Primitives

fai-play-07-builder

Multi-Agent Service builder — supervisor orchestration pattern, agent registry, shared state via Cosmos DB/Redis, Dapr integration, tool routing, and loop prevention.

• reliability
• security
• operational-excellence

fai-play-07-reviewer

Multi-Agent Service reviewer — orchestration logic audit, state management review, loop prevention verification, agent security boundaries, and Dapr configuration checks.

• security
• responsible-ai

fai-play-08-builder

Copilot Studio Bot builder — declarative agent setup, topic design, SharePoint/Dataverse knowledge grounding, Power Platform connectors, and conversation guardrails.

• reliability
• security
• operational-excellence

fai-play-08-reviewer

Copilot Studio Bot reviewer — topic coverage audit, knowledge source validation, DLP compliance, guardrail verification, and conversation flow testing.

• security
• responsible-ai

fai-play-09-builder

AI Search Portal builder — Azure AI Search index design, hybrid search with scoring profiles, faceted navigation, answer generation with citations, and auto-suggest.

• performance-efficiency
• reliability
• security

fai-play-09-reviewer

AI Search Portal reviewer — index schema audit, search relevance testing, answer citation accuracy, facet UX review, and performance benchmarking.

• security
• responsible-ai

fai-play-10-builder

Content Moderation builder — Azure Content Safety API integration, 4-category severity scoring, custom blocklists, APIM gateway middleware, and severity-based routing.

• responsible-ai
• security

fai-play-10-reviewer

Content Moderation reviewer — safety coverage audit, severity threshold verification, blocklist completeness, bypass prevention, and human review workflow testing.

• responsible-ai
• security

fai-play-11-builder

AI Landing Zone Advanced builder — multi-region hub-spoke, Azure Firewall Premium with TLS/IDPS, policy-driven governance at scale, GPU quota orchestration, and disaster recovery automation.

• reliability
• security
• operational-excellence

fai-play-11-reviewer

AI Landing Zone Advanced reviewer — multi-region networking audit, firewall rule review, policy compliance verification, GPU quota validation, and DR testing review.

• security
• reliability

fai-play-12-reviewer

Model Serving AKS reviewer — GPU cluster audit, vLLM config validation, autoscaling verification, pod security review, and inference latency benchmarking.

• security
• reliability

fai-play-13-reviewer

Fine-Tuning Workflow reviewer — training data quality audit, hyperparameter validation, evaluation methodology review, safety retesting, and alignment preservation checks.

• responsible-ai
• security

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

fai-play-15-builder

Document Processing builder — GPT-4o Vision multi-modal analysis, Azure Document Intelligence, table extraction, classification pipeline, and PII-aware storage.

• reliability
• security

fai-play-15-reviewer

Document Processing reviewer — multi-modal extraction accuracy audit, table parsing quality, PII masking verification, pipeline error handling, and classification accuracy review.

• security
• responsible-ai

fai-play-16-builder

Copilot Teams Extension builder — M365 Copilot declarative agent, Microsoft Graph API integration, Adaptive Cards, Entra ID SSO, and Teams message extension development.

• security
• reliability
• operational-excellence

fai-play-16-reviewer

Copilot Teams Extension reviewer — Graph permission audit, SSO flow testing, Adaptive Card rendering review, message extension validation, and Teams policy compliance.

• security
• responsible-ai

fai-play-16-tuner

Copilot Teams Extension tuner — Graph scope minimization, knowledge source config, response tone calibration, Adaptive Card optimization, and permission tuning.

• security
• performance-efficiency

fai-play-17-reviewer

AI Observability reviewer — telemetry coverage audit, KQL query accuracy, dashboard UX review, alert threshold calibration, and PII-in-logs verification.

• operational-excellence
• security

fai-play-18-reviewer

Prompt Optimization reviewer — version management audit, A/B test methodology review, template injection safety, evaluation pipeline validation, and prompt quality assessment.

• security
• responsible-ai

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