-preserving by default — only metadata is logged unless explicitly configured otherwise.

Key env var: OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT — set to NO_CONTENT (metadata only, default in deployed envs), true (full content), or false (disabled). Logging is disabled locally unless LOGS_BUCKET_NAME is set.

For scaffolded project details (Terraform resources, env vars, privacy modes, enabling/disabling, verification commands), see references/cloud-trace-and-logging.md.

For ADK logging docs (log levels, configuration, debugging), fetch https://adk.dev/observability/logging/index.md.

BigQuery Agent Analytics Plugin

Optional plugin that logs structured agent events to BigQuery. Enable with --bq-analytics at scaffold time. See references/bigquery-agent-analytics.md for details.

Third-Party Integrations

ADK supports several third-party observability platforms. Each uses OpenTelemetry or custom instrumentation to capture agent behavior.

Platform

Key Differentiator

Setup Complexity

Self-Hosted Option

AgentOps

Session replays, 2-line setup, replaces native telemetry

Minimal

No (SaaS)

Arize AX

Commercial platform, production monitoring, evaluation dashboards

Low

No (SaaS)

Phoenix

Open-source, custom evaluators, experiment testing

Low

Yes

MLflow

OTel traces to MLflow Tracking Server, span tree visualization

Medium (needs SQL backend)

Yes

Monocle

1-call setup, VS Code Gantt chart visualizer

Minimal

Yes (local files)

Weave

W&B platform, team collaboration, timeline views

Low

No (SaaS)

Freeplay

Prompt management + evals + observability in one platform

Low

No (SaaS)

Ask the user which platform they prefer — present the trade-offs and let them choose. For setup details, fetch the relevant ADK docs page from the Deep Dive table below.

Troubleshooting

Issue

Solution

No traces in Cloud Trace

Verify otel_to_cloud=True in FastAPI app; check service account has cloudtrace.agent role

Prompt-response data not appearing

Check LOGS_BUCKET_NAME is set; verify SA has storage.objectCreator on the bucket; check app logs for telemetry setup warnings

Privacy mode misconfigured

Check OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT value — use NO_CONTENT for metadata-only, false to disable

BigQuery Analytics not logging

Verify plugin is configured in app/agent.py; check BQ_ANALYTICS_DATASET_ID env var is set

Third-party integration not capturing spans

Check provider-specific env vars (API keys, endpoints); some providers (AgentOps) replace native telemetry

Traces missing tool spans

Tool execution spans appear under execute_tool — check trace explorer filters

High telemetry costs

Switch to NO_CONTENT mode; reduce BigQuery retention; disable unused tiers

Deep Dive: ADK Docs (WebFetch URLs)

For detailed documentation beyond what this skill covers, fetch these pages:

Topic

URL

Observability overview

https://adk.dev/observability/index.md

Agent activity logging

https://adk.dev/observability/logging/index.md

Cloud Trace integration

https://adk.dev/integrations/cloud-trace/index.md

BigQuery Agent Analytics

https://adk.dev/integrations/bigquery-agent-analytics/index.md

AgentOps

https://adk.dev/integrations/agentops/index.md

Arize AX

https://adk.dev/integrations/arize-ax/index.md

Phoenix (Arize)

https://adk.dev/integrations/phoenix/index.md

MLflow tracing

https://adk.dev/integrations/mlflow/index.md

Monocle

https://adk.dev/integrations/monocle/index.md

W&B Weave

https://adk.dev/integrations/weave/index.md

Freeplay

https://adk.dev/integrations/freeplay/index.md

BrowserAct

Let your agent run on any real-world website

Bypass CAPTCHA & anti-bot for free. Start local, scale to cloud.

Explore BrowserAct Skills →

Related skills

find-skills
2/3

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities. Helps identify relevant skills by domain and task when users ask "how do I do X" or "find a skill for X" Integrates with the Skills CLI ( npx skills find , npx skills add ) to search, verify, and install packages from the skills.sh directory Recommends skills based on install count, source reputation, and GitHub stars to ensure quality before suggesting installation Presents skill options with install commands and links to skills.sh for user review and one-click installation

Verified authorvercel-labs
SKILLS.SH
1.5M19.6K
2026-05-22
vercel-react-best-practices
3/3

React and Next.js performance optimization guide with 64 prioritized rules across 8 categories. Organized by impact level, from critical waterfalls and bundle optimization down to advanced patterns, each rule includes incorrect/correct code examples and explanations Covers eight domains: async patterns, bundle size, server-side caching, client-side data fetching, re-render optimization, rendering performance, JavaScript efficiency, and advanced patterns Designed for use during component writing, code review, refactoring, and performance audits on React and Next.js applications Each rule has a prefix code (e.g., async-parallel , bundle-barrel-imports ) for easy reference in automated tooling and documentation

Verified authorvercel-labs
SKILLS.SH
389K26.9K
2026-05-22
azure-validate
2/3

Pre-deployment validation for Azure infrastructure, configuration, and permissions before deployment. Requires .azure/plan.md from a prior azure-prepare run; stops immediately if the plan is missing Executes recipe-specific validation commands (azd provision, bicep build, terraform validate) and records proof in the plan document Performs build verification, configuration checks, and permission validation; blocks deployment if any check fails Only authorized method to set plan status to Validated ; must be followed by azure-deploy skill to execute the actual deployment

Verified authormicrosoft
SKILLS.SH
324K1.1K
2026-05-22
appinsights-instrumentation
3/3

Guidance and reference material for instrumenting webapps with Azure Application Insights. Covers SDK setup, telemetry patterns, and configuration for ASP.NET Core and Node.js applications hosted in Azure Distinguishes between this skill (reference and guidance) and azure-prepare (actual implementation); invoke azure-prepare when the user wants to add instrumentation to their project Provides auto-instrumentation guidance for C# ASP.NET Core apps in Azure App Service, plus manual instrumentation paths for creating App Insights resources via Bicep templates or Azure CLI Includes language-specific code modification guides for ASP.NET Core, Node.js, and Python, plus quick references for OpenTelemetry SDKs and exporters

Verified authormicrosoft
SKILLS.SH
324K1.1K
2026-05-22

Stop writing automation&scrapers

Install the CLI. Run your first Skill in 30 seconds. Scale when you're ready.

Start free
free · no credit card