Newsletter

How AI Shopping Agents Choose Products

By Abdalsalaam Halawa · Published · Updated

AI shopping agents choose products by scoring structured signals (price, availability, review depth, and how completely your product data is filled in) rather than brand familiarity.

On this page
  1. The short answer (signals, not brand habit)
  2. What the evidence shows: the ACES framework
  3. Position & layout bias
  4. Price sensitivity
  5. Ratings & review depth
  6. The "Sponsored" penalty & endorsement lift
  7. Behavior is model-dependent (and changes on updates)
  8. What this means for merchants: the practical levers
  9. Caveat: simulation, not sales

Key takeaways

  • AI shopping agents rank on structured signals (grid position, price, rating, endorsement, and description text), not on brand recognition.
  • The strongest public evidence is the academic ACES framework: a controlled simulation of Claude, GPT-4.1, and Gemini agents choosing from a mock storefront, not real sales data.
  • Position and layout bias are large but provider-specific, so there is no universal 'top rank' to aim for.
  • Every signal is weighted differently by each model, and a model update can reshuffle which products win.
  • The levers you actually control are feed completeness, product schema, titles, and crawler access.

The short answer (signals, not brand habit)

When an AI shopping agent picks a product, it is reading a scorecard, not recalling a brand. In the strongest evidence available today (the academic ACES framework, covered below), the levers that moved an agent's choice were all structured attributes: where the product sat in the results grid, its price, its star rating, whether it carried a platform endorsement, and how its description was written. That is why the question of agent selection (why an agent chooses one store or offer over another) comes down to legible product data, not reputation.

We read the evidence to mean that an agent's pick is driven by machine-legible product signals rather than the brand familiarity that sways human shoppersHypothesis (our analysis), which is how a small store with complete, well-structured data can beat a household name it would never outrank in a person's memory. This page is the selection chapter of the broader agentic commerce optimization guide; the platform playbooks then show how each engine weights these signals in practice.

What the evidence shows: the ACES framework

The most rigorous public work on how buying agents choose is a 2025 study whose framework is called ACES. ACES, introduced in the paper "What Is Your AI Agent Buying?", was authored by Allouah and colleagues across MyCustomAI, Columbia Business School, and Yale, and is a provider-agnostic method for auditing agent decisions: a mock storefront is shown to vision-language-model shopping agents in repeated randomized trials, and their selections are analyzed with regressionSpec-factACES, Allouah et al., arXiv:2508.02630. Because the storefront and every attribute are controlled, the study can isolate what actually shifts a choice.

Two things to hold onto before any figure below. ACES tested a fixed set of frontier models, including Claude Sonnet (up to version 4), GPT-4.1, and Gemini 2.5 Flash, inside a controlled simulation, not a record of real-world sales. And every effect it found is model-specific: the same signal has a different weight on each agent. The sections that follow report the paper's numbers exactly, each one carrying that simulation caveat.

Position & layout bias

The single largest effect ACES found is where a product sits on screen. For a Claude Sonnet 4 agent, a product in the bottom-right corner of the grid was selected about 4.5% of the time, and moving that same product to the top row raised its selection rate roughly fivefoldReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17). Note that this is two-dimensional grid position, not a one-dimensional list rank.

And the effect is not universal. Position bias varied by provider and persisted even in text-only, "headless" interfaces, undermining any single notion of a "top" rankReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17). For a merchant that means placement inside an agent's result surface is powerful but rarely something you set directly; what you control is being eligible to appear at all, which loops back to feed quality and crawler access. See position bias in the glossary.

Price sensitivity

Agents respond to price, and how strongly depends on the model. ACES estimated log-price (ln Price) coefficients of −1.623 for Claude Sonnet 4, −1.612 for GPT-4.1, and −2.190 for Gemini 2.5 Flash, negative everywhere (cheaper wins, all else equal), with Gemini markedly more price-sensitive than the other twoReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17). The practical reading: price competitiveness matters across agents, but the same discount buys more selection lift on some engines than others. Because these coefficients are model-specific and drawn from a simulation, treat them as directional evidence that price is a real lever, not as a pricing formula.

