Primitives

fai-mlflow-expert

MLflow specialist — experiment tracking, model registry, metric/artifact logging, Azure ML integration, deployment pipelines, and model lifecycle management.

• operational-excellence
• reliability

fai-mongodb-expert

MongoDB specialist — document schema design, aggregation pipelines, Atlas Vector Search for RAG, Cosmos DB MongoDB vCore, change streams, and AI application data patterns.

• performance-efficiency
• reliability

fai-nats-expert

NATS messaging specialist — JetStream for durable streams, key-value store, object store, request-reply, pub-sub, and lightweight event-driven AI microservice communication.

• reliability
• performance-efficiency

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-openapi-expert

OpenAPI specialist — API-first design, OpenAPI 3.1 spec authoring, code generation, validation middleware, and Copilot plugin API definition for AI applications.

• operational-excellence
• reliability

fai-opentelemetry-expert

OpenTelemetry specialist — distributed tracing, metrics, logs with OTLP protocol, auto-instrumentation, custom spans for AI pipelines, and Azure Monitor exporter integration.

• operational-excellence
• performance-efficiency

fai-pagerduty-expert

PagerDuty incident management specialist — alert routing, escalation policies, on-call scheduling, automated incident creation, and AI-specific runbook integration.

• reliability
• 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-php-expert

PHP 8.3+ specialist — modern PHP with attributes, typed properties, enums, fibers, Composer PSR standards, Laravel/Symfony patterns, and PHP-based AI API integration.

• security
• reliability

fai-php-mcp-expert

PHP MCP server specialist — PHP 8.3+ attributes for tool registration, PSR standards, Composer dependency management, typed properties for JSON Schema, and stdio transport.

• reliability
• security

fai-play-01-builder

Enterprise RAG builder — hybrid search pipeline (BM25+vector), Azure AI Search indexing, OpenAI chat completions with citations, chunking strategies, and evaluation-driven quality gates.

• reliability
• security
• operational-excellence

fai-play-01-reviewer

Enterprise RAG reviewer — RAG quality audit, citation accuracy, search config validation, security compliance, OWASP LLM Top 10, and WAF pillar alignment checks.

• security
• responsible-ai

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-builder

AI Landing Zone builder — hub-spoke networking, private endpoints, Azure Firewall, DNS architecture, identity foundation, and governance baseline for enterprise AI workloads.

• reliability
• security
• operational-excellence

fai-play-02-reviewer

AI Landing Zone reviewer — network security audit, private endpoint verification, identity compliance, Azure Policy enforcement, and Bicep infrastructure review.

• security
• responsible-ai

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-builder

Deterministic Agent builder — zero-temperature architecture, seed pinning, structured JSON output, multi-layer guardrails, confidence scoring, and anti-hallucination defense.

• reliability
• security
• operational-excellence

fai-play-03-reviewer

Deterministic Agent reviewer — reproducibility testing, guardrail completeness audit, anti-sycophancy verification, schema validation review, and confidence calibration checks.

• security
• responsible-ai

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-builder

Call Center Voice AI builder — STT→LLM→TTS streaming pipeline, Azure Communication Services, real-time transcription, intent classification, PII redaction, and escalation triggers.

• reliability
• security
• operational-excellence

fai-play-04-reviewer

Call Center Voice AI reviewer — voice quality audit, pipeline latency review, PII redaction verification, TCPA compliance, and escalation trigger testing.

• security
• responsible-ai

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-builder

IT Ticket Resolution builder — event-driven classification pipeline, auto-resolution via knowledge base, ServiceNow/Jira integration, skill-based routing, and SLA monitoring.

• reliability
• security
• operational-excellence

fai-play-05-reviewer

IT Ticket Resolution reviewer — classification accuracy audit, auto-resolution quality, routing fairness, SLA compliance, ServiceNow integration security, and PII handling review.

• security
• responsible-ai