Skill UI

This SDK allows developers to build persistent, sophisticated AI agents directly on Azure AI Foundry. It supports complex conversational workflows by integrating external functions (tools), enabling code execution, web search, and maintaining conversation history through dedicated thread management. Ideal for developing enterprise-grade, production-ready AI applications.

Expertise in building production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, and complex intelligent agents. This skill covers the entire AI lifecycle, including model orchestration, vector search optimization, multimodal integration (vision/audio), MLOps deployment, and robust safety governance for enterprise-level AI solutions.

Expertise in building production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, and complex intelligent agents. This skill covers the entire AI lifecycle, including model orchestration, vector search optimization, multimodal integration (vision/audio), MLOps deployment, and robust safety governance for enterprise-level AI solutions.

A comprehensive, low-level Software Development Kit (SDK) for building and managing stateful AI Agents within the Azure AI ecosystem using .NET. This SDK provides core clients for managing agent lifecycles, persistent conversation threads, message history, complex run execution, tool/function calling, and integrating file search through vector stores. It is essential for developing enterprise-grade, multi-turn conversational AI applications.

A comprehensive, low-level Software Development Kit (SDK) for building and managing stateful AI Agents within the Azure AI ecosystem using .NET. This SDK provides core clients for managing agent lifecycles, persistent conversation threads, message history, complex run execution, tool/function calling, and integrating file search through vector stores. It is essential for developing enterprise-grade, multi-turn conversational AI applications.

This is a high-level SDK for .NET that provides comprehensive client access to Azure AI Foundry services. It enables developers to manage complex AI workflows, including creating and managing conversational agents, handling data connections, uploading datasets, managing model deployments, and setting up search indexes within an Azure AI project structure. Ideal for integrating advanced AI capabilities into enterprise applications.

The official SDK for interacting with Azure AI Search service using Python. It provides comprehensive functionality for advanced search retrieval, including full-text search, vector similarity search (HNSW), hybrid search, and semantic ranking. Use this tool to build sophisticated enterprise search applications that require deep content understanding and precise information retrieval.

A comprehensive guide and implementation pattern for enforcing granular Role-Based Access Control (RBAC) on the Exa search API in multi-tenant or enterprise environments. This skill demonstrates how to implement API key scoping, restrict search domains by role, enforce maximum result limits, and track daily usage to ensure robust data governance and security.

This system implements Role-Based Access Control (RBAC) for OpenEvidence, an AI-powered clinical decision support platform. It strictly manages access to sensitive data, including PHI-adjacent datasets and medical literature, ensuring compliance with regulations like HIPAA. The system defines distinct roles—Admin, Clinician, Researcher, Student, and Auditor—with granular permissions for querying, data export, and institutional configuration, maintaining a secure and auditable data environment.

This guide details how to implement Role-Based Access Control (RBAC) for Perplexity API in enterprise environments. Since Perplexity lacks native RBAC, the solution involves building a middleware gateway. This gateway enforces granular policies, including team-specific API key usage, model restriction (e.g., limiting access to 'sonar' only), budget caps, rate limiting, and mandatory search domain filtering for compliance and security.

Qdrant is a high-performance, Rust-powered vector database designed for production-grade RAG (Retrieval-Augmented Generation) and semantic search applications. It provides fast nearest neighbor search, supports complex hybrid search using metadata filtering, and offers horizontal scalability through sharding and replication. Ideal for building real-time recommendation systems and enterprise-level knowledge retrieval.

Expert in designing and implementing advanced Retrieval-Augmented Generation (RAG) pipelines. This role focuses on optimizing the entire information retrieval process—from document chunking and embedding model selection to vector database architectures and hybrid search strategies. The goal is to bridge the gap between raw knowledge documents and accurate LLM understanding, drastically reducing hallucination and enhancing context relevance for enterprise applications.