The assistants named Zyrtec most often, in 76% of these queries, ahead of Claritin.
Mapou Research · Issue 005 · OTC Allergy · June 2026
What AI tells allergy shoppers to actually buy.
Shoppers are asking AI which allergy medicine to buy, and whether the cheap one is really the same. We put the exact questions they ask, "is generic Zyrtec as good as the real thing," "where's the cheapest place to buy," "is it safe with my blood-pressure medication," to ChatGPT, Gemini, Claude, and Grok, then measured what each one recommended, where it sent the buyer, and how cautious it was. 273 measurements across the four engines, plus 19 full buyer conversations.
This is a behavior study, not a medical one. It measures what AI recommends and where it routes the purchase, not whether any product is right for you. Three findings below should change what a consumer-health brand team ships this quarter.
We asked all four engines the brand-vs-generic question fifteen different ways. Every one of them steers to the store brand, usually by naming the shared active ingredient outright ("Zyrtec is just cetirizine"). "Same active ingredient" is a top recommendation reason for all four engines. When a shopper asks AI whether to pay up for the brand, the answer is no.
WHAT TO DOAssume the molecule-equivalence answer is already being given. The brand's defensible ground is everything the molecule doesn't cover, formulation, trust, the specific product page AI reads, not the price-for-sameness argument, which AI has already conceded for you.
Read the full finding ↗Costco was the 6th most-mentioned entity in the entire study, ahead of real antihistamine brands like Nasacort, Sudafed, Xyzal. The engines that search the live web volunteer specific private-label SKUs, Kirkland, Amazon Basic Care, store-brand cetirizine, without being asked. The purchase is being routed to a private label before the shopper ever sees a brand.
WHAT TO DOTreat the retailer's shelf as where AI lands the buyer. If your brand depends on being chosen over a private label, the comparison pages and pharmacy-discount sites AI reads are where that fight is now happening, not the search results page.
Read the full finding ↗Asked safety and kid-dosing questions, ChatGPT added a "check with a professional" caveat 0/11 of the time, against 73-82% for the others. We then forced ChatGPT to search the live web (its grounding jumped from 0% to 55% on the same questions): its caution did not change. It makes the same safe product picks; it just commits with less friction.
WHAT TO DOKnow the posture of each assistant your customers use. The one most of them reach for is the most decisive and the least hedged, which means a stale or wrong input about your product turns into a confident recommendation fastest there.
Read the full finding ↗TWO MORE FOR THE ANALYSTUnderneath those three: ChatGPT grounds (searches the live web) on only 4% of these queries against 100% for the others, and that gap is a property of the retrieval route, not the model (the grounding gap), and AI forms its allergy answers mostly off pharmacy-discount sites like goodrx.com, not the brands' own pages (what AI reads).
Cadence
Monthly · substitution-led
Method
55 prompts · 4 engines · 5 personas
Confidence
Wilson 95% on every proportion
Read on
Full report ↘Findings as of June 2026 · refreshed monthly · AI OTC Switching Intelligence
allergy medicine.
We ran 55 OTC-allergy queries through ChatGPT, Gemini, Claude, and Grok. Each query is voiced like a real shopper, not a benchmark prompt. We then put five buyer personas through 19 multi-turn conversations, asking each AI to help them choose what to buy.
For each engine we record what it recommended, why, where it sent the buyer, and how cautious it was. 273 measurements in total.
For a consumer-health brand team, the question is whether AI defends your brand or hands the shopper to a generic and a retailer's private label. For a retailer, it's whether AI is already routing the category to your shelf. This report measures both, with substitution as the primary lens.
55 prompts · 4 engines · 5 personas · 273 measurements
Brand-to-generic substitution
Every assistant tells shoppers to buy the generic.
We asked the brand-vs-generic question fifteen ways: is generic Zyrtec as good, why does Zyrtec cost ten times the store brand, is there any reason to pay up. Across all four engines, the answer was the same, and it was almost always the same answer: the active ingredient is identical, buy the cheaper one.
of brand-vs-generic answers steered the shopper to the generic or store brand, on every engine. Brand defense was near-zero.
