333 docs tagged with "skill"

Orchestrate builder, reviewer, and tuner agent handoffs for solution plays — define roles, model routing, token budgets, and quality gates

Configure API rate limiting, APIM throttling, and retry behavior for AI endpoints — absorb bursts, isolate noisy tenants, and control 429 retries

Configure Application Insights, OpenTelemetry, and KQL dashboards for AI workloads — trace latency, token usage, failures, and cost signals

Implement immutable audit logging, PII redaction, and Sentinel monitoring for AI systems — preserve evidence, prove access history, and detect suspicious activi

Set up Azure OpenAI deployments, RBAC, and monitoring — harden inference endpoints and control latency, quota, and cost

Back up AI data, vector indexes, and configuration state — recover prompts, conversations, and search assets after failures

Create reusable Bicep modules, parameter files, and registry packages — standardize Azure infrastructure and reduce deployment drift

Implement canary deployment, rollout gates, and rollback automation for AI changes — catch latency or quality regressions before full release

Add a circuit breaker, fallback routing, and health checks for Azure OpenAI calls — contain 429 and 503 cascades and preserve service

Run AI compliance audits, collect Azure evidence, and track remediation — assess SOC 2, HIPAA, ISO 27001, and EU AI Act controls

Configure Azure Content Safety thresholds, blocklists, and prompt shields for AI apps - block unsafe inputs, detect jailbreaks, and monitor moderation drift

Create cost dashboards, budget alerts, and attribution views for AI workloads - track token spend by model, team, and tenant before overruns hit production

Optimize RAG chunking, overlap, and metadata boundaries - improve retrieval recall, reduce noisy context, and preserve citation quality

Migrate AI data, embeddings, and index schemas with zero-downtime cutovers - preserve compatibility, validate every step, and keep rollback ready

Containerize AI applications with multi-stage images, health probes, and secure runtime settings - ship smaller containers and safer deployments

Select embedding models, dimensions, and hybrid search settings for vector workloads - balance recall, storage cost, and migration risk

Create evaluation pipelines, CI gates, and regression checks for AI systems - score groundedness, block regressions, and publish release verdicts

Configure builder→reviewer→tuner agent chain with handoff rules, model assignment, and evaluation gates.

Review agent safety controls, budget limits, and human escalation paths - approve only agents that stay bounded, observable, and policy-compliant

Run evaluator-optimizer loops for agents and prompts - score outputs, revise weak instructions, and stop only when quality thresholds hold

Generate API reference docs, examples, and error catalogs from OpenAPI or code annotations - keep endpoint docs accurate, testable, and publishable

Generate typed REST API endpoints with Zod/Pydantic input validation, RFC 7807 error responses, OpenAPI annotation, and Managed Identity auth — eliminating sche

Configure API rate limiting with Azure APIM policies, throttling tiers, and retry headers.

Configure Application Insights with custom AI metrics, anomaly alerts, and operational dashboards.

Generate solution architecture blueprints with Mermaid service topology, component responsibility tables, data flow annotations, and WAF pillar mapping — bridgi

Generate Architecture Decision Records capturing context, forces, decision rationale, rejected alternatives, and consequences — preventing knowledge rot when te

Wire .NET Aspire AppHost for multi-container orchestration, automatic service discovery, distributed OpenTelemetry export, and local Azure emulator integration

Scaffold ASP.NET Core Minimal API with typed route groups, FluentValidation, Managed Identity credentials, OpenAPI v3 via Scalar, Serilog structured logging, an

Implement immutable audit logging with Azure Blob Storage, Sentinel integration, and compliance evidence.

