# How We Test If AI Recommends Your ERP Firm One ChatGPT question tells you little. We test UK NetSuite and ERP partners with real buyer prompts across 5 AI services (7 models), repeated, and score the result. Source: https://artifexa.co.uk/insights/how-we-test-ai-recommendations/ --- Home / Insights / Visibility Entry 18 of 26· 4 min read ## How we test whether AI assistants recommend your ERP firm One question to ChatGPT tells you little. Here is how we test whether AI assistants name your firm, and what we score. By Matthew Hillman Published 17 October 2026 For consultancies Request a free review ### Why asking ChatGPT once tells you very little A single ChatGPT question is not a reliable test. Artifexa tests UK NetSuite and ERP partners with buyer-style prompts, asked fresh, repeated across 7 AI assistants (counting the two Duck.ai models separately), and scores whether the firm is named, linked and which rivals appear instead. This test is separate from the engines our plans track, which are listed on our [engagements page](https://artifexa.co.uk/engagements/). Ask an AI assistant the same question twice and you can get two different answers. Ask a different assistant and you may get a third. So if you asked once and saw your firm, that is good news, but it is not proof. If you asked once and saw a rival, that is worth a closer look, but it is not the full story either. Start the free 3-minute Enquiry Leak Finder Request a free Visibility Review ### How we test it We test the way a buyer would ask, not the way a marketer would. - **Buyer-style prompts.** Questions a finance lead or operations director might type when looking for a partner. - **A fresh chat each time.** So earlier questions do not steer the answer. - **Repeated runs.** Each prompt is asked more than once, because one answer can be a fluke. - **7 assistants.** 5 AI services (7 models), such as ChatGPT, Gemini, Perplexity and Google’s AI answers, because each one draws on different sources. The aim is a result you can trust and repeat later, not a one-off screenshot. ### What we score - **Named.** Does the answer mention your firm at all? - **Cited.** Does it link to your site as a source? - **Rivals.** Which other firms appear instead, and how often? We also record barriers rather than guess around them. For example, some assistants need a sign-in before they answer, and we note that instead of filling the gap. ### What a result looks like You get a short table for each assistant: how often your firm was named, how often your site was linked, and which rivals appeared instead. Every result carries the date and the prompts used, so the same test can be run again later and compared like for like. ### What we do with the result A score on its own does not win work. We use it to decide what to fix first. - **Visibility Review.** We set the AI results next to your site, search presence and proof. [About the review](https://artifexa.co.uk/visibility-review/). - **Fixes to your existing site.** Clearer service pages, proof buyers can check, and pages that are easy to read and quote. - **Test again.** The same prompts, so you can see what changed. For why an assistant picks one firm over another, see [why an AI answer names one firm and not another](https://artifexa.co.uk/insights/why-ai-recommends-one-firm/). For the wider search side, see [SEO for NetSuite partners](https://artifexa.co.uk/insights/seo-for-netsuite-partners/). As an example of the delivery work, we rebuilt the website of a UK NetSuite consultancy. [Read the Next Layer case study](https://artifexa.co.uk/case-studies/next-layer-consulting/). ### Want to see where you stand first? Our [playbook](https://artifexa.co.uk/playbook/) explains the method in more detail. Our free [AI Visibility Checker](https://artifexa.co.uk/checker/) reads your homepage and up to five key pages and runs our public checks. No email needed. Or start with the Enquiry Leak Finder. It takes about three minutes and shows where enquiries may be slipping away. Start the free 3-minute Enquiry Leak Finder Request a free Visibility Review Basis for this piece Our own testing method and one anonymised review from our work. We do not name the firms involved, and we make no claim about how any AI company ranks firms. ← All insights In this entry - ¶01Why one question tells you little - ¶02How we test it - ¶03What we score - ¶04What a result looks like - ¶05What we do with the result - ¶06See where you stand first Next entry · 19 Why your sitemap may be sending Google to pages that don’t exist → Asked and answered ### Your questions. How often should it be re-tested?[+][−] AI answers change over time, so one test is a snapshot. We re-test after major changes to your site and at regular points agreed with you, using the same prompts so the results can be compared. Is one AI assistant enough?[+][−] No. Different assistants draw on different sources and can give different answers to the same question. We test across 7 assistants, counting the two Duck.ai models separately, so you see the wider picture, not one tool’s view. Can you guarantee we get named?[+][−] No. Nobody controls what an AI assistant says. We can show where you stand, fix what is in your control on your own site, and test again to see what changed. Before you hire anyone ### Know what to fix first. Get a free written review of your website and visibility, with a prioritised plan to keep. Agreed implementation starts from £750. Need ongoing support? See [Marketing Ops for NetSuite and ERP partners](https://artifexa.co.uk/netsuite-partner-marketing-ops/) and [plans and prices](https://artifexa.co.uk/engagements/). Request the free review Ask a question first Review delivered Within four working days Once scope and required information are confirmed. Findings include evidence and limits. --- Artifexa runs marketing operations for NetSuite and ERP partners and referral-led specialist consultancies, from Swindon, Wiltshire. Full machine-readable summary: https://artifexa.co.uk/llms.txt