Learning outcomes:

By the end of the programme, participants will be able to:

• Explain what makes an AI agent different from a chatbot.

• Design an agentic workflow using triggers, inputs, tasks, outputs, and human review points.

• Build or simulate a basic no-code / low-code AI workflow prototype.

• Test and refine AI workflow outputs.

• Identify privacy, accuracy, and governance considerations.

• Present an AI prototype concept and implementation roadmap.

Learner deliverables:

• Agentic Workflow Canvas.

• Prototype or prototype simulation.

• Testing and risk checklist.

• Implementation roadmap.

• Capstone presentation.

Key topics include:

• Difference between chatbot, copilot, automation, and AI agent.

• Anatomy of an agentic workflow: trigger, input, task, context, logic, tool, output, and review.

• Workflow logic and automation design.

• Prompt chaining and conditional routing.

• Human-in-the-loop approval design.

• Knowledge, data, and context design.

• Testing and evaluation of AI outputs.

• Guided prototype build and capstone presentation.