Analyze Azure AI workload spend with Cost Management API queries, flag overprovisioned PTU, identify semantic cache gaps, right-size model SKUs, and produce act

Provision Azure AI Foundry Hub and Project with Managed Identity RBAC, private endpoint networking, connected Azure AI Services and Key Vault — ready for Prompt

Create Azure AI Search vector indexes with HNSW profiles, semantic ranker configuration, hybrid BM25+vector search, field mappings for chunked RAG documents, an

Wire Azure App Configuration with feature flag targeting filters, Key Vault reference chaining, .NET/Python SDK refresh polling, and blue/green rollout strategi

Conduct Azure Well-Architected Framework reviews with scored pillar assessments, tiered finding severity, remediation priority tables, and an executive scorecar

Design and apply Azure Blob Storage lifecycle management policies with tiering to cool/archive, retention rules, and delete-after-N-days automation — reducing s

Integrate Language, Speech, Vision, and Translator services with Managed Identity authentication, pre-built and custom models, content safety filters, and regio

Configure Azure Container Registry with geo-replication across regions, image scanning for vulnerabilities, Managed Identity pull access, and OCI artifact suppo

Design Cosmos DB data models with optimal partition keys, Request Unit (RU) estimation, vector search embedding storage, and analytical workload isolation — exc

Configure Azure Data Explorer for real-time telemetry ingestion with KQL queries, time-series aggregations, and interactive dashboards — analyzing AI workload m

Configure Azure Event Grid for event-driven AI pipelines with topic subscriptions, dead-letter queues, retry policies, and role-based filtering — routing docume

Configure Azure Event Hubs for real-time data ingestion with stream processing, auto-scaling, Managed Identity auth, and consumer groups — enabling AI workload

Scaffold Azure Functions apps with HTTP/Event Hub/Service Bus triggers, input/output bindings, Managed Identity, Application Insights, and local development set

Configure Azure Key Vault with managed identities, RBAC, secret rotation policies, customer-managed keys (CMK), and app integration patterns — avoiding hardcode

Deploy Azure OpenAI with model selection, PTU vs PAYG pricing tiers, content safety filters, token management strategies, and streaming patterns — maximizing co

Set up Azure OpenAI Service with model deployments, RBAC, content filtering, and monitoring.

Query Azure Resource Graph across subscriptions with KQL for compliance audits, cost analysis, RBAC reviews, and cross-tenant resource discovery — enabling unif

Diagnose Azure resource health issues via Resource Health events, platform metrics, activity logs, and one-click remediation workflows — preventing cascading AI

|

|

|

|

|

|

Set up backup and restore procedures for AI application data, model configs, and index state.

|

Create a reusable Bicep module with typed parameters, conditions, outputs, and AVM alignment.

|

Analyze and refine prompts with specificity scoring, few-shot examples, and constraint encoding — improving accuracy by 20-40% and reducing token spend by 15-25

Build autonomous agent loops with ReAct pattern, tool calling, reflection cycles, and termination conditions — enabling multi-turn reasoning without callback he

Create reusable Bicep modules following AVM patterns with typed parameters, outputs, deployment tests, and registry publishing — standardizing infrastructure ac

Build optimized Docker images with multi-stage builds, non-root runtime, health checks, and AI model weight caching — reducing deployment time by 60% and image

Build custom LLM evaluation metrics for groundedness, coherence, relevance, and domain-specific quality — enabling automated CI gates and production quality mon

Build NoSQL data models (Cosmos DB documents, partition keys) for AI workloads with optimal consistency and throughput.

Build end-to-end prompting systems using Prompt Flow, versioning, A/B testing, and performance tracking.

Implement semantic search with embeddings, reranking, and hybrid search combining BM25 + vector similarity.

Migrate SQL schemas to cloud with zero downtime, validation, and rollback automation.

Create reusable Terraform modules for multi-cloud AI infrastructure provisioning.

Build comprehensive test harnesses for LLM applications covering deterministic and non-deterministic flows.

Implement custom tokenizers for domain-specific AI models optimizing vocabulary size and encoding efficiency.

Write effective unit tests for AI functions covering happy path, edge cases, and error handling.

Provision vector stores (Cosmos DB, Pinecone, Weaviate) with scaling, indexing, and retrieval optimization.

Implement canary deployment for AI model updates with traffic splitting and rollback on quality drop.

Generate automated changelogs from commit messages and PRs with structured formatting.

Add circuit breaker pattern for Azure OpenAI calls with exponential backoff and fallback behavior.

Apply cloud design patterns (bulkhead, retry, circuit breaker, CQRS) for AI workloads.

Analyze Python/TypeScript code for smell patterns and suggest refactoring opportunities.

