Primitives

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-21-builder

Agentic RAG builder — autonomous retrieval agent, multi-source fusion (Search+web+DB), iterative query refinement, citation pipeline, and reflection-based quality gates.

• reliability
• performance-efficiency

fai-play-21-reviewer

Agentic RAG reviewer — retrieval autonomy audit, source selection review, iteration limit verification, citation accuracy check, and reflection quality assessment.

• reliability
• responsible-ai

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-play-lifecycle

FAI play lifecycle manager — handles play initialization (scaffold file structure), Bicep deployment, evaluation quality gates, and config tuning for any of the 101 solution plays.

• operational-excellence
• reliability
• cost-optimization

fai-postgresql-expert

PostgreSQL specialist — pgvector for embedding storage, HNSW/IVFFlat indexes, query optimization with EXPLAIN ANALYZE, connection pooling (PgBouncer), partitioning, and RAG vector store patterns.

• performance-efficiency
• reliability

fai-production-patterns-expert

Production AI patterns expert — hosting selection (Container Apps/AKS/Functions), APIM gateway patterns, streaming SSE, retry/circuit-breaker, health checks, and multi-region deployment for production AI workloads.

• reliability
• performance-efficiency
• cost-optimization
• operational-excellence

fai-prompt-engineer

Prompt engineering specialist — system message design, few-shot patterns, chain-of-thought, structured output schemas, anti-hallucination techniques, and evaluation-driven prompt optimization.

• reliability
• responsible-ai
• cost-optimization

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-rag-expert

RAG expert — advanced retrieval patterns (agentic, graph, multi-modal RAG), chunking strategies, hybrid search, re-ranking, evaluation metrics, and production RAG optimization.

• reliability
• performance-efficiency
• cost-optimization

fai-refactoring-expert

Code refactoring specialist — extract method, reduce cyclomatic complexity, improve testability, SOLID principles, design pattern application, and safe behavior-preserving transformations.

• reliability
• performance-efficiency

fai-remix-expert

Remix framework specialist — nested routing, loaders/actions, progressive enhancement, streaming SSR, error boundaries, and AI-integrated full-stack patterns.

• performance-efficiency
• reliability

fai-ruby-expert

Ruby 3.3+ specialist — pattern matching, Ractor concurrency, block DSL patterns, Rails 8, RuboCop standards, and AI API integration with httprb and ActiveJob.

• reliability
• operational-excellence

fai-ruby-mcp-expert

Ruby MCP server specialist — mcp-rb gem, block DSL tool definitions, Rails integration, idiomatic Ruby patterns, and stdio transport for AI tool development.

• reliability

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-semantic-kernel-expert

Semantic Kernel specialist — plugins with function calling, KernelFilter middleware, memory/vector stores, agent group chat orchestration, and RAG pipeline patterns in C#/Python.

• reliability
• 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-slack-expert

Slack integration specialist — Bot API, Block Kit UI, slash commands, interactive modals, AI-powered conversation summarization, thread-based notifications, and incident war room automation.

• operational-excellence
• reliability