About Util

A compute scheduling product designed around timing as a controllable variable.

Util exists because flexible workloads already create room for better timing decisions, but the cost and carbon signals that should guide those decisions are rarely surfaced in everyday tooling.

Positioning

What Util is

Util is a recommendation and scheduling layer for compute. It helps users decide when a workload should run based on changing electricity prices and carbon intensity.

Explainable recommendations
The product is designed to show why a schedule is better, not just output a hidden score.
Desktop-first direction
The real product is a downloadable application. This website is the marketing surface where the story and future download path live.
Operator clarity
Users should be able to understand timing tradeoffs quickly without reading raw energy charts.
Why it matters

Timing compute changes both economic and carbon outcomes

A lot of workloads are deadline-sensitive but not start-time-sensitive. That difference creates a real optimization surface.

Electricity cost changes hourly
Running at 1:00 PM and 3:00 AM can produce meaningfully different cost outcomes.
Carbon intensity shifts with the grid
The same workload can land against very different emissions conditions depending on timing.
Flexibility is often already present
Training runs, overnight jobs, render pipelines, and ETL workflows are often movable without harming delivery.
Better timing compounds
Once timing becomes part of planning, optimization becomes repeatable instead of ad hoc.
Visual anchor

System diagram slot

Drop `/diagrams/util-system-diagram.svg` here to show workload input, grid signal comparison, and optimized output.

Expected file
/diagrams/util-system-diagram.svg
Add the system explainer diagram here. A wide SVG with transparent background works best.
Audience

Who Util is for

Util is for people who want a practical way to reason about when compute should happen without becoming energy-market specialists.

Independent researchers with overnight workloads
Teams running GPU or CPU batch jobs with flexible deadlines
Operators who care about both spend and grid impact
Long-term vision

From recommendations now to more automated systems later

The long-term direction is to make timing-aware compute a normal part of how flexible workloads get planned and launched.

From suggestions to automation
Start with recommendations users can inspect, then move toward increasingly automated scheduling where appropriate.
From single jobs to systems
Over time, the product can expand from individual workloads to fleets, regions, and more integrated execution environments.