The working app · 4:09 walkthrough
Follow the sun.
Explore flexible household energy around expected solar generation. Follow the inputs, calculated schedule, comparison, and saved scenarios.
Follow along at your pace
The full walkthrough.
Every spoken word, in scene order. Times indicate the beginning of each scene.
Everyday energy, thoughtfully timed
Sunshift helps a person plan flexible household electricity use around expected solar energy. Its opening pairs a calm planning workspace with an imagined solar neighborhood, created with AI image generation. The illustration is not a photographed installation. This is a narrated interface walkthrough using actual app screenshots and synthetic narration.
A better time for everyday energy
The working planner brings an hourly energy chart and appliance timing into one workspace. The starting day is an editable sample, not live meter data. This view has the Sunshift plan selected, with six point seven five kilowatt hours of modeled grid import. A person can explore which loads might use more of the solar energy they expect, then compare the same inputs with the original schedule.
Start with the original schedule
The original view shows the starting schedule for this illustrative sunny day. It calculates twenty two point nine five kilowatt hours of grid import. The sample Sunshift plan shown earlier calculates six point seven five. That difference comes from shifting load within the same model and assumptions. It is not a claim about a measured household saving. The useful question is which input and timing choices explain that difference.
Begin with the assumptions
The energy inputs are deliberately visible. There are twenty four hourly solar estimates and twenty four household consumption estimates. Each value represents kilowatt hours in that hour. A sunny sample, a cloudy sample, or an all zero profile can help explore a different day. Household consumption excludes the flexible appliances being scheduled, so the same demand is not counted twice. These remain user supplied assumptions.
Keep the schedule practical
Select an appliance to edit its power, whole hour duration, and allowed running window. The entire uninterrupted run must fit between the earliest start and the finish by time. An original start defines the comparison schedule. A fixed start can preserve a personal constraint. Changing an input invalidates the old plan and asks the user to optimize again, keeping old calculations from appearing current.
Compare a calculated schedule
The optimize action calculates a schedule within those windows and locks. Original and Sunshift plan views compare the same day using different appliance start times. Grid import is computed hour by hour whenever demand exceeds solar generation. Solar self consumption shows the share of generated solar used in that modeled day. Any displayed improvement is a calculation for these inputs, not a measured reduction from a household.
Keep a day worth revisiting
A named scenario can be saved in this browser and reopened later. The scenario library supports multiple days and variants, so an experiment with different assumptions does not have to erase the previous idea. The saved charge at noon example shown here is a separate illustrative variant. Scenario JSON provides a portable backup, and a schedule can be exported as a CSV or printed. There is no account or cloud sync; clearing browser data removes locally saved scenarios.
Transparent math, honest limits
The method page explains how the model works. The scheduler tries alternative starts and improves them through a bounded heuristic. It is deterministic, but it does not guarantee a globally optimal combination. Overlapping appliance loads are allowed and reported. There is no battery, tariff, weather feed, carbon factor, or circuit capacity model. Those limits matter before anyone translates an exploratory schedule into real appliance use.
A small tool with a complete loop
Sunshift's code, design, documentation, and tests were developed with OpenAI Codex assistance. No AI service runs inside the product: scheduling is implemented in TypeScript. The result is a focused planning loop from editable assumptions to a calculated schedule and a reusable export. Its purpose is to make timing choices understandable, while keeping the evidence, the calculation, and the limits visible.