Configure CodeQL for security scanning of ML/AI code against OWASP LLM Top 10.

Auto-generate code tutorials from comments and docstrings with executable examples.

Run a compliance audit against HIPAA, FedRAMP, SOC 2, and EU AI Act requirements for AI systems.

Generate component documentation from code annotations and type signatures.

Containerize ASP.NET Core AI APIs with Dockerfile multi-stage builds and health checks.

Containerize legacy ASP.NET Framework apps for cloud deployment.

Review AI-generated content against safety policies and compliance requirements.

Visualize architecture context maps showing bounded domains and integration points.

Implement contextual RAG with dynamic prompt augmentation based on user context and conversation history.

Enforce conventional commits for automated changelog, versioning, and release notes generation.

Set up GitHub Copilot CLI for code generation, explanation, and commit message assistance.

Generate custom Copilot instructions for domain-specific coding patterns and conventions.

Integrate Copilot SDK into applications for AI-assisted features and chat capabilities.

Configure Copilot Spaces for team-based collaborative AI development environments.

Track Copilot usage metrics for cost attribution, productivity analysis, and adoption monitoring.

Design Cosmos DB data models with optimal partition keys, throughput, and vector indexes.

Build cost estimation models for AI workloads across Azure, models, and infrastructure.

Automate daily prep workflows: code audits, test coverage checks, dependency updates.

Design database schemas with normalization, indexing, and partition strategies for AI workloads.

Identify and remove dead code paths in Python/TypeScript applications with automated tooling.

Deploy Enterprise RAG solution play with orchestration, monitoring, and scaling.

Deploy AI Landing Zone infrastructure with networking, governance, and compliance.

Deploy Deterministic Agent with structured output validation and evaluation gates.

Deploy Call Center Voice AI with STT, LLM, TTS streaming pipeline.

Deploy IT Ticket Resolution automation with multi-agent orchestration.

Deploy Document Intelligence solution with OCR and entity extraction.

Deploy Multi-Agent Service coordinator with agent delegation and state management.

Deploy Copilot Studio bot with custom actions and conversation flows.

Deploy AI Search Portal with semantic ranking, hybrid search, and result reranking.

Deploy Content Moderation system with safety scoring and policy enforcement.

Deploy Advanced AI Landing Zone with hub-spoke networking and compliance.

Deploy Model Serving on AKS with GPU scheduling and autoscaling.

Deploy Fine-Tuning workflow with JSONL data prep and evaluation gates.

Deploy Cost-Optimized Gateway with model routing and caching.

Deploy Multi-Modal Document Processing with vision and layout analysis.

Deploy Copilot Teams Extension with custom actions and bot framework.

Deploy AI Observability stack with KQL, dashboards, and alerting.

Deploy Prompt Management system with versioning and A/B testing.

Deploy Phi4 models on edge devices with quantization and local inference.

Deploy Anomaly Detection system using statistical and ML methods.

Deploy Agentic RAG with tool use and dynamic retrieval.

Deploy Multi-Agent Swarm coordinator with topology and state sync.

Deploy Browser Automation Agent with Selenium and Playwright.

Run preflight checks before deploying solution play infrastructure.

Design accessible AI interfaces following WCAG 2.1 AA standards.

Design smooth animations and transitions for AI response streaming.

Design data visualizations for AI metrics and model diagnostics.

Design multi-turn dialog systems with context and flow management.

Design error state UI patterns with retry, recovery, and fallback options.

Design forms for AI interactions with validation, accessibility, and feedback.

Create consistent icon systems for AI UI workflows and operations.

Design layout patterns for responsive AI dashboards and chat interfaces.

Design loading states and skeleton screens during AI processing.

Design onboarding flows for AI features with guided tours and prompts.

Ensure responsive design across devices for AI tools and dashboards.

Manage UI state transitions during multi-turn AI interactions.

Define design tokens for colors, spacing, typography in AI UIs.

Implement light/dark themes and custom branding for AI products.

Design reusable UI components for AI applications (buttons, cards, modals).

Implement deterministic agents with structured output and validation.

Auto-generate API and architecture documentation from code annotations.

Apply Domain-Driven Design principles to AI system architecture.

