Primitives

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-fine-tuning-expert

Fine-tuning and MLOps specialist — LoRA/QLoRA techniques, JSONL training data preparation, Azure OpenAI fine-tuning workflow, hyperparameter tuning, evaluation-driven iteration, and model versioning.

• cost-optimization
• operational-excellence
• responsible-ai

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-neon-expert

Neon serverless Postgres specialist — database branching, auto-scaling compute, pgvector for AI embeddings, connection pooling, and database-per-branch development workflows.

• cost-optimization
• performance-efficiency

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-01-tuner

Enterprise RAG tuner — config optimization for search quality, token costs, chunking parameters, evaluation thresholds, and model selection economics.

• cost-optimization
• performance-efficiency

fai-play-02-tuner

AI Landing Zone tuner — network sizing, firewall rule optimization, SKU right-sizing, cost analysis, DR configuration, and production readiness verification.

• cost-optimization
• performance-efficiency

fai-play-03-tuner

Deterministic Agent tuner — confidence threshold optimization, guardrail severity calibration, evaluation metric tuning, retry config, and A/B testing for determinism quality.

• cost-optimization
• performance-efficiency

fai-play-04-tuner

Call Center Voice AI tuner — speech config optimization, neural voice selection, latency tuning, escalation thresholds, cost-per-call analysis, and CSAT metric targeting.

• cost-optimization
• performance-efficiency

fai-play-05-tuner

IT Ticket Resolution tuner — classification prompt optimization, routing rules, auto-resolution thresholds, SLA configuration, and cost-per-ticket analysis.

• cost-optimization
• performance-efficiency

fai-play-06-tuner

Document Intelligence tuner — OCR settings optimization, extraction confidence calibration, custom model training data, batch performance, and cost-per-document analysis.

• cost-optimization
• performance-efficiency

fai-play-07-tuner

Multi-Agent Service tuner — supervisor routing config, per-agent token budgets, loop limits, model selection per role, memory TTL, and orchestration cost analysis.

• cost-optimization
• performance-efficiency

fai-play-08-tuner

Copilot Studio Bot tuner — trigger phrase expansion, knowledge source optimization, response tone calibration, guardrail sensitivity, and conversation flow tuning.

• cost-optimization
• performance-efficiency

fai-play-09-tuner

AI Search Portal tuner — hybrid weight optimization, scoring profile calibration, reranker config, suggester tuning, and answer generation quality.

• cost-optimization
• performance-efficiency

fai-play-10-tuner

Content Moderation tuner — per-category severity calibration, blocklist optimization, false positive reduction, routing distribution, and moderation cost analysis.

• responsible-ai
• cost-optimization

fai-play-11-tuner

AI Landing Zone Advanced tuner — multi-region network sizing, firewall rule optimization, policy effect progression, GPU type selection, and DR cost optimization.

• cost-optimization
• performance-efficiency

fai-play-12-builder

Model Serving AKS builder — GPU cluster design, vLLM/TGI serving engines, NVIDIA device plugin, HPA/KEDA autoscaling, model versioning, and canary deployments.

• performance-efficiency
• reliability
• cost-optimization

fai-play-12-tuner

Model Serving AKS tuner — GPU SKU selection, vLLM memory/batching optimization, quantization decisions, autoscaling thresholds, and inference cost analysis.

• cost-optimization
• performance-efficiency

fai-play-13-builder

Fine-Tuning Workflow builder — Azure OpenAI fine-tuning, JSONL data preparation, LoRA/QLoRA techniques, MLflow experiment tracking, evaluation-driven iteration, and A/B deployment.

• operational-excellence
• cost-optimization
• responsible-ai

fai-play-13-tuner

Fine-Tuning Workflow tuner — learning rate scheduling, LoRA rank/alpha optimization, epoch calibration, batch sizing, data quality filtering, and training cost analysis.

• cost-optimization
• performance-efficiency

fai-play-14-builder

Cost-Optimized AI Gateway builder — APIM AI gateway, semantic caching with Redis, smart model routing by complexity, token budget enforcement, and multi-region load balancing.

• cost-optimization
• performance-efficiency
• reliability

fai-play-14-reviewer

Cost-Optimized AI Gateway reviewer — routing accuracy audit, cache quality verification, budget enforcement testing, security review, and cost savings validation.

• security
• cost-optimization