Course Outline
Day 1: Workflows and the AI Step
Introduction
- Determining when to automate, when to implement AI steps, and when to deploy agents
- n8n in context: understanding cloud versus self-hosted deployments and their implications for company data
n8n Fundamentals
- Overview of workflows, nodes, triggers, and executions
- Transferring data between nodes by dragging fields, eliminating the need for syntax entry
- Interpreting execution logs to identify and resolve issues
Connecting Apps and Data
- Utilising webhooks and form triggers
- Integrating spreadsheets, email, and calendar nodes
- Managing credentials and authentication for external services
- A step-by-step guide to the HTTP Request node
The AI Step
- Incorporating models into a workflow
- Crafting prompts that ensure reliable output
- Achieving structured output and automatically correcting malformed responses
- Classifying and extracting information from emails, forms, and documents
Decision Making and Actions
- Implementing branching logic with If and Switch nodes
- Establishing approval steps to seek human input before actions are executed
- Recording results in spreadsheets and dispatching notifications
Hands-on Lab: First End-to-End Workflow
- Transitioning from an incoming request to a classified, recorded, and routed outcome
Day 2: Agents and Operations
Agents
- Defining agents: models, memory, and tools
- Choosing between fixed workflows and agents
- Providing agents with access to company documents and spreadsheets
Agents That Act
- Distinguishing between read and write tools
- Setting system prompt rules: enforcing required fields, preventing data fabrication, and avoiding duplicate records
- Stress-testing agents to ensure robustness
Channels
- Implementing a chat interface for internal use
- Connecting agents to a single messaging channel
Reliability
- Configuring error workflows, retries, and notifications
- Analysing logs and execution history
- Managing model and execution costs
Data and Privacy
- Understanding what data is transmitted externally when a model is invoked
- Demonstration of self-hosting and local models by the instructor
- Creating a review checklist for IT or legal teams
Building Workflows with AI
- Using an AI assistant to draft a workflow
- Reviewing the draft: analysing node functions, data sources, and handling empty states
Final Project and Next Steps
- Participants complete and present a workflow featuring an AI step and an agent applied to their own process
- Developing a maintenance plan and identifying future automation candidates
Deliverable: A functional workflow incorporating an AI step, an agent connected to company data, error handling mechanisms, and a review checklist.
Requirements
- No prior programming experience is required
- Familiarity with web applications and spreadsheets
- A clear understanding of at least one repetitive process within their current workflow
Target Audience
- Professionals in business, operations, and customer-facing roles
- Team leaders and process owners
- Non-technical staff seeking to build automations and AI agents using company data
Testimonials (3)
The trainer is patient and very helpful. He knows the topic well.
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
Course - Agentic AI for Business Automation: Use Cases & Integration
Good mixvof knowledge and practice
Ion Mironescu - Facultatea S.A.I.A.P.M.
Course - Agentic AI for Enterprise Applications
The mix of theory and practice and of high level and low level perspectives
