AI PROJECT · WORKFLOW DEMONSTRATION
Turn Repetitive Work into
a Reviewable AI-Assisted Workflow
A practical demonstration of how AI can process and structure information while accountable owners review critical steps before outputs are used.
Project status
Demonstration
Business problem
Many workflows still rely on manually copying data, reformatting it, and checking it again by hand.
Why the problem matters
The gap isn't a lack of AI — it's that the steps, AI's role, and the review points haven't been designed yet.
Who this is for
Built for executives and teams who want a concrete example of an AI-assisted workflow with clear review points, before considering how the approach might apply to their own work.
Project purpose
Demonstrate workflow design end to end — from process map to error handling — with review by an accountable owner treated as part of the design, not an afterthought.
Chanikan's role
Designed the trigger–action–output pattern, placed the review points, and wrote the pre-launch safety checklist.
Tools and technology
- n8n for workflow design
- Google Sheets as source and destination
- A large language model for text-generation steps
- A self-written safety checklist
Workflow overview
Workflow
- Map the process as it is done manually today
- Define trigger, action, and output for each step
- Design the prompt chain for AI-assisted steps
- Insert review by the accountable owner before any externally visible step
- Add error handling and failure notification
Expected output
- A readable workflow map
- A sample workflow running on fictional data
- A pre-launch safety checklist
Example application
Illustrative workflow example
Weekly business performance summary
Input
- Synthetic sales data
- Campaign notes
- Operational updates
AI-assisted process
- Organise the information into one structure
- Identify notable changes
- Prepare a structured summary
Human Review
- Verify the numbers
- Confirm context
- Remove unsupported conclusions
Output
- A management-ready summary
Review by the accountable owner
AI can prepare and structure outputs, but an accountable owner must review accuracy, context and suitability before use.
Responsible AI and data boundaries
- Examples use public, sample, or synthetic data
- Customer data, personal data, or confidential data should never be entered into a public demo
- AI output must be reviewed before it is used
- This project demonstrates an approach — it is not a fully autonomous enterprise system
Current limitations
- A demonstration of the design approach, not an organisational deployment
- Runs on fictional data only
- Not designed for enterprise-scale throughput
Next development stage
Package it as a step-by-step exercise for the Build Your First AI Workflow course.
Chanikan's methodology
Chanikan Kanchanasalee
AI-Native Business Strategist specialising in Commercial Growth
Experienced in leading cross-functional work across Commercial Growth, Marketing, Sales, CRM, Data and Operations.