hosted_agent_deploy_expert

Correlate deployment records and runtime telemetry to classify failed Microsoft Foundry hosted-agent deployments.

5|2|Updated Apr 28, 2026
One-click install
npx skills add https://github.com/aiappsgbb/awesome-gbb --skill hosted-agent-deploy-expert
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hosted_agent_deploy_expert
Source: https://github.com/aiappsgbb/awesome-gbb/tree/main/skills/azure-sre-agent/references/plugins/gbb-foundry/skills/hosted_agent_deploy_expert
Command: npx skills add https://github.com/aiappsgbb/awesome-gbb --skill hosted-agent-deploy-expert

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps troubleshoot failed Microsoft Foundry hosted-agent deployments by guiding investigation of deployment states, runtime logs, and common configuration or SDK issues.

Core Features & Use Cases

  • Deployment triage: Identify the failed deployment instance, provisioning state, and failure reason from Foundry.
  • Log-driven root-cause classification: Map App Insights/Log Analytics error patterns to specific known causes and KI handoffs.
  • Targeted remediation paths: Provide safe, human-approve-only guidance for MAF SDK breaking changes, ACR push/pull issues, BYOK/AOAI RBAC, azd AI agent envelope quirks, and missing generated config.

Quick Start

Ask an AI agent to guide you through investigating a specific failed hosted-agent deployment by using the agent name, the approximate failure time window, and the Foundry project details to classify the error pattern and select the appropriate fix or handoff.

Frequently Asked Questions about hosted_agent_deploy_expert

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I troubleshoot a failed hosted-agent deployment on Microsoft Foundry?

Diagnose failed hosted-agent deployments on Microsoft Foundry by correlating deployment states and App Insights runtime telemetry with known failure patterns. This read-only investigation classifies errors and triggers specific remediation guidance for safe resolution.

Why does my azd AI agent deploy fail on the first invoke call?

Your azd AI agent deploy may fail on the first invoke call due to MAF SDK breaking changes, ACR push or pull issues, BYOK/AOAI RBAC misconfiguration, azd AI agent envelope quirks, or missing generated config. Map App Insights traces to identify the specific cause.

How do I fix ACR push and pull issues during azd deploy?

Fix ACR push and pull issues during azd deploy by correlating App Insights and Log Analytics error patterns to identify the failure. This process maps container registry errors to specific known causes, triggering targeted remediation paths for safe resolution.

Does troubleshooting Foundry hosted agents require write access to fix RBAC issues?

Troubleshooting Foundry hosted agents requires only read-only investigation steps to diagnose BYOK or AOAI RBAC issues. It provides human-approve-only remediation guidance for configuration fixes without exposing secrets or requiring direct write access.

What is the best way to classify az ml online-deployment failure reasons?

The best way to classify az ml online-deployment failure reasons is to query the deployment state and correlate App Insights trace logs against known failure patterns. This deterministic classification triggers KI-specific remediation guidance for the identified error.

When should I use App Insights trace queries for deployment troubleshooting?

Use App Insights trace queries for deployment troubleshooting when a hosted-agent deployment fails during rollout or provisioning. Querying runtime logs helps map error patterns to specific known causes like SDK breaking changes or missing generated config.