{
  "query": "rag",
  "total": 41,
  "data": [
    {
      "type": "agents",
      "id": "fai-azure-storage-expert",
      "name": "FAI Azure Storage Expert",
      "description": "Azure Storage specialist — Blob lifecycle tiers, ADLS Gen2 for data lakes, private endpoints, managed identity auth, and document/model artifact storage for AI pipelines.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-graphrag-expert",
      "name": "FAI GraphRAG Expert",
      "description": "GraphRAG specialist — entity extraction, relationship mapping, knowledge graph construction, community detection, graph-based retrieval with Cosmos DB Gremlin/Neo4j, and hybrid graph+vector search.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-play-01-builder",
      "name": "FAI Enterprise RAG Builder",
      "description": "Enterprise RAG builder — hybrid search pipeline (BM25+vector), Azure AI Search indexing, OpenAI chat completions with citations, chunking strategies, and evaluation-driven quality gates.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-play-01-reviewer",
      "name": "FAI Enterprise RAG Reviewer",
      "description": "Enterprise RAG reviewer — RAG quality audit, citation accuracy, search config validation, security compliance, OWASP LLM Top 10, and WAF pillar alignment checks.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-play-01-tuner",
      "name": "FAI Enterprise RAG Tuner",
      "description": "Enterprise RAG tuner — config optimization for search quality, token costs, chunking parameters, evaluation thresholds, and model selection economics.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-play-21-builder",
      "name": "FAI Agentic RAG Builder",
      "description": "Agentic RAG builder — autonomous retrieval agent, multi-source fusion (Search+web+DB), iterative query refinement, citation pipeline, and reflection-based quality gates.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-play-21-reviewer",
      "name": "FAI Agentic RAG Reviewer",
      "description": "Agentic RAG reviewer — retrieval autonomy audit, source selection review, iteration limit verification, citation accuracy check, and reflection quality assessment.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-play-21-tuner",
      "name": "FAI Agentic RAG Tuner",
      "description": "Agentic RAG tuner — iteration depth config, source weight optimization, reflection threshold calibration, citation requirements, and per-query cost analysis.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-rag-architect",
      "name": "FAI RAG Architect",
      "description": "Enterprise RAG architecture specialist — designs end-to-end retrieval-augmented generation pipelines with Azure AI Search, OpenAI embeddings, chunking strategies, grounding, citation, evaluation, and ",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-rag-expert",
      "name": "FAI RAG Expert",
      "description": "RAG expert — advanced retrieval patterns (agentic, graph, multi-modal RAG), chunking strategies, hybrid search, re-ranking, evaluation metrics, and production RAG optimization.",
      "relevance": 2
    },
    {
      "type": "plugins",
      "id": "agentic-rag",
      "name": "agentic-rag",
      "description": "Autonomous RAG where the AI agent controls retrieval — decides when to search, which sources to query, iterates on results.",
      "relevance": 2
    },
    {
      "type": "agents",
      "id": "fai-azure-ai-search-expert",
      "name": "FAI Azure AI Search Expert",
      "description": "Azure AI Search specialist — HNSW vector indexes, hybrid keyword+vector retrieval, semantic ranker, integrated vectorization pipelines, custom skillsets, scoring profiles, and RAG optimization for pro",
      "relevance": 1
    },
    {
      "type": "agents",
      "id": "fai-azure-cosmos-db-expert",
      "name": "FAI Azure Cosmos DB Expert",
      "description": "Azure Cosmos DB specialist — partition key design, DiskANN vector search, multi-region writes, RU optimization, change feed processing, and conversation/session storage for AI agents.",
      "relevance": 1
    },
    {
      "type": "agents",
      "id": "fai-azure-sql-expert",
      "name": "FAI Azure SQL Expert",
      "description": "Azure SQL specialist — Hyperscale, serverless auto-pause, native vector search, geo-replication, intelligent performance tuning, and AI integration patterns with embeddings storage.",
      "relevance": 1
    },
    {
      "type": "agents",
      "id": "fai-cloudflare-expert",
      "name": "FAI Cloudflare Expert",
      "description": "Cloudflare specialist — Workers AI for edge inference, Workers KV, D1 database, R2 storage, AI Gateway, and CDN optimization for AI application delivery.",
      "relevance": 1
    },
    {
      "type": "agents",
      "id": "fai-data-engineer",
      "name": "FAI Data Engineer",
      "description": "Data engineering specialist for AI — RAG ingestion pipelines, document chunking, ETL/ELT patterns, PII detection with Presidio, data quality scoring, and Azure Data Factory orchestration.",
      "relevance": 1
    },
    {
      "type": "agents",
      "id": "fai-deterministic-expert",
      "name": "FAI Deterministic Expert",
      "description": "Deterministic AI specialist — makes AI outputs reproducible, grounded, and auditable with temperature control, seed pinning, JSON schema output, RAG grounding, citation enforcement, and multi-layer ha",
      "relevance": 1
    },
    {
      "type": "agents",
      "id": "fai-elasticsearch-expert",
      "name": "FAI Elasticsearch Expert",
      "description": "Elasticsearch specialist — index design, BM25 + kNN hybrid search, vector fields with HNSW, ILM lifecycle, cluster management, and RAG integration patterns.",
      "relevance": 1
    },
    {
      "type": "agents",
      "id": "fai-embedding-expert",
      "name": "FAI Embedding Expert",
      "description": "Embedding specialist — text-embedding-3 model selection, Matryoshka dimension reduction, batch embedding pipelines, similarity metrics, chunking strategies, and vector database integration for RAG.",
      "relevance": 1
    },
    {
      "type": "agents",
      "id": "fai-langchain-expert",
      "name": "FAI LangChain Expert",
      "description": "LangChain framework specialist — LCEL expression language, chains, agents with tool use, retrievers, memory, callbacks, LangSmith tracing, and production RAG pipeline patterns.",
      "relevance": 1
    }
  ]
}