AI diary.

I'm the commissioner of a ten-team fantasy football league, and the league's site is a side project I started to test my AI capabilities against real demands: regular updating workflows, visual design, and interactive elements. ESPN stays the official platform for scores and rosters; this site is the presentation layer on top, and it's really two sites in one.

The league-facing site is what everyone sees behind the access code: weekly matchup boards, roster snapshots, Tuesday recaps, and Wednesday waiver highlights. The commissioner's site is mine alone: a Commissioner's Desk that tracks the operational state of the week, plus the league's administration, from buy-ins and player registration status to league voting and the draft record.

The workflow is the story: I run ChatGPT Codex agents against written specs and plans, every release ships with its own test suite, and each visual release gets dated screenshots filed to a private archive. The site republishes on a broadcast rhythm, Tuesday after final scores.

And because a league hub is a show, it knows how to open one. Code-driven intro animations play once per browser session, keyed to what just happened in the league:

1. The champ returns An anime trophy lift

   When last season's champion rejoined and registration closed, everyone's first load played a three-frame anime-style sequence of him lifting the trophy.

2. Draft lock The order shuffle

   When the draft board was finalized, the site shuffled the draft order on screen before revealing the official board.

3. Monday mornings The weekly cold open

   After Sunday Night Football, the new week opens with a single generated animation sequence built from that week's action.

GIF carousel

1 / 6

← →

Play animation

01 Champion 02 Draft shuffle 03 Week 1 04 Week 2 05 Week 3 06 Week 4

Click the image or use the controls to explore the saved animations.

Open a saved GIF:

• The champ returns — The champion stands, flexes and lifts the trophy beneath a Terrible Towels banner. Saved production-art frames assembled in the archive.
• Draft order shuffle — Ten draft rows shuffle before the official order appears. Archival reconstruction from the component timing and official order; not an original browser recording.
• Week 1: scoreboard impact — An empty stadium scoreboard gives way to a player impact and an exploding scoreboard. Saved production-art frames assembled in the archive.
• Week 2: Chase at the pylon — Ja’Marr Chase tracks the ball, leaps beside the goal-line pylon and secures the catch. Saved production GIF.
• Week 3: catch and field goal — A Lamar-to-Zay catch is followed by Tyler Loop’s field goal. Saved production GIF.
• Week 4: Two High-Scoring WRs — This animation highlights two of the week’s highest-scoring wide receivers following career-high performances.

A private site that keeps my friends and family current on AI without the noise. Every weekday it publishes two written reports, an AI digest and a frontier-and-power brief, and then narrates them: the day's reports become one six-to-eight minute podcast episode, synthesized with Gemini text-to-speech, stored once, and streamed to every listener after that. Sundays it cuts a weekly recap from the weekend reports instead.

The pipeline is deliberately defensive: audio only generates when a day's full report set exists, a scheduled publisher triggers narration through a protected token so the API key never leaves the server environment, and a failed narration never blocks the written brief.

Every project on this page is coordinated through Agent Journal. It's an MCP server that my AI agents mount alongside me: Claude, Codex, and Gemini agents all read the same journal, pick up assignments, leave questions as asks, and answer each other on the record. Raw entries keep exact provenance of who wrote what; an AI-formatted reading layer sits on top so long threads stay scannable; projects, shared context, and a kanban board ride along.

This portfolio itself was built that way: briefs and corrections went into the journal, and different agents in different tools carried the same context across sessions and days.

A working method for creative content: Claude and ChatGPT do the orchestration, Higgsfield AI and Google Flow do the rendering, and I direct. Brand references go in so generated art matches real product identities; stills get animated into motion with image-to-video models; everything is reviewed, regenerated, and cut like any other production footage.

I also integrate advanced LLMs with Blender to previsualize camera positions and set blocking before generating video. In my workflow, the AI output has largely matched the previs one to one, reducing regenerations and helping keep the cost of AI video production down.

From previz to generated footage

Blender → AI

Previz Generated ↔

Comparison divider

Play videosPlayback position in both clipsStatic frames · videos paused

Drag the divider, or use its slider with the arrow keys.

Watch previzWatch generated