Primitives

fai-ai-infra-expert

AI infrastructure expert — GPU compute sizing (A100/H100), VRAM estimation, model serving (vLLM/TensorRT-LLM/Triton), AKS node pool design, PTU vs PAYG cost modeling, and quantization strategies.

• performance-efficiency
• cost-optimization
• reliability

fai-api-gateway-designer

API gateway architect — Azure APIM patterns, rate limiting, token-based throttling, multi-region load balancing, backend circuit breakers, and cost-aware routing for LLM endpoints.

• cost-optimization
• reliability
• performance-efficiency

fai-architect

Senior cloud-native solution architect — Azure Well-Architected Framework alignment, AI system design, multi-service integration, cost modeling, trade-off analysis, and production readiness assessment.

• reliability
• security
• cost-optimization
• performance-efficiency
• +2

fai-azure-aks-expert

Azure Kubernetes Service specialist — GPU node pools (A100/H100), NVIDIA device plugin, model serving with vLLM/TGI/Triton, HPA/KEDA autoscaling, and production AI inference workload patterns.

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

fai-azure-apim-expert

Azure API Management specialist — AI Gateway patterns, semantic caching, token metering, multi-backend load balancing, circuit breaker, rate limiting, and FinOps for LLM API layers.

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

fai-azure-container-apps-expert

Azure Container Apps specialist — serverless containers, Dapr sidecars, KEDA autoscaling, GPU workload profiles, scale-to-zero, and AI agent hosting patterns with blue/green deployments.

• cost-optimization
• reliability
• operational-excellence

fai-azure-event-hubs-expert

Azure Event Hubs specialist — partitioned event streaming, Kafka compatibility, Schema Registry governance, real-time AI inference pipelines, and high-throughput data ingestion.

• performance-efficiency
• reliability
• cost-optimization

fai-azure-logic-apps-expert

Azure Logic Apps specialist — low-code workflow automation, 1400+ connectors, AI integration actions, Durable orchestration, B2B/EDI, and enterprise integration patterns.

• operational-excellence
• reliability
• cost-optimization

fai-azure-monitor-expert

Azure Monitor specialist — Application Insights for AI distributed tracing, KQL for token analytics, custom dashboards for groundedness/coherence metrics, cost alerting, and AI-specific observability patterns.

• operational-excellence
• cost-optimization
• reliability

fai-azure-openai-expert

Azure OpenAI specialist — model deployment types (PTU/PAYG/Global), content filtering, structured output, token optimization, multi-region load balancing, and production inference patterns.

• cost-optimization
• performance-efficiency
• security
• responsible-ai

fai-azure-sql-expert

Azure SQL specialist — Hyperscale, serverless auto-pause, native vector search, geo-replication, intelligent performance tuning, and AI integration patterns with embeddings storage.

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

fai-azure-storage-expert

Azure Storage specialist — Blob lifecycle tiers, ADLS Gen2 for data lakes, private endpoints, managed identity auth, and document/model artifact storage for AI pipelines.

• security
• cost-optimization
• reliability

fai-batch-processing-expert

Batch processing specialist — Azure Batch pools, Global Batch API (50% cost savings), Durable Functions fan-out, large-scale document/embedding pipelines, and async LLM inference patterns.

• cost-optimization
• reliability
• performance-efficiency

fai-capacity-planner

AI capacity planning specialist — GPU sizing, PTU allocation, token volume forecasting, cost modeling, scaling strategy, and FinOps for Azure AI workloads.

• cost-optimization
• performance-efficiency
• reliability

fai-collective-orchestrator

Multi-agent orchestrator — routes tasks to specialist agents, manages turn limits, decomposes complex requests, synthesizes results, and ensures quality gates across the FAI Collective.

• reliability
• cost-optimization
• operational-excellence

fai-cost-optimizer

FinOps cost optimizer for AI workloads — model routing economics, semantic caching ROI, token budget design, PTU vs PAYG analysis, right-sizing recommendations, and Azure cost attribution.

• cost-optimization
• performance-efficiency

fai-dspy-expert

DSPy framework specialist — declarative LM programs, signature-based modules, optimizers (BootstrapFewShot, MIPRO), assertions, metric-driven prompt optimization, and compiled prompt pipelines.

• performance-efficiency
• cost-optimization
• reliability

fai-embedding-expert

Embedding specialist — text-embedding-3 model selection, Matryoshka dimension reduction, batch embedding pipelines, similarity metrics, chunking strategies, and vector database integration for RAG.

• cost-optimization
• performance-efficiency

fai-event-driven-expert

Event-driven architecture specialist — Azure Event Grid, Service Bus, Event Hubs selection, event sourcing, CQRS, saga orchestration, and exactly-once processing patterns for AI pipelines.

• reliability
• performance-efficiency
• cost-optimization

fai-genai-foundations-expert

GenAI foundations expert — transformer architecture, tokenization, inference optimization (KV cache, speculative decoding), model taxonomy, prompt engineering theory, and evaluation benchmarks.

• performance-efficiency
• cost-optimization

fai-llm-landscape-expert

LLM landscape expert — model families (GPT, Claude, Llama, Gemini, Phi), benchmarks (MMLU, HumanEval, MT-Bench), deployment types, quantization, and model selection frameworks.

• cost-optimization
• performance-efficiency

fai-ml-engineer

ML engineering specialist — model training pipelines, LoRA/QLoRA fine-tuning, evaluation metrics, MLOps with Azure AI Foundry, model registry, and serving optimization for production AI.

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

fai-performance-profiler

Performance profiling specialist — latency analysis (P50/P95/P99), token optimization, GPU utilization profiling, bottleneck identification, cold start analysis, and AI pipeline performance tuning.

• performance-efficiency
• cost-optimization

fai-play-dispatcher

FAI play dispatcher — routes user requests to the correct solution play based on intent classification, understands all 101 plays and their domains, delegates to specialist agents.

• cost-optimization
• operational-excellence