What is an agentic AI system?
An agentic system organizes decisions, tools and state toward a goal.
What you will learn
- Explain: a workflow has explicit structure
- Apply the idea in an example: What is an agentic AI system?
- Recognize limitations and verify the exercise outcome
An agentic system organizes decisions, tools and state toward a goal. Choose coordination based on dependencies between steps.
You can follow this course without an account or programming. Examples use synthetic data and AI outcomes need checking.
How it works, step by step
The seven-template map
ReAct chooses the next action; Reflection revises a draft; Sequential applies fixed stages. Router selects a branch, Orchestrator dynamically delegates and combines results, Parallel distributes independent tasks, and Plan-and-Execute maintains and revises a plan. Ask who decides, where results return and what stops execution.
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
A support response may need simple retrieval, routing to a specialist or a team. For FAQ, one agent with RAG is a good starting point.
Try it yourself
- Compare a fixed task, an exploratory task and independent subtasks.
- 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
Choose a template by roles and dependencies rather than maximum agent count. 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
A workflow graph and a knowledge graph describe different things. 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 more autonomy always give a better result?
No. It also increases room for errors, costs and unnecessary actions.
What outcome should this exercise produce?
Choose a template by roles and dependencies rather than maximum agent count.
Words to remember
- Nod: A stage in an execution graph.
- Agent: A system that can choose steps and use tools toward a goal.
- Regresie / Regression: A change that breaks a previously correct case.
Sources and your next step
To prepare: A01 — Anatomy of an AI agent · P02 — Context engineering: what reaches the model?