AI Engineering: Advent of AI with goose Day 3

Source: Dev.to

The Urgent Email

Date: December 3
From: Sarah Chen, Winter Festival Coordinator

URGENT – Hot Cocoa Championship Results Need Visualization
The Hot Cocoa Championship was AMAZING but we need these results visualized for the awards ceremony tomorrow at 2 PM. Our data person is sick and we’re in a panic.
Deadline: 18 hours
My data‑viz experience: Minimal
Panic level: Rising

Attachment: a massive markdown file with tournament data, voting breakdowns, recipe scorecards, and 5,294 total votes.

Enter the Auto‑Visualiser

I discovered goose’s Auto‑Visualiser extension, powered by MCP‑UI (Model Context Protocol UI). The tool lets you paste data and describe what you want; the appropriate visualization is generated directly in the conversation—no code, no exports, no separate tools.

The Data

Tournament Bracket

• Quarterfinals: 4 matches
• Semifinals: 2 matches
• Championship: 1 final showdown
• Winner: Dark Chocolate Decadence 🏆

Recipe Scorecards

Eight recipes rated on four attributes (0‑10):

• Richness
• Sweetness
• Creativity
• Presentation

Voting Breakdown

Fun Stats

• Closest match: Peppermint Dream vs. Salted Caramel Swirl (14‑vote difference)
• Biggest blowout: Dark Chocolate Decadence vs. White Chocolate Wonder (73 votes)
• Most controversial: Spicy Mexican Mocha

What I Created

🏆 Tournament Bracket Flow (Sankey Diagram)

Why a Sankey? It clearly shows how votes moved from quarterfinals through semifinals to the championship, highlighting Dark Chocolate Decadence’s dominance.

Key insights

• Peppermint Dream led Round 1 with 312 votes.
• Dark Chocolate Decadence peaked in the finals with 678 votes.
• The semifinals attracted massive voter turnout.

📊 Recipe Attribute Comparison (Radar Chart)

Observations

• Dark Chocolate Decadence: Perfect 10/10 in richness and presentation.
• White Chocolate Wonder: Maxed sweetness but low elsewhere.
• Spicy Mexican Mocha: High creativity (9/10) but polarizing overall.
• Classic Swiss Velvet: Balanced across all attributes.

📈 Voting Trends Over Time (Line Chart)

• Morning: 1,247 votes (early risers)
• Afternoon: 1,891 votes (+52 % increase)
• Evening: 2,156 votes (peak engagement)

Insight: Evening voters decided the championship—timing matters for engagement.

🥊 Head‑to‑Head Matchup Analysis (Bar Charts)

• Round 1: Four matches, clear winners.
• Round 2: Closer battles, higher stakes.
• Finals: Epic 678 vs 623 showdown.

The nail‑biter: Peppermint Dream vs. Salted Caramel Swirl in Round 1—only 14 votes apart.

The AI Engineering Process

I didn’t write any visualization code; I simply conversed with Goose.

My Prompts

Create a tournament bracket showing how each recipe progressed through quarterfinals, semifinals, and the championship.

Result: Beautiful Sankey diagram, instantly rendered.

Compare all 8 recipes on a radar chart using their judge scores for richness, sweetness, creativity, and presentation.

Result: Multi‑series radar chart with color‑coded recipes.

Show voting trends across the three time periods.

Result: Clear line chart of voter engagement.

Charts created: 6+
Crisis averted: ✅

The Tech Behind the Magic

MCP‑UI (Model Context Protocol UI)

Traditional AI outputs plain text (e.g., JSON). MCP‑UI returns interactive components—actual charts that can be embedded directly.

Auto‑Visualiser Extension

Built on MCP‑UI, it:

• Parses various data formats (CSV, JSON, markdown, etc.)
• Understands natural‑language visualization requests
• Selects the appropriate chart type
• Renders the interactive visualization in‑chat