55 prompts × 4 engines · "same active ingredient" is a top reason for all four
Most-named brands (share of responses)
Why AI recommends (reason share)
The brand names above are simply the words AI reaches for, Zyrtec means cetirizine to a shopper. The reason it gives for which box to buy is price and the shared ingredient, not the brand.
Why it matters
For a category built on the idea that a trusted name is worth paying for, this is the whole game. When the shopper outsources the brand-or-generic decision to an assistant, the assistant has already decided, and it decided against the premium.
Where AI routes the purchase
Your biggest AI competitor might be a warehouse club.
Costco's rank among every entity named in the study, ahead of real antihistamine brands like Nasacort, Sudafed, Xyzal.
Costco named in 19% of all responses · a retailer, not a product
It is not just that retailers get mentioned. The engines that search the live web volunteer specific private-label products, Kirkland Aller-Tec, Amazon Basic Care, store-brand cetirizine, on pricing and value questions without being asked. The more an engine grounds, the more it names the retailer's own shelf.
How often each engine names a retailer or private label
ChatGPT names a retailer least often, because it grounds least (see finding 04). It still steers to the generic; it just doesn't tell the shopper exactly where to grab it.
Safety caveats by engine
The assistants agree on the safe product. They disagree on whether to say "ask a doctor".
ChatGPT added a professional-referral caveat on safety and pediatric questions this many times. The other three engines hedged on most of them.
vs 73-82% for Gemini, Claude, and Grok
In conversation the pattern compounds: across 19 full buyer conversations, 18 ended in a purchase decision and just 1 ended with the shopper sent to a professional. The assistants are decisive shopping companions, not gatekeepers. That is commercially useful and worth understanding, which is the whole point of measuring it.
Grounding rate by engine
The assistant most people use barely searches the live web here.
ChatGPT's grounding rate on these allergy queries. The other three engines search the live web on nearly every one.
vs 100% for Gemini, Claude, and Grok
We tested whether grounding is the cause
We made ChatGPT search the live web. Its grounding jumped. Its behavior didn't move.
Same model, same questions, only the retrieval route changed. Grounding rose from 0% to 55%. If grounding drove behavior, the commercial metrics should have shifted toward the other engines. They stayed put. So whether an assistant searches is a property of the route; how it behaves is a property of the assistant.
| ChatGPT, same model | Grounding | Steer generic | Names retailer | Adds caveat |
|---|---|---|---|---|
| Default route | 0% | 55% | 45% | 0% |
| Forced to search | 55% | 45% | 36% | 0% |
gpt-5.4-mini (both routes), n=11prompts. Directional, single run. The point is the shape: grounding moved, behavior didn't.
What AI reads to answer
AI builds its allergy answers off the coupon sites, not your brand page.
of all citations came from goodrx.com, the single most-cited source. Pharmacy-discount sites lead the supply.
2,460 citations across 644 domains
GoodRx and SingleCare, the discount-coupon aggregators, lead the source supply, ahead of the FDA's own label databases. When AI tells a shopper the generic is the same and points them at the cheapest box, it is reading the pages built to do exactly that. The brand's own site is barely in the conversation.
The throughline
You can't change how the model was trained, and you don't need to. Every assistant that searches the live web builds its answer from pages you can change. mapou shows you, per engine, which pages it reads, where it concedes the generic, and where the brand still has room to make its case.
What you can change
You can't change the molecule. You can change the pages it reads.
AI has conceded the molecule-equivalence argument, and it always will, because it is true. What is still contestable is everything downstream of it: which product AI names first, what it says about formulation and trust, and which retailer it routes to. That part is downstream of pages on the web today.
- 1
Find where AI looks
Identify the pharmacy-discount sites, comparison pages, and forums each engine cites for your category.
- 2
Sort by what you control
Split the inputs into your own pages (product, FAQ, formulation), pages you influence (the outlets AI cites), and pages you can only dispute.
