Google

Prepare to fine-tune open models or Gemini models on Agent Platform. Check the environment, convert and validate training data, choose supported models and settings, and estimate tuning costs for open models.

• Checking whether an Agent Platform tuning environment is ready
• Converting and validating training datasets
• Choosing models and training settings for a task

Inspect and manage model tuning jobs, which adapt models through additional training, in Agent Platform. List jobs, check their status and details, and cancel running jobs after reviewing the target and explicitly confirming the action.

• List running model tuning jobs
• Check the status and details of a specific job
• Cancel a long-running job after confirmation

Investigate 403 and 500 errors in Google Cloud Gemini Enterprise Agent Platform. Examine logs, registered destinations, agent identities, and authorization policies to produce a diagnostic report with evidence, recommended fixes, and verification steps.

• Investigating 403 errors when an agent calls an external API
• Diagnosing Agent Runtime 500 errors involving Model Armor
• Checking registration and permissions for failing MCP connections

Find and manage agent skills in the Gemini Enterprise Agent Platform Skill Registry, a catalog of available capabilities. The skill supports searching, uploading, updating, deleting, inspecting revision histories, checking operation status, and creating local starter files.

• Search for skills that provide a needed capability
• Upload or update skills in the registry
• Inspect skill details and revision histories

Manage saved prompts in Agent Platform with Python, including creation, listing, retrieval, version tracking, and deletion. Retrieve a specific version and fill template variables to reuse a prompt with its associated model.

• Create a managed prompt template
• List saved prompts and inspect their contents
• Retrieve a specific version and fill template variables

Guides migration from Google AI Studio’s Gemini API to Gemini Enterprise Agent Platform on Google Cloud, covering billing, access permissions, authentication, and connection settings for SDKs and supported agent tools.

• Moving a Gemini application to Google Cloud
• Using Google Cloud credits for Gemini API calls
• Unifying agent authentication and billing

Audit Google Mobile Ads SDK integration in iOS, Android, or Unity projects. Check test IDs, ad units, SKAdNetwork IDs, adapter compatibility, and ad preloading, then report findings and next steps in a table.

• Audit mobile ad integration before launch
• Check for remaining test IDs and invalid formats
• Review SKAdNetwork IDs and adapter compatibility

Call Gemini and OpenMaaS models such as Llama, DeepSeek, and Qwen through Google Cloud Agent Platform. Prepare authentication and SDK code, run prompts, configure connection endpoints, and troubleshoot common request errors.

• Send a test prompt to Gemini
• Call Llama or DeepSeek with the OpenAI SDK
• Write code to call an existing custom endpoint

Evaluate AI models and agents on Google Cloud using test datasets and scoring criteria. Generate simulated user scenarios, analyze failures, and compare results across changes to guide improvements to prompts and code.

• Build evaluation datasets from conversation logs
• Generate simulated user scenarios
• Choose scoring criteria for responses and tool use

Set up credentials and a development environment for your first Google Ads API request to retrieve campaigns. Choose from six official client libraries or direct HTTP requests, with guidance for account IDs, developer tokens, and common authorization errors.

• Prepare credentials for a first Google Ads API integration
• Build an example that retrieves advertising campaigns
• Choose a client library or direct REST requests

Create Terraform files that define alerts for AI agent latency, errors, token use, safety, security, and response quality. Check telemetry and existing policies first, then validate the generated configuration. Quality alerts require Vertex AI.

• Configure alerts for agent latency and error rates
• Monitor rapid increases in token usage
• Monitor safety triggers and permission denials

Manage machine learning models and their versions in the Agent Platform Model Registry. List registered models, inspect details, upload new versions, update names or descriptions, and delete models through workflows that require confirmation for changes.

• List registered models and inspect their details
• Register a new model or model version
• Update a model's display name or description

Implement full-screen ads at natural transitions in mobile apps using the Google Mobile Ads SDK. Follow platform-specific guidance for Android, iOS, or Unity, covering ad loading, event handling, display, and implementation verification.

• Add full-screen ads between app screens
• Implement interstitial ads on Android or iOS
• Integrate interstitial ads into a Unity app

Integrate video and audio ads into websites, apps, and TV platforms with Google IMA SDK. Follow platform-specific guidance for client-side ad requests, playback coordination, error handling, and cleanup after ads finish.

• Adding video ads to a website
• Integrating ads into mobile and TV apps
• Coordinating ad playback with main content

Implement rewarded ads with the Google Mobile Ads SDK on Android, iOS, or Unity. Add a user interface for choosing to view an ad for a reward, and follow steps for loading, event handling, display, and verification.

• Add ads users choose to view for in-app rewards
• Implement rewarded ads on Android or iOS
• Integrate rewarded ads into a Unity app

Configure Google Cloud logs across multiple projects, either by storing them centrally or querying them together where they already reside. The skill guides routing, access permissions, and log views, and helps diagnose missing logs and permission failures.

• Collect logs from multiple projects in one central bucket
• Query distributed logs without copying their data
• Set log access boundaries by project or log type

Configure Cloud Logging within one Google Cloud project. Set storage locations, retention periods, routing rules, and viewing permissions; create metrics from logs; and adjust stored volume through exclusions or sampling, which retains only a portion of entries.

• Set regional log storage and retention periods
• Restrict access to sensitive logs
• Count specific errors with logs-based metrics

Learn Cloud Build fundamentals and set up a basic build trigger for source code changes. Covers project preparation, configuration files, manual trigger runs, and checking build history and logs in Google Cloud.

• Learn build steps, artifacts, and configuration file basics
• Create a trigger that builds code after a Git push
• Run an existing trigger manually

Create and work with Google Bigtable instances and tables, design row keys and column groups, and query data with SQL or client libraries. Investigate slow queries and concentrated access patterns using Key Visualizer and command-line diagnostics.

• Designing row keys and column families
• Creating Bigtable instances and tables
• Writing SQL queries or data access code

Investigate failing or slow BigQuery jobs and unexpected cost increases. Compare execution details and resource usage with a normal baseline to isolate bottlenecks, identify likely causes, and determine practical remediation steps.

• Investigate failed or slow BigQuery jobs
• Locate bottlenecks in execution stages
• Diagnose sudden increases in query or capacity costs

Review BigQuery capacity, table layouts, storage retention, and SQL to improve cost efficiency. Compare billing options, plan partitioned tables, and evaluate search indexes, stored aggregation results, and BI Engine for suitable workloads.

• Compare On-Demand pricing with Editions
• Review storage billing models and retention periods
• Design table partitioning and clustering

Write SQL that uses BigQuery’s built-in machine learning and generative AI for forecasting, anomaly detection, identifying drivers of change, searching by meaning, and classifying or summarizing text stored in your data.

• Forecasting future values from time-series data
• Detecting anomalies and investigating drivers of change
• Searching documents by meaning

Create and administer AlloyDB for PostgreSQL databases, including clusters, instances, backups, secure connections, and access permissions. It also covers command-line operations, infrastructure configuration, and MCP tools that let agents automate database tasks.

• Create an AlloyDB cluster and primary instance
• Manage backups and plan recovery
• Configure secure connections and access permissions

Integrate the Google Mobile Ads SDK into an Android, iOS, or Unity app for AdMob or Ad Manager. Follow platform-specific steps to add dependencies, set the application identifier, initialize the SDK, and verify the integration.

• Add the SDK to an Android app
• Configure the SDK for an iOS app
• Integrate mobile ads into a Unity project