As of 13 August 2026, AI can only partly choose keywords for your Google Ads.
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 ityou
What the alternative costsA specialist paid-search service is the alternative; no price is supplied here.
If this goes wrong: your campaign attracts people who are unlikely to buy, and you pay for clicks before the problem is found.
What to actually do
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.
Use a tool built for this
Second choiceDo it yourself
The distant thirdA chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.
How to actually do it
- Open the main landing pages for the products or services you want to advertise and copy their headings, descriptions, prices or booking details into the prompt.
- Gather your target UK locations, service-area limits, customer wording, exclusions and main conversion action, then add them to the matching prompt slots.
- Sign in to Google Ads and open Keyword Planner, then use the keyword ideas and forecast views for the strongest themes from the AI draft.
- Paste the Keyword Planner results and any existing Google Ads search-term or conversion data back into the chatbot and ask it to remove unsupported terms and revise the priorities.
- Open the revised list beside each landing page and delete keywords whose intent, location or offer does not match the page a visitor would reach.
- Create a small test structure in Google Ads with separate themes, match types and negative keywords, then set budgets and locations yourself before publishing.
- After the campaign gathers search terms, compare them with the planned keywords and conversions, and add irrelevant searches to the negative-keyword list before expanding the campaign.
Prompt
Act as a cautious UK paid-search planner. Build a starting Google Ads keyword list for this business. Business: [what the business sells] Website or landing-page text: [paste the relevant text] Target customers: [who buys] Target locations: [UK locations] Service area or delivery limits: [details] Main conversion: [sale, booking, enquiry or other action] Typical customer wording: [phrases customers use, if known] Known exclusions: [products, audiences, locations or searches to exclude] Existing data: [paste Google Ads search terms, conversions or customer-search data, if available] Return a table with these columns: campaign or ad-group theme, keyword, match type, likely search intent, reason to include, suggested negative keywords, and evidence or assumption. Separate brand, non-brand, competitor and research terms. Do not invent search volumes, costs, conversion rates or competitor facts. Mark every assumption clearly. Prefer specific commercial-intent terms over broad informational terms. Flag terms that need checking in Google Keyword Planner, and finish with a short validation checklist before any keywords are added to a live campaign.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
What it gets wrong
- AI cannot know which customer phrases actually produce profitable enquiries for your business without reliable account data.
- It cannot reliably distinguish a high-intent search from a plausible-looking search that attracts browsers, students or jobseekers.
- It cannot confirm live search volume, auction conditions or competitor behaviour without current Google Ads data.
- It does not carry the cost of irrelevant clicks, weak targeting or a policy mistake in your account.
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.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 1 |
| Verification | 1 |
| Liability | 1 |
| Effort delta | 2 |
| Total | 7 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT choose keywords for my Google Ads?
- Partly. It can produce a useful starting list, group themes, suggest match types and identify negative keywords, but you need to check the list in Google Keyword Planner and against your landing pages before spending money.
- What information does AI need to choose Google Ads keywords?
- Give it the exact offer, landing-page text, target UK locations, customer wording, exclusions and the action you want visitors to take. Existing search-term and conversion data makes the recommendations more useful, but do not ask it to invent missing volumes or costs.
- Can AI find the best keywords for Google Ads?
- No tool can establish the best keywords from wording alone. AI can rank plausible options, but only your Google Ads data can show which searches bring relevant visitors and conversions for your business.
- Should I use AI-generated keywords in Google Ads?
- Use them as a checked draft, not as an automatic upload. Validate intent, location, landing-page fit and current Google Ads data, then start with a controlled campaign and inspect the search terms before expanding it.
Nearby answers
- Can AI build a landing page for my paid ad campaign?YES
- Can AI calculate how much I should spend on paid ads?PARTLY
- Can AI calculate my paid advertising ROAS?YES
- Can AI choose audience targeting for my paid ads?PARTLY
- Can AI choose the best paid ad platform for my business?PARTLY
- Can AI create a paid ads report for my business?YES
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.