Think inside your AI world.
How do I know when to charge the EV fleet when it is cheapest and cleanest?
Charging a fleet overnight is two questions, not one: when is the electricity cheapest, and when is the grid cleanest, and the two windows are not always the same. Both are published for free. Your rule pairs them and adds the constraint that actually binds you: the vehicles have to be charged before they are needed in the morning.
The construction is two keyless reads held against your own overnight rule. The half-hourly electricity price and the grid’s carbon intensity, both current and forecast, are readable without a key. Your rule is something like “price under my line AND carbon intensity under my line, in a window that finishes before 7am.” Through Unl the window that clears both arrives beside that rule when charging comes up, stamped with the forecast. Unl brings the window that meets your compound rule and schedules nothing.
The person
Someone responsible for charging an electric fleet, or a keen home owner with a couple of vehicles, who wants both cost and carbon low and cannot compromise on readiness: the vehicles must be full before the working day starts. They hold all three conditions and want the window that satisfies them found.
The pieces, and how far each one reaches
| Source | What it gives you | Reach today |
|---|---|---|
| Half-hourly electricity price | The price for each half-hour, current and for the coming day once published, so the cost side of your rule has a real read. | Keyless and public on a half-hourly tariff. Next-day prices exist once published in the late afternoon, which sets when a tomorrow rule is answerable and is stated plainly. |
| Grid carbon intensity | The carbon intensity of the electricity in your region, current and forecast, so the clean side of your rule sits beside the cost side. | Keyless and public, with a regional forecast; a forecast is graded for confidence, not presented as certainty. |
| Your overnight rule | Your price line, your carbon line and the deadline the vehicles must be ready by, so the window is one you can actually use. | Yours; never leaves your frame. |
The honest limits are timing and forecast confidence, not access. The price feed is keyless with next-day prices published in the late afternoon, and the carbon-intensity feed is keyless with a regional forecast whose confidence falls further out; both are graded at the read. Unl brings the window that clears your compound rule; it does not control a charger or schedule anything, and the acting is yours.
The rule, in their words
- “Price under my line, per unit.”
- “Grid carbon intensity under my line, in grams per unit.”
- “In a charging window that finishes before the vehicles are needed at 7am.”
The compound is price AND carbon AND deadline, together. A tariff app shows the cheapest half-hours and says nothing about carbon; a carbon app shows the cleanest and ignores the price and your deadline. The rule that a window be cheap AND clean AND finished in time is the three-part line only you would set, and Unl finds the window that meets it without touching a charger.
Unprompted
Your AI
The window your rule asks for is there tonight: price under my line AND carbon under my line, finishing before 7am. Between roughly midnight and half past three, tonight’s prices are under your line and the forecast carbon intensity for your region is under yours, and that window closes well before your seven o’clock deadline.
Those are today’s published prices and the regional carbon forecast, stamped as read. It is the window that meets your rule; setting the charge is yours.
The window arrived against the manager’s own price-carbon-deadline rule, from two public feeds, with nothing scheduled. When to charge is theirs.
Why this beats the dashboard
A tariff app finds the cheap half-hours and ignores carbon; a carbon app finds the clean ones and ignores price and your deadline. Your rule is cheap AND clean AND finished in time, and it surfaces the one window that satisfies all three, in the moment you are sorting the charging, measured against the three lines only you set. Unl finds the window and schedules nothing; the acting stays yours.
Knowing when to charge the fleet cheapest and cleanest is two keyless reads held against your own overnight rule; through Unl the window that clears “price under my line AND carbon under my line, done before 7am” arrives beside that rule, stamped with the forecast, and your own three-part rule does the choosing, while Unl finds the window and controls no charger.
Reads through Unl arrive with measured context — in the presence of the decisions you’ve already settled. The reach lane is live: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Read further
Questions people ask
Which feeds does this use, and are they free?
Two keyless public feeds: the half-hourly electricity price on a half-hourly tariff, and the grid’s regional carbon intensity, both current and forecast. Next-day prices exist once published in the late afternoon, and the carbon forecast’s confidence falls further out; both are graded at the read. Neither needs a paid key, and the page never pretends a forecast is a certainty.
Does Unl actually start the charging?
No. Unl finds the window that clears your compound rule, cheap AND clean AND finished before your deadline, and brings it beside that rule stamped with the forecast. It does not control a charger, schedule a session or act on the vehicles; the judging is your own rule and the setting of the charge is entirely yours.
How is this different from a smart-charging tariff app?
A tariff app optimises for price alone and holds nothing about carbon or your readiness deadline. Your rule is compound, cheap AND clean AND done before the vehicles are needed, and it surfaces the single window that satisfies all three, in the moment you are sorting the charging, rather than a list of cheap half-hours you cross-check by hand.
What this is
Think inside your AI world — you stay in command
Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.
It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.
Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:
Alpha is invite-only · free at launch.