# Why every reviews app just added an AI summary (and what should actually be in one) Loox and Judge.me both shipped AI review summaries in mid-2026. Here is what a useful summary actually does, where most implementations stop short, and what Iris does differently. By Rohin Aggarwal · 2026-07-30 In the space of a few weeks in mid-2026, both Loox and Judge.me shipped AI-generated review summaries as core widget features. Neither announcement was a surprise to anyone watching the category. The interesting question is not why they built it — of course they did — but what a review summary should actually contain, and where most implementations fall short. **Quick answer** - Both Loox and Judge.me shipped AI review summary widgets in mid-2026, making it a mainstream feature in the reviews-app category. - A basic AI summary generates a paragraph from review text. A useful one links the claim back to a specific review, tags the relevant product attribute, and is readable by AI shopping agents, not just the shopper. - Most implementations stop at the paragraph. The harder parts (claim attribution, product-tag linkage, agent-readable output) are where the category still has gaps. - Iris, Idukki's AI layer, goes further: it surfaces which UGC assets back each claim, tags the relevant products, and outputs the summary in a format AI agents (ChatGPT, Gemini, Google AI Mode) can cite. The category converging on a feature is usually a sign the feature has moved from competitive advantage to table stakes. That is what is happening with AI review summaries. Loox shipped theirs in July 2026. Judge.me's version followed within the same window. If Okendo and REVIEWS.io do not have one live by the end of the year, it will be the exception. That is a reasonable moment to ask: what should a review summary actually do? Because the basic version, a synthesised paragraph that says "shoppers praise the fit and packaging", is easy to build and not very useful. ## What the basic version does The standard AI summary implementation takes your review corpus, runs it through a language model, and outputs a one-to-three-sentence synthesis to display at the top of the reviews section. It is a compression exercise: a shopper who does not want to scroll 200 reviews gets the main themes in a sentence. This is useful. The Baymard Institute has documented consistently that review section friction (too many reviews, no way to filter, no clear signal about what matters) is a real barrier at the decision stage. A paragraph that says "consistent praise for fit and sizing accuracy, frequent mentions of fast delivery, some concerns about packaging for fragile items" tells the shopper something actionable faster than scrolling does. The problem is what it does not do. ## Where the basic version stops A synthesis paragraph with no citations is an assertion. A shopper who sees "shoppers praise the fit" has no way to verify that claim, or to find the three reviews that actually mentioned fit, without scrolling anyway. The summary replaced a reading task with a trust task: do you believe the summary? The product-tag gap is the other problem. A summary that says "consistent praise for sizing accuracy" is not connected to a specific SKU or size range. A shopper buying a large in a different colourway has no signal from that summary about whether "sizing accuracy" applies to their variant. Product-tagged UGC, where the review or video is linked to a specific variant, is the evidence that the summary should be drawing from, but most review-app summaries aggregate across all variants and lose that signal. The third gap is agent readability. AI shopping agents (ChatGPT Shopping, Google AI Mode, Gemini via Agentforce) read structured data, not just rendered HTML. A summary paragraph that lives inside a JavaScript widget and is not published in any structured format is invisible to those agents. The brands with AI-summarised reviews who are also showing up in agent recommendations are the ones who have published that content in a machine-readable layer, not just on the page. ### AI review summary: what most apps ship vs. what is actually useful _The gap between the basic implementation and a complete one._ **Category standard: Basic summary** What Loox, Judge.me and most new implementations ship. - ✓ Reduces review-section friction for the casual shopper - ✓ Auto-generates without manual curation - ✓ Displays as a readable paragraph above the review list - ✗ No citation trail: claims are unverifiable without scrolling - ✗ Aggregates across all variants, loses SKU-level signal - ✗ Not published in a structured format; invisible to AI agents **Idukki Iris: Attributed summary** What a complete implementation should do. - ✓ Each claim links back to the specific reviews backing it - ✓ Product-tagged: summary draws from variant-level UGC - ✓ Published to llms.txt + MCP: AI agents can read and cite it - ✓ Multi-language: synthesised in the buyer's locale, not translated - ✗ More setup than a paragraph widget - ✗ Requires UGC to be product-tagged first (takes a few weeks on a real catalogue) ## What Iris does differently Iris is Idukki's unified AI layer. Its review summary implementation starts from product-tagged UGC, meaning the source material for the summary is already linked to a specific SKU and variant, not to the product as a whole. The summary it generates is therefore variant-specific: if a shopper is on the large-cobalt colourway, the summary draws from reviews on that variant, not from reviews on the small-sage version that sits on the same PDP. Each claim in the Iris summary links to the specific review (or set of reviews) that supports it. A shopper who sees "consistent praise for sizing accuracy" can click through to the four reviews that used that phrasing. The summary is a navigation aid, not a replacement for the underlying evidence. The agent-readability part matters for a different audience. Iris publishes the summary content, along with the supporting review attribution, into the structured feed that Idukki maintains for AI agents: llms.txt, review JSON-LD, and the MCP endpoint. A ChatGPT Shopping agent asking about sizing for a specific product variant can resolve that query against the structured summary data, not just the rendered HTML. That is how a product page earns an AI recommendation, not by appearing in a search result. **In one line:** AI review summaries are now table stakes in the reviews-app category. The differentiation is in what the summary is connected to: specific reviews, specific SKUs, and the structured feed that AI shopping agents actually read. [The Agentforce Commerce GA piece](/blog/agentforce-commerce-ga-product-pages) covers why the agent-readability side of this has become urgent in the last month. [The Idukki vs. Loox comparison](/compare/loox) now reflects the AI Summaries feature in Loox's updated feature set. ### FAQ **Q: What is an AI review summary?** A: An AI review summary is a generated paragraph (or short block of text) that synthesises the main themes from a product's review corpus, displayed at the top of the reviews section. Loox and Judge.me both ship one as of mid-2026. The quality range is wide: from a generic paragraph to a cited, variant-specific, agent-readable output. **Q: Does Loox have an AI review summary?** A: Yes, Loox shipped an AI Summaries widget in July 2026. It displays a synthesised review paragraph on the PDP. It is a basic implementation: it generates a paragraph without per-claim citations or variant-level attribution. **Q: Does Judge.me have an AI review summary?** A: Yes, Judge.me also shipped an AI review summary feature in mid-2026, following Loox. The core behaviour is similar: a synthesised paragraph from the review corpus, displayed above the review list. **Q: What is Iris?** A: Iris is Idukki's AI layer: the unified intelligence behind product-tag suggestions, UGC curation, review summaries and the conversational assistant in the dashboard. For review summaries specifically, Iris draws from product-tagged UGC (variant-specific), links each claim to the supporting reviews, and publishes the summary in a machine-readable format that AI shopping agents can cite. ### Sources - [Loox product page — AI Summaries feature](https://loox.app/product) — Loox AI Summaries widget, shipped July 2026 - [Shopify App Store: Loox](https://apps.shopify.com/loox) - [Shopify App Store: Judge.me](https://apps.shopify.com/judgeme) - Baymard Institute: checkout and product-page UX — Review section friction as a barrier at the decision stage - [Idukki: Agentforce Commerce GA and product pages](/blog/agentforce-commerce-ga-product-pages) - [Idukki vs. Loox comparison](/compare/loox) --- Canonical: https://idukki.io/blog/why-every-reviews-app-added-ai-summary Tags: AI review summary, Loox, Judge.me, Iris, Reviews, UGC