PARTLY

As of 13 August 2026, AI can only partly choose a more efficient boiler.

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 neededchat-fluent

Who has to check ita professional

What the alternative costsNo priced human or software alternative is provided in the available tool data.

If this goes wrong, you can pay for an unsuitable boiler or installation and still have higher bills or poor heating performance.

What to actually do

  1. Hand it to a person

    The route this page recommends

    Someone with a licence or accountable authority has to sign this before it counts.

  2. Use a tool built for this

    Second choice
  3. Do it yourself

    The distant third

    A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

    How to actually do it

    1. Open your latest gas, oil or electricity bills and write down the fuel used, annual consumption, current cost and current boiler details, leaving unknown fields marked as unknown.
    2. Gather the property facts that affect heating demand, including property type, approximate age, bedrooms, bathrooms, occupants, insulation, radiators, hot water requirements and any planned extension.
    3. Take a clear photo of the current boiler, controls, flue route if visible and the surrounding space, without removing any covers or entering restricted areas.
    4. Paste the gathered facts, bills, photos or transcribed details and any existing boiler models or installer quotes into the prompt.
    5. Ask the chatbot to separate manufacturer claims, your supplied facts, assumptions and missing information, then remove any option whose efficiency or suitability cannot be supported.
    6. Check each remaining model against its current manufacturer specification and compare the quoted efficiency, output, warranty, controls and installation requirements rather than relying on an AI summary.
    7. Send the comparison and question list to at least one qualified heating engineer and ask them to confirm heat-loss sizing, flue arrangements, controls, system compatibility and the assumptions in the quote before you choose.

    Prompt

    Help me compare options for a more efficient boiler in a UK home. Do not make a final recommendation until you have listed the missing information and explained why it matters. Use only facts I provide or current, identifiable manufacturer and UK official sources, and separate verified facts from assumptions.
    
    My details:
    - Location: [town or postcode area]
    - Property type and age: [details]
    - Number of bedrooms and bathrooms: [details]
    - Number of occupants: [number]
    - Current heating system and boiler: [details, if known]
    - Fuel available: [mains gas, LPG, oil, electricity or other]
    - Current boiler output and age: [details, if known]
    - Current annual energy use and costs: [paste bills or readings]
    - Hot water requirements: [details]
    - Existing radiators and insulation: [details]
    - Planned changes to the property: [details]
    - Budget and priorities: [details]
    - Candidate boilers or installer quotes: [paste details]
    
    Explain which boiler types are worth considering, what efficiency information is comparable, and which figures cannot be compared without knowing the installation conditions. Do not estimate savings unless the calculation inputs and source are clear. Flag any information that needs checking against the manufacturer, an energy supplier or a qualified heating engineer. Produce a comparison table, a list of questions for installers, and a short list of checks before I accept a quote. State clearly that a qualified heating engineer must confirm sizing, flue arrangements, controls and installation suitability. This is not professional advice.

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

What it gets wrong

What caps this at PARTLY: judgement under ambiguity, 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 delta1
Total6 / 10

FAQ

Can ChatGPT tell me which boiler is most efficient?
It can compare published efficiency information and organise your shortlist, but it cannot decide which boiler will perform best in your property without accurate sizing and installation details. A qualified heating engineer must confirm the final choice.
Can AI calculate how much I will save with a new boiler?
It can make a comparison from your bills and stated assumptions, but the result is only as reliable as those inputs and the tariff information. Treat any saving as an estimate and check the assumptions against current supplier and manufacturer information.
What information does AI need to recommend a boiler?
Give it your fuel type, property size, occupants, heating and hot water needs, current boiler, insulation, radiators, usage and any installer quotes. It still needs a heating engineer’s site assessment for heat-loss sizing, flue arrangements and installation suitability.
Should I trust an AI boiler recommendation?
Use it to structure a shortlist and prepare questions, not to approve the installation. Check the specifications yourself and ask a qualified heating engineer to confirm the sizing, safety and quote before you buy.

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.