Design Handoff

Complete RAG pipeline for document ingestion, embedding, retrieval, and LLM-powered response generation.

Iterative evaluation and refinement patterns for improving AI agent outputs through self-critique loops.

Comprehensive safety analysis and improvement framework for AI prompts with detailed assessment methodologies.

Polish and refine agent prompt files against proven best practices.

Deploy and manage MCP-based declarative agents across Microsoft 365 with admin center governance, role-based access, and organizational distribution.

Scaffold a declarative agent for Microsoft 365 Copilot integrated with an MCP server.