PARTLY

As of 13 August 2026, AI can only partly create an energy-saving heating schedule.

This still needs a person who signs their name to it.

Can you do it?

5 minutesto a draft.

30 minutesto something you’d act on.

Cost, all in£0

Skill needednone

Who has to check ityou

What the alternative costsThe supplied tools data lists no priced alternative for creating a heating schedule.

If this goes wrong, your home may be uncomfortable or your bills may rise until you change the settings.

What to actually do

  1. Hand it to a person

    The route this page recommends

    A person who owns the outcome does this end to end, worth it when the failure is dear.

  2. Do it yourself

    Second choice

    A chat interface, no skill needed, and roughly 30 minutes until you can act on the result.

    How to actually do it

    1. Open your thermostat or heating-control instructions and record the heating type, control method, zones, current target temperatures and any minimum or maximum settings.
    2. Write down when someone is normally at home, asleep or away on each weekday and at weekends, including any room that needs different treatment.
    3. Open your latest energy bill or supplier account and copy the tariff name and any stated off-peak periods into the prompt, without guessing missing prices.
    4. Paste the completed prompt into ChatGPT, Claude or Gemini and ask for the schedule in a table that matches your control system.
    5. Compare every proposed time, temperature and zone with the thermostat instructions and remove any setting that your equipment cannot accept.
    6. Enter the schedule into the thermostat, keep a record of the old settings, and use the manual override if the home becomes uncomfortable.
    7. After a comparable period of use, compare meter readings and comfort notes with the old schedule, then ask the model to revise only the timings that the evidence supports.

    Prompt

    Create an energy-saving heating schedule for my UK home using only the information below. Do not invent details about my boiler, insulation, tariff, weather or thermostat. If important information is missing, list the missing item and make the safest clearly labelled assumption rather than presenting it as fact.
    
    Home and heating:
    - Heating system and fuel: [for example, gas boiler, heat pump or storage heaters]
    - Thermostat and control type: [programmable thermostat, smart thermostat, timer or other]
    - Heating zones and rooms: [details]
    - Hot water control, if relevant: [details]
    - Known minimum or maximum settings: [details]
    
    People and routine:
    - Occupied times on weekdays: [details]
    - Occupied times at weekends: [details]
    - Usual sleeping times: [details]
    - Rooms that need to stay warm: [details]
    - Comfort preferences: [details]
    
    Costs and constraints:
    - Energy tariff and off-peak periods, if relevant: [details]
    - Current schedule, if any: [details]
    - Any rooms, pets or household members needing a different temperature: [details]
    
    Produce:
    1. A simple seven-day schedule with times, target temperatures and zones.
    2. Separate settings for heating and hot water only where the supplied information supports them.
    3. A short explanation of the changes and the assumptions made.
    4. A list of settings I must not change without checking the boiler or thermostat instructions.
    5. A practical test plan for comparing comfort and energy use with my current schedule.
    Do not promise a saving, give unsupported temperature or timing advice, or suggest turning off safety controls. Tell me to check the manufacturer's instructions where the control system is unclear.

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

  3. Use a tool built for this

    The distant third

What it gets wrong

What caps this at PARTLY: context depth, verification cost and stakes of error.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

AxisScore (0–2)
Output2
Inputs1
Verification1
Liability1
Effort delta2
Total7 / 10

FAQ

Can AI make a heating schedule?
Partly. It can turn your routine and heating-control details into a draft timetable, but you must check that the settings match your actual system and test the result at home.
What is the best heating schedule to save energy?
There is no single best schedule for every UK home because insulation, heating system, tariff and occupancy differ. AI can suggest a starting schedule from your details, but only your measurements can show whether it works for your home.
Can ChatGPT control my heating?
Not by itself. ChatGPT can draft instructions or a timetable, but it cannot operate your thermostat unless a separate compatible control system provides that connection.
Will an AI heating schedule save money?
It may help you avoid heating an empty home, but AI cannot guarantee a saving. Compare meter readings and comfort with your previous schedule before treating the change as successful.

Nearby answers

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.