OpenParable
Skip to content
← Back to skills

Azure Personalizer

Development
azure-personalizer

Azure Personalizer is an Agent Skill for development published in the MicrosoftDocs/Agent-Skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Expert knowledge for Azure AI Personalizer development including troubleshooting, decision making, security, configuration, and integrations & coding patterns. Use when choosing single vs multi-slot, tuning exploration policies, configuring CMK encryption, debugging low rewards, or using local inference SDK, and other Azure AI Personalizer related development tasks. Not for Azure AI Metrics Advisor (use azure-metrics-advisor), Azure AI Anomaly Detector (use azure-anomaly-detector), Azure Machine Learning (use azure-machine-learning).

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/MicrosoftDocs/Agent-Skills/blob/HEAD/skills/azure-personalizer/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/azure-personalizer, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Azure AI Personalizer Skill

This skill provides expert guidance for Azure AI Personalizer. Covers troubleshooting, decision making, security, configuration, and integrations & coding patterns. It combines local quick-reference content with remote documentation fetching capabilities.

How to Use This Skill

IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g., L35-L120), use read_file with the specified lines. For categories with file links (e.g., [security.md](security.md)), use read_file on the linked reference file

IMPORTANT for Agent: If metadata.generated_at is more than 3 months old, suggest the user pull the latest version from the repository. If mcp_microsoftdocs tools are not available, suggest the user install it: Installation Guide

This skill requires network access to fetch documentation content:

  • Preferred: Use mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.
  • Fallback: Use fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.

Category Index

CategoryLinesDescription
TroubleshootingL33-L37Diagnosing and fixing common Azure Personalizer problems: configuration and training issues, API/latency errors, low reward performance, and steps to debug and resolve service failures.
Decision MakingL38-L42Guidance on when to use single-slot vs multi-slot Personalizer, comparing scenarios, behavior, and design tradeoffs for different personalization needs.
SecurityL43-L48Configuring encryption at rest (including customer-managed keys) and controlling data collection, storage, and privacy settings for Azure Personalizer.
ConfigurationL49-L56Configuring Personalizer’s learning behavior: policies, hyperparameters, exploration, apprentice mode, explainability, model export, and learning loop settings.
Integrations & Coding PatternsL57-L60Using the Personalizer local inference SDK for low-latency, offline/edge scenarios, including setup, integration patterns, and best practices for calling the model locally.

Troubleshooting

TopicURL
Diagnose and resolve common Azure Personalizer issueshttps://learn.microsoft.com/en-us/azure/ai-services/personalizer/frequently-asked-questions

Decision Making

Security

Configuration

Integrations & Coding Patterns

TopicURL
Use Personalizer local inference SDK for low latencyhttps://learn.microsoft.com/en-us/azure/ai-services/personalizer/how-to-thick-client