Build AG-UI protocol clients and servers with the Microsoft Agent Framework .NET SDK (Microsoft.Agents.AI.AGUI + Microsoft.Agents.AI.Hosting.AGUI.AspNetCore). Use when exposing an AIAgent over HTTP with server-sent events, building remote agent clients, supporting frontend tool rendering, agentic generative UI, predictive state updates, shared state, or human-in-the-loop UX. Covers AGUIChatClient, MapAGUI, AddAGUI, session storage, DelegatingAIAgent, and the AgentResponseUpdate streaming contract.
Build AG-UI (Agent UI) protocol servers and clients in Python with the Microsoft Agent Framework (`agent-framework-ag-ui`). Use when hosting an `Agent` or `Workflow` as a streaming HTTP endpoint via `add_agent_framework_fastapi_endpoint`, consuming an AG-UI server with `AGUIChatClient`, wiring hybrid client-side + server-side tool calls, managing thread-scoped state and conversation continuity, returning rich tool payloads via `state_update`, or implementing the seven standard AG-UI features (chat, backend tool rendering, human-in-the-loop, generative UI, tool-based UI, shared state, predictive state updates).
Build local GitHub Copilot–backed agents using the Microsoft Agent Framework for .NET (Microsoft.Agents.AI.GitHub.Copilot). Use when creating agents with CopilotClient + AsAIAgent that delegate to the GitHub Copilot CLI, configuring permission handlers (shell, read, write, url, mcp), managing Copilot sessions for multi-turn conversations, registering local/HTTP MCP servers, applying skill directories, enforcing function-tool approval, and streaming responses. Covers function tools (AIFunctionFactory), runtime SessionConfig overrides, and multi-permission workflows.
Build deterministic, multi-step workflows with the Microsoft Agent Framework .NET SDK (Microsoft.Agents.AI.Workflows). Use when composing executors and edges into a DAG, running agents as graph nodes, doing fan-out/fan-in concurrency, conditional routing, shared state, streaming events, checkpoint/resume, human-in-the-loop request ports, or higher-level orchestration patterns (sequential, concurrent, handoff, group chat, Magentic). Covers WorkflowBuilder, AgentWorkflowBuilder, IWorkflowContext, CheckpointManager, and the StreamingRun event loop.
Build deterministic multi-step, multi-agent workflows in Python with the Microsoft Agent Framework (`agent-framework`). Use when composing `Executor` nodes and edges, embedding `Agent` instances as workflow nodes, streaming workflow events, fan-out/fan-in, conditional routing, loops, checkpointing and resume, human-in-the-loop with `ctx.request_info()`, sub-workflows with `WorkflowExecutor`, wrapping a workflow as an agent with `workflow.as_agent()`, or using the high-level orchestration builders (`SequentialBuilder`, `ConcurrentBuilder`, `HandoffBuilder`, `GroupChatBuilder`, `MagenticBuilder`).
ZavaShop domain knowledge — product catalog schema, SKU format, warehouse codes, order lifecycle states, supply-chain entities, and locations of the workshop's sample data files. Use whenever a task references ZavaShop, Zava products, Zava warehouses, Zava orders, retail or supply-chain scenarios in this workshop.
Build local GitHub Copilot–backed agents using the Microsoft Agent Framework Python SDK (agent-framework-github-copilot). Use when creating agents with GitHubCopilotAgent that delegate to the GitHub Copilot CLI, configuring permission handlers (shell, read, write, url, mcp), managing Copilot sessions for multi-turn conversations, registering local/HTTP MCP servers, applying instruction directories, enforcing function-tool approval, and streaming responses. Covers function tools, runtime option overrides, and multi-permission workflows.