A map of the application

Organizations and projects provide the workspace. Agents, knowledge, tools and widgets connect within it.

These steps refer to features identified in the application code. This material has not been validated on a live instance; check the documentation and the options in your version.

How it works, step by step

A workflow has explicit structure

A node is a stage, an edge is a transition, and state carries results between stages. A workflow has an application-defined path, although the model may choose some branches. Agentic systems include both workflows and dynamically acting agents. Nymrio offers ReAct, Reflection, Sequential, Orchestrator, Router, Parallel and Plan-and-Execute. Each changes coordination; it does not automatically make a model an expert. More agents mean more calls and contracts between roles. Start with the simplest solution that passes your tests.

RAG accesses evidence, it does not retrain

RAG means retrieval-augmented generation: retrieval supplies relevant passages before the model answers. Ingestion prepares documents, while query execution searches the index and builds context. An embedding model represents text numerically; the response model writes the answer. Rerankers, vision, graph and router models have different roles when needed. RAG helps with private or changing information but does not guarantee truth. Use an authorized API for balances, exact inventory or permissions; an old document is not a reliable source for current state.

Host, client and server

MCP is a protocol connecting AI applications to external capabilities. The host provides the experience, the client manages the connection, and the server exposes tools, resources or prompts according to support. Tools execute operations; resources provide addressable content; prompts provide templates. Not every server implements all three. Transport carries messages, authentication identifies callers, and authorization controls access. Check protocol revision and supported extensions at both ends. Compatibility cannot be inferred from an “MCP” label alone.

The visual map

Follow the solid arrows for the main flow. Dashed blue arrows supply data or context; dashed pink arrows show feedback or returning results. Colors and shapes distinguish models, stores, decisions and outputs. On smaller screens, scroll horizontally to follow the entire diagram.

A complete example

Luna Workshop contains a policy RAG, guide agent, stock server and widget. Groups organize lists; do not assume they enforce access boundaries.

Try it yourself

1. Create a test project and draw entity relationships.
2. Record the input, source and expected outcome before running the experiment. Use only the fictional data in the example.
3. Follow the diagram stages. At every step record what information is received and produced; do not confuse intermediate output with the final outcome.
4. Repeat after removing necessary information or making the input ambiguous. Check whether the system clarifies, stops or invents an answer.
5. Compare with the explained solution. Keep the configuration, date, result and an explanation for differences. Change one thing and retest.

An explained solution

You can explain each entity and verify the active project before changes. A successful exercise lets you show the connection between input, stages and outcome. When information is missing, a cautious answer is more useful than invented details. Compare more than style: check conditions, sources and operations too.

When it helps and what can go wrong

The active project affects visible and usable entities. Choose this approach when it improves a measured need. Keep a simple baseline and compare outcomes using identical inputs. One successful example does not establish reliability in every situation.

Check your understanding

Is multi-agent an eighth template?

No. It is an architectural category that can use several existing templates.

Does RAG change LLM parameters?

No. It supplies request-time context; parameter changes belong to training.

What outcome should this exercise produce?

You can explain each entity and verify the active project before changes.

Words to remember

• Nod: A stage in an execution graph.
• Retrieval: Finding relevant information in accessible sources.
• MCP server: A service exposing capabilities through Model Context Protocol.

Sources and your next step

• LangGraph — Workflows and agents
• Lewis et al. — Retrieval-Augmented Generation
• Model Context Protocol — Specification

To prepare: F06 — Chatbot, assistant, agent and agentic system