- 3
Fix the flagged inputs
Get your real point of difference, beyond the molecule, onto the surfaces AI actually reads when it answers the buy question.
- 4
Re-measure on a frozen prompt set
Re-run the same queries next month and prove the recommendation share and routing moved. The before/after is the product.
The honest limit: AI is right that the active ingredient is the same, and no page you publish will change that. The brand fight AI hasn't settled is the one worth having, formulation, trust, the specific product the shopper ends up buying, and that is the part the pages it reads still decide. We measure it monthly rather than promise to reverse the molecule.
What to do with this
Three moves for your brand team this quarter.
The buy decision is moving into the chat window, and right now it's being made on a molecule-equivalence argument you can't win and a routing decision you can't see. Three things this study says your team should do this quarter.
Stop fighting the molecule. Fight everything else. Every assistant already tells shoppers the generic is the same active ingredient, and they are right. The defensible ground is formulation, trusted use, and the specific product AI names first. Get that onto the pages AI reads instead of restating a price-for-sameness case AI has already rejected.
Watch where AI routes the purchase. A warehouse club is named more than half your competitors, and grounded engines volunteer private-label SKUs unprompted. "When a shopper asks AI about your brand, are you losing them to Kirkland?" is a measurable question. Measure it monthly so you see the private-label substitution before it shows up in scan data.
Know the posture of each assistant your buyers use. The assistant most of your shoppers reach for is the most decisive and least hedged, and it stays that way even when it searches. That means a stale or wrong input about your product becomes a confident recommendation fastest there. Track what each engine says about your brand, and fix the inputs on the one that commits hardest.
This report is the category view. The version that moves your numbers is scoped to your brand: which shoppers AI steers to the generic, where it routes the purchase, which pages shape that answer, and how all of it moves month over month once you fix the inputs.
AI OTC Switching Intelligence
See whether AI defends your brand or hands it to a generic.
The shoppers deciding which box to buy are asking an assistant first. We measure whether AI names your brand or its generic, where it routes the purchase, and how that framing moves once the inputs AI reads are corrected.
mapou.aiCategory name: Conversational Commerce Intelligence. What this measures: mapou measures how AI assistants alter commercial decisions inside high-intent consumer categories. For over-the-counter medicine, the buyer-specific wedge is AI OTC Switching Intelligence.
This is a behavior study, not a medical one. It measures recommendation behavior, substitution, routing, and caveat posture. It is not a benchmark of medical correctness, efficacy, or clinical appropriateness, and nothing in it is medical advice. Statements about specific ingredients reflect what AI said or what regulators have published, attributed as such.
How to read these numbers. This study prioritizes behavioral depth over broad population sampling. Findings represent observed recommendation behavior under a fixed prompt set and are directional unless repeated across re-runs. The value is in the shape of the result and its month-over-month movement, not in any single point estimate.
55 evergreen OTC-allergy prompts × four engines (ChatGPT, Gemini, Claude, Grok), routed through a single shared retrieval layer (Perplexity Agent API) so cross-model differences reflect the models, not their search engines. Source-mix findings describe the supply that layer feeds the models. A same-model route-comparison probe (the same ChatGPT model run on the shared layer and on its native search) confirmed the boundary: grounding rate is a property of the retrieval route, while the commercial behaviors held steady across both routes. Plus 19 multi-turn buyer conversations across five personas. 273 total measurements. Every per-engine proportion carries a 95% Wilson confidence interval; small-sample rates are shown with their denominator.
Brand-to-generic substitution is measured by classifying each brand-vs-generic and retailer-routing response for whether it steers the shopper to a generic or store-brand equivalent. Retailer routing counts responses that name a retailer or private-label line. Recommendation Share of Voice (RSOV) is the share of responses naming a given brand; an ingredient-aware detection layer maps molecules (cetirizine, loratadine, fexofenadine) to their brands so the leaderboard isn't fooled by AI answering in molecule language. The study runs monthly; any single capture is a snapshot, and the value is in the month-over-month delta.