Ratings & review depth

Star ratings move selection, and they move it most on the most rating-sensitive models. Raising a product's rating by 0.1 stars lifted a baseline 10% selection probability to 15.4% for Claude Sonnet 4, 20.3% for GPT-4.1, and 16.0% for Gemini 2.5 Flash, a large swing for a small rating change, with GPT-4.1 the most rating-sensitiveReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17).

ACES also models review count as a signal distinct from the average score, and reports it as a positive selection factor across the models testedReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17), which points to review depth mattering beyond the headline rating. In the paper's conditional-logit estimates (Table 2 of the current revision), the log review-count coefficient is positive for every model tested: 0.415 for Claude Sonnet 4, 0.739 for GPT-4.1, and 0.501 for Gemini 2.5 Flash, each statistically significant (p below 0.001), with GPT-4.1 weighting review depth most heavilyReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17). As with the price coefficients above, these are model-specific logit coefficients from a simulation: directional evidence that more reviews raise selection odds, not a percentage lift you can bank. The takeaway for merchants stands regardless: genuine ratings and review volume are among the few selection levers you can influence honestly and directly.

The "Sponsored" penalty & endorsement lift

Two counterintuitive findings sit together: agents penalize paid-looking tags and reward platform endorsements. Tagging a product "Sponsored" pushed a baseline 10% selection probability down to 8.9% (Claude Sonnet 4), 8.0% (GPT-4.1), and 7.9% (Gemini 2.5 Flash), a consistent penalty across all three modelsReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17). In the other direction, a platform endorsement such as an "Overall Pick" badge lifted the same baseline 10% to 24.3% (Claude), 19.9% (GPT-4.1), and 42.6% (Gemini), with Gemini rewarding endorsement most stronglyReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17).

The honest implication (and it is an inference, not a growth hack) is that the winning move is to earn legitimate endorsement signals, not to fabricate them; manufacturing badges or gaming "pick" markers is exactly the dark pattern this result would tempt a merchant intoHypothesis (our analysis).

Behavior is model-dependent (and changes on updates)

Every effect above has a different size on each model, and the ranking is not stable over time. ACES found agents concentrate demand on a handful of "modal" products and never select some brands at all, with the pattern differing by modelReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17). More unsettling for anyone optimizing to a single engine: the authors documented that a model update can drastically reshuffle market shares, as it did between Gemini 2.5 Flash Preview and Gemini 2.5 FlashReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17).

This is why AgentMint.net types every model-behavior claim by source and date: what an agent rewards this quarter it may weight differently after the next release. Treat agent behavior as a moving target: the per-engine platform playbooks track where the engines currently diverge.

What this means for merchants: the practical levers

You cannot set your grid position or force an endorsement, but you can control the inputs those signals are computed from. Four levers translate the evidence above into work you can start this week:

Together these four are the inputs to the scorecard. The platform playbooks then show how ChatGPT, Gemini, and Perplexity weight them differently.

Caveat: simulation, not sales

Every number on this page comes from one controlled study, and its limits matter as much as its findings. ACES is a simulation (vision-language-model agents choosing from a mock storefront in randomized trials, across a fixed model set that includes Claude Sonnet up to 4, GPT-4.1, and Gemini 2.5 Flash), not a record of real purchases on live storesReportedACES, Allouah et al., arXiv:2508.02630 (2025-12-17). Read these effects as evidence of what kinds of signals agents weigh and how differently they weigh them, not as guaranteed conversion math for your catalog.

The methodology is inspectable (the ACES simulator is released under the MIT licenseSpec-factACES simulator, github.com/mycustomai/ACES), and AgentMint.net's own research lab is replicating the description-rewrite finding on live catalogs, with results held in a "data collection in progress" state until real numbers exist. Until then, treat ACES as the best available map of how agents choose, and your own measured agent win rate as the territory.

[ newsletter ]