Microsoft

Describes your app's CPU, memory, and traffic pattern — get a specific Azure VM family recommendation with pricing, autoscale settings, and capacity reservation guidance.

Pulls your Azure spend history by service and resource, projects next month's bill, and flags the top three cost drivers with a concrete cut to try.

Integrates Claude with Azure Search, Speech, Document Intelligence, and OpenAI endpoints. Handles vector search, hybrid queries, transcription, and OCR in one place.

Describe what a user or service needs to do in Azure, and get the minimal RBAC role plus ready-to-run CLI and Bicep code to assign it safely.

Compares Blob, Files, Queues, and Tables; explains when hot vs. cool vs. archive tiers save money; recommends the cheapest fit for your access pattern.

Walks through the Day-0 decisions—SKU type, network isolation, security defaults, autoscaling—and outputs a working terraform or CLI config for a locked-down cluster.

Scans your Azure config, Bicep/Terraform, RBAC roles, and managed identities to surface permission gaps, misconfigurations, and missing prerequisites—all before you deploy.

Connects to AppLens and Azure Monitor to surface logs, resource health, and error traces. Narrows down whether the issue is deployment, CPU, networking, or code.

Handles the Azure OpenAI setup end-to-end: picks the right SKU and region, sets capacity, applies your compliance policy, and routes requests to the deployed model.

Walks through model version, SKU tier, capacity, content-filter policy, and quota options in sequence, then outputs the exact deployment config and cost estimate.

Walks through cluster verification, controller install, GPU assessment, and provider setup to get your first model deployed on AKS without manual debugging.

Analyzes your current Azure workload, compares cost and performance across plans and SKUs, and produces a migration runbook with downtime estimates and rollback steps.

Runs your pre-configured deployment plan — azd up, terraform, container pushes — against Azure. Watches for errors and rolls back on failure.

Maps your Lambda, Beanstalk, or Fargate setup to Azure equivalents, generates a migration playbook with code samples, and flags breaking changes before you refactor.

Scans your cluster manifests and config for incompatibilities with Azure's managed Kubernetes service, flags blockers, and suggests fixes to unblock migration.

Reads an Event Hubs or Service Bus error stack and pinpoints the cause—auth misconfiguration, connection pool limits, partition key mismatches—with a concrete next step.

Queries your Azure account for current quotas, usage, and regional availability—then flags when a deployment plan risks hitting a limit and suggests which region has headroom.

Scans your deployed Functions and App Service instances for zone redundancy, failover, and storage resilience gaps. Returns a prioritized checklist with CLI commands to fix each.

Reads a resource group and draws a Mermaid diagram showing every resource, how they connect, and the flow of data between them. Exports as PNG or SVG.

Converts plain-English questions about your Kusto database into KQL queries and returns results with context — anomaly detection, time-series patterns, and drill-down options included.

Scaffolds and deploys a GitHub Copilot SDK application to Azure, handling auth, environment config, and the SDK client setup so you don't repeat it each time.

Builds a Docker image, pushes to ACR, deploys to Foundry, runs evals against a dataset, then fine-tunes the model based on failures—all from one command.

Prepares a dataset, submits a training job to Azure AI Foundry, and deploys a fine-tuned model. Supports supervised learning, preference optimization, and reinforcement training with custom graders.

Queries your Azure projects, surfaces quota limits per region, and shows which deployment location has the headroom you need right now.

Scans Azure OpenAI capacity across all regions in real time and routes your deployment to the lowest-latency endpoint with available quota. Falls back if your preferred region is full.

Builds Bicep/Terraform infrastructure, azure.yaml, and Dockerfiles configured for your stack. Ready to deploy to Azure Container Apps or App Service without manual setup.

Queries your Azure subscriptions and resource groups by name, type, or tag — returning configs, endpoints, and status in seconds without manual console digging.

Walks through creating an app registration in Microsoft Entra, configuring OAuth scopes and permissions, and provides working code samples for MSAL integration.

Provisions agent identities, blueprints, and OAuth token exchange in Entra via Microsoft Graph. Handles cross-tenant scenarios and AgentID sidecar setup for production workloads.

Walks through SDK setup, telemetry patterns, and configuration for tracking errors, performance, and user behavior in a webapp—with runnable code snippets for common frameworks.

Routes Claude through Azure's API gateway to enforce token limits, detect jailbreaks, cache expensive calls, and balance load across models — all without touching your code.

Runs a security scan across your Azure resources, checks Key Vault expiration, and flags policy violations and misconfigurations against industry best practices.

Describe your workload and compliance needs once; generates a network topology, identity scheme, security baseline, and Bicep/Terraform code ready to deploy—with WAF alignment baked in.