Generate Draw.io diagrams from architecture definitions automatically.

Build dynamic prompts that adapt based on user context and history.

Generate test cases for edge cases in AI workflows.

Configure EditorConfig for consistent code style across team.

Choosing between embedding models (text-embedding-3-small vs large vs ada-002),Configuring dimensions, batch sizes, and chunking parameters,Benchmarking embeddi

Break down epics into architecture tasks and technical stories.

Break down epics into product management stories and features.

Adopt evaluation-driven development for continuous AI quality assessment.

Run evaluation pipelines with metrics tracking and result reporting.

Evaluate Enterprise RAG recall, precision, and groundedness.

Evaluate Landing Zone compliance, security posture, and governance.

Evaluate Deterministic Agent output consistency and reliability.

Evaluate Voice AI latency, accuracy, and conversation quality.

Evaluate ticket resolution quality and automation effectiveness.

Evaluate OCR accuracy and entity extraction correctness.

Evaluate multi-agent coordination and task completion.

Evaluate bot conversation quality and user satisfaction.

Evaluate AI Search Portal search quality and reranking accuracy.

Evaluate Content Moderation coverage and policy adherence.

Evaluate Advanced Landing Zone resilience and performance.

Evaluate Model Serving latency, throughput, and availability.

Evaluate fine-tuning quality improvements and job success.

Evaluate gateway routing efficiency and cost savings.

Evaluate multi-modal document processing accuracy.

Evaluate extension adoption and user engagement metrics.

Evaluate observability coverage and alerting effectiveness.

Evaluate prompt versioning and A/B test performance.

Evaluate edge AI model performance and resource utilization on devices.

Evaluate anomaly detection accuracy and false-positive rates.

Evaluate agentic RAG decision quality and retrieval effectiveness.

Evaluate multi-agent swarm coordination and task completion.

Evaluate browser automation success rate and error recovery.

Build comprehensive evaluation frameworks for AI system quality gates.

Generate Excalidraw diagrams from architecture descriptions.

Design fabric lakehouses for unified data analytics and AI.

Scaffold FastAPI microservices with async handlers and OpenAPI.

Break down features into implementation tasks with acceptance criteria.

Finalize agent system prompts with guardrails and context anchoring.

Prepare and execute LLM fine-tuning with quality evaluation.

Craft opening prompts to gather requirements for AI systems.

Design workflows in Azure Flow Studio or Zapier.

Establish project folder structure for AI solution plays.

Ensure GDPR compliance in AI data processing and storage.

Use GitHub CLI for repository and issue automation.

Apply conventional commits and meaningful commit messages.

Implement Git Flow branching strategy for team collaboration.

Triage and prioritize GitHub issues using labels and automation.

Manage GitHub issues with automation, templates, and workflows.

Execute effective PR reviews with checklists and CI gates.

Define go-to-market strategy for AI products.

Build developer ecosystem and community engagement.

Design enterprise onboarding workflows for AI solutions.

Plan enterprise deployments with RFP responses.

Communicate AI value propositions to investors.

Execute go-to-market launch plan for AI product.

Establish operating cadence for AI product team.

Build partnership strategy for AI platform ecosystem.

Define product positioning and competitive differentiation.

Implement product-led growth strategy for AI tools.

Define safety guardrails and acceptable use policies.

Implement human-in-the-loop workflows for AI decisions.

Generate implementation plans from architecture.

Import existing infrastructure as code for modernization.

Optimize model inference latency and throughput.

Refactor Java code via extract method patterns.

Write Jest tests for JavaScript/TypeScript applications.

Write JUnit tests for Java applications with coverage.

Integrate LangChain with Azure OpenAI, semantic search, RAG chains, memory systems, and production tooling.

Generate LLMS.txt file from codebase structure to help LLMs understand repository context and conventions.

Load test an AI endpoint with k6/Locust for p95 latency and error rates

Guide through creating a complete, production-ready contribution to an open-source repository with testing, documentation, and review readiness.

|

Create or update fai-manifest.json with solution play context, primitive wiring, and guardrails thresholds.

