Primitives

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

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-23-reviewer

Browser Agent reviewer — domain allowlist verification, vision accuracy testing, credential security audit, error recovery review, and task completion validation.

• security
• responsible-ai

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-react-expert

React/Next.js specialist — React 19 Server Components, Suspense streaming for AI chat, App Router, Tailwind CSS, useActionState, and accessibility-first patterns.

• performance-efficiency
• security
• responsible-ai

fai-red-team-expert

AI red teaming specialist — prompt injection testing, jailbreak simulation, PyRIT automation, bias detection, adversarial dataset creation, and OWASP LLM Top 10 validation.

• security
• responsible-ai

fai-responsible-ai-reviewer

Responsible AI specialist — bias detection, fairness metrics, transparency requirements, EU AI Act compliance, content safety, groundedness evaluation, and AI governance frameworks.

• responsible-ai
• security

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-rust-mcp-expert

Rust MCP server specialist — rmcp SDK, tokio async handlers, proc macro tool registration, serde for schemas, and ultra-high-performance MCP tool serving.

• performance-efficiency
• security

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-security-reviewer

Security reviewer — audits code, infrastructure, and AI pipelines against OWASP Top 10, OWASP LLM Top 10, Azure security baselines, managed identity compliance, network isolation, and secrets management.

• security
• responsible-ai

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