Primitives

fai-play-19-reviewer

Edge AI reviewer — quantized model quality audit, offline resilience testing, fleet rollout verification, cloud fallback review, and device security checks.

• reliability
• security

fai-play-20-reviewer

Real-Time Analytics reviewer — ingestion reliability audit, windowing correctness, anomaly detection accuracy, scoring logic review, and alert quality verification.

• reliability
• security

fai-play-22-builder

Swarm Orchestration builder — mesh/star/hierarchical agent topologies, supervisor task decomposition, agent specialization, shared memory via Cosmos DB, and conflict resolution.

• reliability
• performance-efficiency
• security

fai-play-22-reviewer

Swarm Orchestration reviewer — topology audit, supervisor logic review, agent specialization validation, shared memory consistency, and conflict resolution testing.

• reliability
• security

fai-play-23-builder

Browser Agent builder — Playwright MCP integration, GPT-4o Vision page navigation, multi-step web task automation, form filling, data extraction, and domain-restricted browsing.

• security
• reliability

fai-python-expert

Python development specialist — Python 3.12+, async/await patterns, Pydantic v2, FastAPI, pytest, type hints, Azure SDK, and production-grade AI application patterns.

• security
• reliability
• performance-efficiency

fai-python-mcp-expert

Python MCP server specialist — FastMCP framework, @mcp.tool() decorators, async handlers, Pydantic input models, uv deployment, and Azure service integration for AI tools.

• security
• reliability
• performance-efficiency

fai-rag-architect

Enterprise RAG architecture specialist — designs end-to-end retrieval-augmented generation pipelines with Azure AI Search, OpenAI embeddings, chunking strategies, grounding, citation, evaluation, and production deployment.

• security
• reliability
• cost-optimization
• performance-efficiency

fai-rust-expert

Rust specialist — ownership/borrowing, async with tokio, serde serialization, error handling with thiserror/anyhow, and high-performance AI infrastructure (inference proxies, MCP servers).

• security
• performance-efficiency
• reliability

fai-salesforce-expert

Salesforce specialist — Apex development, Lightning Web Components, Flow automation, Einstein AI, and enterprise CRM integration patterns with Azure OpenAI.

• reliability
• security

fai-sap-expert

SAP integration specialist — SAP BTP, OData APIs, BAPI/RFC connectors, procurement/inventory/order processing, and AI-enhanced enterprise resource planning.

• reliability
• security
• operational-excellence

fai-servicenow-expert

ServiceNow ITSM integration specialist — incident/change/request management via REST API, CMDB queries, knowledge base search, AI-powered ticket triage, and service catalog automation.

• reliability
• security
• operational-excellence

fai-solutions-architect

Cloud solutions architect — end-to-end AI solution design, Azure service selection, multi-service integration, cost estimation, WAF trade-off analysis, and architecture decision records.

• reliability
• cost-optimization
• performance-efficiency
• security

fai-supabase-expert

Supabase specialist — pgvector for AI embeddings, real-time subscriptions, Edge Functions (Deno), Row Level Security, Storage for documents, and Auth for user management in AI applications.

• reliability
• security

fai-terraform-expert

Terraform specialist — Azure provider, state management, module design, plan/apply workflow, drift detection, and multi-environment infrastructure deployment.

• operational-excellence
• reliability
• security

fai-typescript-expert

TypeScript/Node.js specialist — strict mode, Zod validation, ESM modules, Vitest testing, Azure SDK integration, async patterns, and production-ready AI application development.

• security
• reliability
• performance-efficiency

fai-typescript-mcp-expert

TypeScript MCP server specialist — @modelcontextprotocol/sdk, McpServer class, Zod schema validation, async tool handlers, stdio/SSE transport, and npm distribution.

• security
• reliability
• performance-efficiency

agent-coding-patterns

Agent coding standards — ReAct loop, tool selection, memory management, circuit breaker on tools.

• reliability
• security

agent-safety

AI agent safety standards — fail-closed defaults, least-privilege tool access, human-in-the-loop for destructive actions, prompt injection defense, budget controls, OWASP LLM Top 10 alignment, and governance audit trails for all agent workflows.

• security
• responsible-ai
• reliability

agentic-rag-patterns

Play 21 patterns — Agentic RAG patterns — retrieval decision loop, multi-source routing, query refinement, self-evaluation.

• reliability
• security

ai-landing-zone-advanced-patterns

Play 11 patterns — Advanced landing zone — multi-region, ExpressRoute, Azure Firewall, Policy as Code, Defender for Cloud.

• reliability
• security

ai-landing-zone-patterns

Play 02 patterns — Landing zone patterns — hub-spoke VNet, private endpoints on ALL PaaS, Managed Identity, tag enforcement, GPU quota.

• reliability
• security

ai-observability-patterns

Play 17 patterns — AI observability patterns — OpenTelemetry spans, token metrics, quality dashboards, alert thresholds.

• reliability
• security

ai-search-portal-patterns

Play 09 patterns — Search portal patterns — faceted search, semantic ranker, result rendering, analytics, personalization.

• reliability
• security