An AI support team

This project compares one agent with a team. Each specialist needs an observable responsibility.

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.

The model proposes, the tool executes

Tool calling produces a call request with a name and arguments. The application validates the schema, permissions and limits before execution. The result returns to context for the next step. For example, get_product_stock takes a SKU and returns a quantity; its description should explain that it does not reserve products. Distinguish empty results, validation errors, missing access and timeouts. Valid JSON does not prove the arguments are correct or the action is authorized. For external effects, also consider duplicate execution.

Define success before optimizing

Prepare representative requests and expected answers or properties. Include ordinary cases, ambiguity, missing data and tool errors. For RAG, measure evidence retrieval separately from answer correctness. Recall@k measures the share of relevant evidence found in the first k results; precision@k measures the share of returned results that are relevant. For agents, also track actions, permissions and stopping. An LLM-as-judge can speed evaluation but needs calibration against humans. Do not change prompt, model and index simultaneously if you want to understand what improved results.

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. The router is the illustrated implementation. Compare it separately with an orchestrator and a single-agent baseline. On smaller screens, scroll horizontally to follow the entire diagram.

A complete example

Specialists handle products, delivery and returns. Router handles one intent; Orchestrator can coordinate two needs. Use identical fictional data and tests for both configurations.

Fictional exercise data

Source	Information to use
Catalog	LX-240 uses part P-12; P-12 uses adapter A-7.
Returns	Requests within 14 days of receipt; unused product in original packaging.
Delivery	Estimated 2–3 business days after dispatch, not guaranteed.

Starter questions: “Which adapter does LX-240 use?”, “Can I return a used product?” and “How long does delivery take?”. Add ambiguous and unanswerable cases. Keep the same source in every comparison.

Try it yourself

1. Build Orchestrator with two workers and compare with the baseline agent on ten requests.
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

The report explains when a team improves outcomes and when it adds unnecessary delegation. 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

If role validation prevents saving Router, do not declare that lab successful. 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.

Who executes a call proposed by the model?

The application or host service after validation. The model does not automatically gain unrestricted access.

What outcome should this exercise produce?

The report explains when a team improves outcomes and when it adds unnecessary delegation.

Words to remember

• Nod: A stage in an execution graph.
• Tool calling: A structured request to use an external capability.
• Regresie / Regression: A change that breaks a previously correct case.

Sources and your next step

• LangGraph — Workflows and agents

To prepare: W05 — Orchestrator: coordinator and specialists · W06 — Router: send requests to the right specialist · W09 — Multi-agent: choosing and combining patterns · E01 — How to measure whether AI is useful