/azure-microsoft-discovery

name: azure-microsoft-discovery
description: Expert knowledge for Azure Microsoft Discovery development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Discovery Engine shared sessions, supercomputer jobs, REST job APIs, custom tools, or ACR deployments, and other Azure Microsoft Discovery related development tasks.
compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
metadata:
  generated_at: "2026-08-09"
  generator: "docs2skills/1.0.0"

Azure Microsoft Discovery Skill

This skill provides expert guidance for Azure Microsoft Discovery. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. 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](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)

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

| Category | Lines | Description | |----------|-------|-------------| | Troubleshooting | L37-L42 | Diagnosing and resolving Microsoft Discovery Engine task failures, and locating/using correlation IDs from Activity Logs to debug and trace issues. | | Best Practices | L43-L50 | Best practices for structuring projects and shared sessions, applying responsible AI, calibrating trust and safety patterns, and planning tool capabilities and compute for Discovery. | | Decision Making | L51-L58 | Guidance on selecting ACR setup, agent types, pricing/billing, and suitable AI models to design and configure Microsoft Discovery agents effectively. | | Architecture & Design Patterns | L59-L63 | Designing and implementing advanced shared session patterns in Discovery Engine, including multi-user session management, data sharing, and scalable architecture best practices. | | Limits & Quotas | L64-L69 | Planning capacity and Azure quotas for Microsoft Discovery deployments, plus required naming conventions and rules for Discovery resources. | | Security | L70-L84 | Security, encryption, RBAC, managed identities, private networking, supercomputer network hardening, and audit logging for protecting Microsoft Discovery resources. | | Configuration | L85-L105 | Configuring Discovery workspaces, supercomputers, storage, tools, data handling, and querying operational/indexing logs via Log Analytics, Kusto, and Azure activity logs | | Integrations & Coding Patterns | L106-L113 | Integrating custom tools/models into Discovery workflows, containerizing them with Docker, calling Discovery Supercomputer REST job APIs, and writing action scripts for action-based tools. | | Deployment | L114-L120 | Deploying Discovery infrastructure and tools: network-hardened stacks, Bicep-based deployments, REST provisioning of supercomputer resources, and publishing tool images to Azure Container Registry. |

Troubleshooting

| Topic | URL | |-------|-----| | Troubleshoot Discovery Engine task execution issues | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-debug-task-execution | | Find Microsoft Discovery correlation IDs in Activity Log | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-get-correlation-id |

Best Practices

| Topic | URL | |-------|-----| | Apply projects and shared session best practices in Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-projects-investigations | | Apply responsible AI practices in Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-responsible-ai | | Calibrate trust and basic shared session patterns in Microsoft Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-trust-basic-investigation-patterns | | Plan tool functionality and compute for Discovery tools | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-plan-tool-requirements |

Decision Making

| Topic | URL | |-------|-----| | Choose and configure Azure Container Registry for Discovery | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-azure-container-registry | | Choose the right Microsoft Discovery agent type | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-discovery-agent-types | | Understand Microsoft Discovery billing and charges | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-discovery-billing | | Choose appropriate models for Microsoft Discovery agents | https://learn.microsoft.com/en-us/azure/microsoft-discovery/how-to-select-models-for-agents |

Architecture & Design Patterns

| Topic | URL | |-------|-----| | Apply advanced shared session patterns with Discovery Engine | https://learn.microsoft.com/en-us/azure/microsoft-discovery/concept-advanced-investigation-patterns |

Limits & Quotas

| Topic | URL | |-------|-----| | Plan Azure quotas and capacity for Microsoft Discovery deployments | https://learn.microsoft.com/en-u