Sequential: a team working in order
Sequential is a relay: one stage’s output becomes the next stage’s input.
What you will learn
- Explain: a workflow has explicit structure
- Apply the idea in an example: Sequential: a team working in order
- Recognize limitations and verify the exercise outcome
Sequential is a relay: one stage’s output becomes the next stage’s input. Order matters and stages need clear contracts.
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.
Context is the workbench
Context includes instructions, the current request, relevant history, retrieved documents and tool results. The context window has limited capacity; reserve room for the response too. More text does not automatically improve accuracy. Irrelevant information and contradictions can hide important evidence. Summarize history carefully and preserve the origin of facts. State describes the current run, a checkpoint saves a resumable point, and persistent memory retains information across runs. These are different mechanisms managed by the application.
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.
Detailed lab
Contracts between stages
Ask the first agent for deadline, starting event and conditions without marketing prose. The second turns facts into an explanation; the third translates while preserving numbers. An intermediate example is “deadline=14; start=receipt; unused=true; packaging=original”.
If extraction omits packaging, the translator cannot recover it from input lacking that fact. Inspect every step. For independent branches, Sequential may be slower than Parallel; dependent stages cannot be parallelized without changing their logic.
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
Agent 1 extracts deadline and conditions. Agent 2 explains simply in Romanian. Agent 3 translates into English without changing numbers.
step_1: LunaExtractor
step_2: LunaExplainer
step_3: LunaTranslator
Try it yourself
- Create at least two stages and assign agents in extraction, explanation and translation order.
- Record the input, source and expected outcome before running the experiment. Use only the fictional data in the example.
- Follow the diagram stages. At every step record what information is received and produced; do not confuse intermediate output with the final outcome.
- Repeat after removing necessary information or making the input ambiguous. Check whether the system clarifies, stops or invents an answer.
- Compare with the explained solution. Keep the configuration, date, result and an explanation for differences. Change one thing and retest.
An explained solution
Both versions preserve 14 days and the unused condition. Check each output, not just the final translation. 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
An early error propagates unless detected. 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.
Is a checkpoint permanent user memory?
No. Saving a run does not imply retaining preferences across conversations.
What outcome should this exercise produce?
Both versions preserve 14 days and the unused condition. Check each output, not just the final translation.
Words to remember
- Nod: A stage in an execution graph.
- Checkpoint: Saved state used to resume an execution.
- Regresie / Regression: A change that breaks a previously correct case.
Sources and your next step
To prepare: W03 — Reflection: improving the first draft