What 1.5 days and about 5 billion AI tokens produced

10h (edited) • Wins 🌟

I just shared the full walkthrough of the Vois website refresh on LinkedIn. I have attached it here too because the process is more useful than the screenshots alone.

The headline is big: less than 1.5 days from idea to deployment, with about 5 billion text-agent tokens used along the way. That total excludes image and video generation.

Before I posted it, I asked a friend who is a veteran UI/UX designer to review the work. His response:

"I hate you. this is good... I hate you for making it"

For context, I am the founder of Vois, and this is my own product and codebase.

I ran the refresh like a coordinated AI product team. I stayed responsible for the product direction, visual taste, quality bar, and every ship or reject decision.

The setup:

• GPT-5.6-sol handled the main orchestration. It broke the work into plans, assigned specialist agents, integrated their output, and kept the release moving.

• More than 300 specialist sub-agents using GPT-5.6-terra and Grok-4.5 worked in parallel and in sequence across planning, UX, choreography, visual design, asset creation, copy, frontend development, mobile QA, accessibility, browser testing, performance optimisation, and deployment.

• Fable-5 acted as an independent advisor. It reviewed alternatives, challenged decisions, and sent weak work back through another pass.

• GPT-image-2 generated the images and characters. Grok Imagine generated the video assets. Their generation usage is not included in the roughly 5 billion text-token total.

The text-agent token split:

Main agent: 13%

Sub-agents: 51.3%

Advisor agent: 35.7%

What shipped:

• a complete visual refresh for Vois

• a cinematic, scroll-driven homepage

• a consistent design system across the site

• dedicated desktop and mobile behavior

• generated visual and motion assets

• accessibility, performance, browser, and deployment fixes

The 5 billion total makes the trade visible. I used far more compute and coordination to compress a large design and engineering cycle into less than 1.5 days.

That speed came with a coordination cost. More agents meant more integration, more review, and more chances for the work to drift. My role shifted from producing every asset to setting constraints, sequencing the work, and deciding what survived.

The advisor loop used 35.7% of the text-agent tokens. The sub-agents used 51.3%. If I ran this again with a tighter budget, I would look at those two areas first.

Full LinkedIn walkthrough:

https://www.linkedin.com/feed/update/urn:li:activity:7483132570574954496/

Current site:

https://vois.so

New design:

https://pre-release.vois.so

After you watch it, I want two kinds of feedback:

Product: does the scroll story explain Vois faster, or does it get in the way?

Process: where would you cut the compute without lowering the quality of the result?

9 comments

What 1.5 days and about 5 billion AI tokens produced