Creating charts is easy. Making them GOOD is hard. Users struggled with chart type selection, styling decisions, and best practices—resulting in suboptimal visualisations even when data was correct.
As Lead Designer for Copilot Chart Design Recommendations, I designed an LLM-powered system that analyses data shape, infers user intent, and suggests optimal chart configurations. This required deep collaboration with ML engineers to train and tune the RAG models with data visualisation principles—essentially encoding expert knowledge into AI prompts.
The result bridges the gap between 'chart exists' and 'chart communicates effectively,' democratising data visualisation expertise for 400M users.
<aside>
Execution Success
</aside>
<aside>
User Effort Saved
</aside>
<aside>
Clicks Eliminated
</aside>
<aside>
Shipping Timeline
</aside>
https://drive.google.com/file/d/1WXHbtYtugWS0mrJ9DJqLoT_0sYKAOrBy/view?usp=drive_link
What Users Were Struggling With
<aside>
"No suggestions... I have to try different charts and hope one communicates my idea." — Usability Study 2024
</aside>
<aside>
"I spend hours tweaking charts to look professional." — Power User
</aside>
<aside>
"It looks boring. How do I make it presentation-ready?" — Enterprise Analyst
</aside>
<aside>
"I created a chart but don't know if I picked the right type." — Intermediate User
</aside>
| Pain Point | User Behaviour | Business Impact |
|---|---|---|
| Chart Type Uncertainty | Try multiple types, delete, start over. 5-10 minute cycle. | Wasted time, user frustration, suboptimal final choices |
| Styling Paralysis | Don't know which formatting options matter. Either over-style or under-style. | Charts look unprofessional or cluttered |
| Best Practice Ignorance | Unaware of data viz principles (e.g., start axis at zero, use direct labels) | Misleading visuals, poor communication |
<aside> 💡
The pattern was clear: Users could INSERT charts (thanks to our P0 improvements), but they couldn't optimise them.
</aside>
Competitive analysis revealed sophisticated design assistance
<aside> 📐
The Ease-Complexity Inverse
Tools that handle complex data are hard to use. User-friendly tools handle simple data.
</aside>
<aside> 🎨
Defaults ARE The Product
40% of Excel charts were deleted same session. Canva/Flourish users kept charts because they looked presentation-ready on first insert.
</aside>
<aside> ☝
One-Click Is Table Stakes
Google Explore, Napkin.ai, Tableau Show Me — every modern tool reduces data→chart to 1-2 clicks. Excel required 5+ steps with no guidance.
</aside>
<aside> ✋
Direct Manipulation Wins
Pitch, Miro, Figma use click-to-format context menus. Excel used ribbon + dialog boxes — 3+ clicks to format a single element.
</aside>
<aside> 🚨
Copilot Scored Lowest
In our AI compete benchmark, Copilot in Excel scored 48/100 — below ChatGPT (85), Gemini (72), even Gemini Sheets (56). Task success was 40%.
</aside>
<aside> 📖
Charts Must Tell Stories
BI tools provide insights alongside charts. Google Gemini explains trends. Excel charts were 'purely graphical — static visuals, with no story.’
</aside>