AI in Data Visualisation
Augmenting Our Ability to Generate Visual Data Narratives. Artificial Intelligence is reshaping the way we approach data storytelling. This presentation explores how AI is diminishing the time needed for context-setting and analysis, making unstructured data more accessible, and elevating prompting as the new must-have skill.
AI in Data Visualisation
Augmenting Our Ability to Generate Visual Data Narratives
Felipe Rego
Data Analytics and Visualisation Expert
Contact: felipe@feliperego.com.au
LinkedIn: linkedin.com/in/feliperego
YouTube: youtube.com/@FelipeRego
Opening Hook: AI Is Redefining Data Storytelling
What if the steps we spent years mastering in data viz are no longer needed?
Visual Concept: Old vs new model side-by-side (CDW vs AI framework)
Purpose: Capture attention and set the tone for a transformative discussion about how AI is fundamentally changing data storytelling workflows.
The Classic Workflow
Traditional Framework: Context → Investigate → Organise → Deliver
Characteristics:
- Human-led at every step
- Thorough and methodical
- Structured and time-intensive
This proven framework has been the foundation of data storytelling, but AI is about to change everything. Let's establish this baseline to understand the transformation ahead.
The Impact of AI on Workflow
Why Everything Is Changing
Context is shrinking - AI infers meaning faster
Data handling is democratised - No more technical barriers
Analysis is automated - Patterns surface instantly
Delivery is accelerated - From concepts to presentations in minutes
Visual Concept: Arrows showing compression of traditional workflow steps
The traditional linear process is being compressed and parallelised by AI capabilities.
Context Shrinks
Do We Still Need Weeks of Scoping?
Traditional Approach:
- Define problems, audience, and medium in extensive detail
- Multiple stakeholder meetings and alignment sessions
- Detailed project scoping and requirement gathering
AI-Enabled Approach:
- AI infers meaning from prompts, documents, and messy data
- Context emerges through intelligent processing
- Example: Upload a meeting transcript → AI summarises the core problem and decision framework in minutes
The time spent on extensive upfront context-setting is dramatically reduced when AI can extract intent from existing materials.
Data Democratised
From Big Data Skills to AI Accessibility
Traditional Requirements:
- SQL expertise for database queries
- ETL knowledge for data pipeline management
- Coding skills for data manipulation and analysis
AI-Enabled Reality:
- AI consumes unstructured inputs: PDFs, images, transcripts, emails
- Natural language interfaces replace technical query languages
- Impact: Analysts no longer need heavy technical skills to access insights
Example: Drop messy documents into an AI system → Receive structured insights and visualisation recommendations
Analysis Automated
From Hours to Seconds
Traditional Process:
- Manual regression analysis
- Custom chart creation
- Dashboard construction and refinement
AI-Accelerated Process:
- AI runs analysis and surfaces patterns instantly
- Automated insight generation and pattern recognition
- Key Shift: From "doing" analysis to "validating" AI outputs
Demonstration Opportunity: Google AI Studio generating insights from raw data in real-time
Rise of Prompting
Prompt as the New Organising Principle
The Transformation:
- Prompt replaces the traditional Investigate + Organise phases
- Prompt literacy becomes the new essential skill
- Quality equation: Good prompt → great narrative; Poor prompt → irrelevant output
Prompting is not just about asking questions—it's about encoding context, constraints, and desired outcomes in a way that produces actionable results.
Demonstration Opportunity: StoryVizAI showing dramatically different outputs based on prompt variations
Results Reimagined
From Dashboards to Instant Stories
AI-Generated Outputs:
- Complete presentation decks
- Interactive dashboards
- Narrated video explanations
- Executive summaries with recommendations
Human Focus Shifts To:
- Refining AI outputs for accuracy and relevance
- Adding storytelling finesse and emotional resonance
- Ensuring alignment with organisational goals
Demonstration Opportunities:
- Gamma.ai creating presentation decks from prompts
- Napkin.ai generating instant diagrams and visual frameworks
The New Framework
Context → Data+Docs → Prompt → Result
Characteristics of the AI-Era Workflow:
- Leaner: Fewer manual steps and reduced overhead
- Faster: Rapid iteration and immediate output generation
- More iterative: Quick refinement cycles based on AI feedback
- Human-guided: Strategic direction with AI acceleration
This framework fundamentally reframes the practitioner's role from executor to curator and director.
Where Humans Still Matter
The Human Role in an AI Workflow
Critical Human Responsibilities:
- Curation of prompts - Crafting effective instructions and context
- Validation of AI results - Ensuring accuracy and relevance
- Adding narrative depth - Emotional resonance and persuasive elements
- Strategic alignment - Connecting insights to organisational priorities and decision-making frameworks
Visual Concept: Spotlight on human judgment and strategic thinking
These skills compound over time and represent sustainable career advantages in an AI-augmented world.
AI Tools That Change the Game
Practical Applications in Your Workflow
StoryVizAI → Storytelling with contextual prompts and framework guidance
Gamma.ai → Automated presentation deck generation from concepts
Google AI Studio → Intelligent analysis and pattern recognition
Napkin.ai → Instant visual diagrams and conceptual frameworks
Key Insight: Each tool addresses a specific part of the traditional workflow, but the real power comes from understanding how they integrate into a cohesive AI-augmented process.
From Analysts to AI Storytellers
The Transformation Summary
What's Decreasing:
- Manual context-setting time
- Technical analysis overhead
- Repetitive visualization tasks
What's Increasing:
- Prompt crafting and refinement skills
- AI output validation and quality control
- Strategic storytelling and stakeholder engagement
Closing Reflection:
"The value of data is no longer in the dashboard—it's in the story we curate with AI."
Call to Action:
Experiment with these tools. Build your prompt literacy. Redefine your role as an AI storyteller who combines human insight with artificial intelligence capabilities.
Questions and Discussion
Let's Explore Your Use Cases and Concerns
Seed Questions for Discussion:
- Where would AI save you the most time in your current workflow?
- Which part of delivery worries you most with AI involvement?
- What specific use cases would you like to explore first?
Contact Information:
Felipe Rego · Data Analytics and Visualisation Expert
Email: felipe@feliperego.com.au
LinkedIn: linkedin.com/in/feliperego
YouTube: youtube.com/@FelipeRego