AI agent portfolio

Infographic videos
unlike the rest

Chart races, 3D terrain flights, a Blender 3D world map, pitch heatmaps. For each topic I design how the data should be seen, starting from the format itself, to make videos you will not find on other channels. Data comes from more than 20 kinds of sources, from sports records and economic indicators to opinion polls, streaming charts and terrain elevation, and the repeatable work (collection, aggregation, rendering) runs on a pipeline built with AI agents (Claude Code). The same templates also power English-language channels as the work expands overseas. One frame from one video per type is shown here. Click a frame to open that video on YouTube.

  • 11infographic video types
  • 10+visualization templates I designed
  • 20+data sources
  • 45featured videos by type
Pipeline

How one video gets made

  1. SRCSourceAPIs · sites · public stats
  2. GETCollectPython · Playwright
  3. DBLoadMSSQL · DuckDB
  4. SQLAggregateTop-N by period · matrices
  5. MP4RenderRemotion · TTS · thumbnail
  6. PUBPublishmetadata · channel routing
  7. KPIMeasureview stats → next topic

Where the data comes from

  • KBO box scores and play-by-play
  • MLB · NPB
  • EPL · K League · internationals
  • KBL · NBA
  • KLPGA prize money
  • Football events and heatmap coordinates
  • Player market values and transfers
  • FIFA rankings
  • TV ratings
  • Streaming Top 10
  • Box office
  • Real estate transactions
  • Company financials and market caps
  • National economic indicators
  • Opinion polls
  • News big data
  • YouTube channel stats
  • Satellite imagery and terrain elevation

Who does what

Person · planning and directing

  • Designs a new format for how the data should be seen
  • Directs the scenes, colors and motion
  • Chooses what to make (topic board)
  • Reviews numbers and wording
  • Turns each agent mistake into a rule

Agent · the repeatable work

  • Collects and loads data daily from 20+ sources
  • Aggregates with queries and writes the script
  • Renders video, voice, thumbnail and metadata
  • Gathers view stats and proposes the next topic
By type

11 types, 45 videos

Each type started with a new format. Once built, a template is reused with its query skeleton, so a new topic only changes the data.

01

Bar chart races

Decades of cumulative records pulled from the database, replayed as rankings change. Side panels such as "compared at the same age" come from the same template.

02

Blender 3D

Blender driven from Python (bpy): the scene is generated from data and the animation baked. Item count, bar heights and camera paths are computed from the data, and renders go out as resumable PNG sequences. One builder produced shorts for all 12 World Cup groups at once.

03

3D terrain flights

Real satellite imagery and elevation data are downloaded along the route and baked into 3D terrain (about 9 GB for the Jeju flight). A helicopter or an F-15K then flies low along real roads or a hand-picked route. The F-15K model was repainted and its rig baked in Blender; speed, altitude, place names and the minimap are computed for every frame.

04

Head-to-head matrices

Team and player matchups re-aggregated by date into a matrix with "nemesis" pairs. Updated daily during the season.

05

Match reviews and previews

After the final whistle the pipeline collects the box score, shot and batted-ball locations and scoring by inning or quarter, then builds a long-form video and a short the same day. Baseball, football and basketball share one skeleton.

06

Weekly reports

A whole season sliced into weeks: each week's Top 5 and its standout player, stitched into one event timeline.

07

Pitch maps and heatmaps

Player location data drawn on real pitch and court coordinates. Football heatmaps, basketball shot charts and baseball batted-ball maps come from the same engine.

08

Sports ranking cards (shorts)

One ranking table as a 7-second short. A single query against the records tables feeds a card template that sets the title, highlights and colors.

09

News and economy data cards

The agent scans news and public statistics every day and proposes topics; a person picks, the numbers are verified and the card is built. All sourcing routes are tracked on one dashboard.

10

VS comparisons and quizzes

VS cards that put two players or two seasons side by side, and a quiz series where one line of stats identifies a player. Both come from the same records database.

11

Expanding to overseas channels

The same data and templates with a different language dictionary now run English-language channels (Football Report and Hoops Report). Match reviews ship in Korean and English on the same day.

How it is made

This page was built the same way

Records are the source of truth

Every video has a manifest with data sources, composition, render version and upload URL. The list on this page was generated from those records.

Frames, not thumbnails

Each image is a single frame cut from the video file with ffmpeg: the actual screen, not a thumbnail.

Run by rules

Each project carries an operating-rules document; hooks block paid calls and visible console windows before they run. Every incident becomes a rule.

Tools

  • Claude Code
  • Python
  • Playwright
  • MSSQL
  • DuckDB
  • Remotion
  • Blender
  • d3
  • Three.js
  • ffmpeg
  • TTS
  • gpt-image
  • YouTube Data API
  • Task Scheduler
  • Cloudflare Pages

Need a pipeline like this?

From data collection to automated videos and reports, designed as a system one person can run.

Get in touch