Scaffold a production-ready C#/.NET MCP server with ModelContextProtocol NuGet, dependency injection, async tools, and Azure Managed Identity.

|

|

|

|

|

Scaffold a production-ready Python MCP server with FastMCP decorators, async tools, structured outputs, and Azure integration.

Generate a project skeleton for Python MCP servers with FastMCP, async tools, testing harness, and Docker deployment.

Scaffold a Ruby MCP server using the official SDK with tool handlers, resource capabilities, and error handling.

Build a high-performance Rust MCP server with async tokio runtime, type-safe tool handlers, and zero-copy serialization.

Generate a Swift MCP server for macOS/iOS with type-safe tool definitions, Codable serialization, and native integration.

Generates Mermaid diagrams (flowcharts, sequence, Gantt) from natural language.

|

Implement model routing logic: cheap model for simple, capable for complex tasks

Generates optimized multi-stage Dockerfiles with minimal runtime images.

Create an observability dashboard with KQL queries for AI system health

Set up PII detection and masking with Azure AI Language service

Scaffold a new solution play with FAI Protocol wiring, directory structure, primitives stubs, and deployment config.

Design Power BI dashboards with KPIs, drill-through navigation, real-time streaming, and row-level security.

|

Create quality playbooks with test requirements, performance benchmarks, release criteria, and rollback procedures.

Test a RAG pipeline end-to-end with relevance and groundedness metrics

Set up RBAC role assignments for a solution play's Azure resources

|

|

|

|

|

|

|

|

|

|

Implement semantic caching for AI responses with Redis and embedding similarity

|

|

Set up SLA monitoring with availability, latency, and quality metrics

|

|

|

|

|

|

Configure SSL certificates for custom domains on Azure App Service/AKS

Implement streaming AI responses with Server-Sent Events (SSE)

Enforce structured JSON output from LLMs with schema validation

|

|

|

|

|

|

|

|

Enforce token budgets per user/team with tracking and alerting

|

|

|

|

Tune Play 05 (IT Ticket Resolution) classifier routing, priority scoring, SLA thresholds, and escalation model config.

|

Tune Play 07 (Multi-Agent Service) agent orchestration, handoff rules, model routing, and inter-agent communication config.

Tune Play 08 (Copilot Studio Bot) topic routing, generative answers config, handoff triggers, and channel settings.

Tune Play 09 (AI Search Portal) semantic ranking, scoring profiles, suggesters, and index schema for optimal relevance.

Tune Play 10 (Content Moderation) severity thresholds, category blocklists, Prompt Shields config, and review workflows.

Tune Play 11 (AI Landing Zone Advanced) hub-spoke topology, private DNS, governance policies, and network segmentation.

Tune Play 12 (Model Serving AKS) GPU node pools, vLLM configuration, autoscaling policies, and inference optimization.

Tune Play 13 (Fine-Tuning Workflow) training hyperparameters, dataset validation, LoRA config, and evaluation metrics.

Tune Play 14 (Cost-Optimized AI Gateway) model routing rules, token budgets, caching policies, and APIM rate limiting.

Tune Play 15 multi-modal document processing with OCR, vision model selection, extraction confidence, and fallback routing.

Tune Play 16 Teams extension behavior with command routing, intent matching, adaptive card payloads, and auth flow.

Tune Play 17 observability settings for traces, semantic metrics, alert thresholds, and log retention policy.

Tune Play 18 prompt management with version gates, A/B split, rollback policy, and template lint checks.

Tune Play 19 edge deployment for Phi-4 with quantization, device constraints, and offline fallback behavior.

Tune Play 20 anomaly detection with window sizing, seasonality handling, threshold calibration, and alert suppression.

Tune Play 21 agentic RAG with planner depth, retrieval fan-out, reranker policy, and citation strictness.

Tune Play 22 swarm behavior with role assignment, consensus thresholds, conflict policy, and budget controls.

Tune Play 23 browser automation with selector strategy, retry policy, anti-flake waits, and safety restrictions.

Generate production-ready tutorials with prerequisites, runnable code, verification steps, and troubleshooting paths.

Create and populate a vector search index in Azure AI Search or Cosmos DB

Set up webhooks for AI system events: evaluation results, safety alerts, cost alerts