Features · PDP Score

PDP Score

Updated 2026-05-25 Feature eCommerce Insights team

PDP Score grades every D2C and retailer-hosted product-detail page on its AI-readability. It looks at 25 criteria across five buckets — GEO, Content, Semantic, Visual, Technical — and produces a 0-100 score plus a ranked list of recommendations the merchant can act on.

The 100-point AI-readiness score broken down per bucket.
The 100-point AI-readiness score broken down per bucket.

What it measures

PDP Score answers one question per SKU: how AI-readable is this page? The number is calibrated against citation outcomes in Prompt Runs. Pages that get cited tend to score above 70. Pages that stay invisible tend to score below 50. The score is not a vibe — it is reverse-engineered from "what predicts citation."

The five buckets

Twenty-five criteria. Five buckets. Five criteria each. The buckets map to the five signal types AI engines actually weight. See AI visibility for the underlying mechanism.

BucketCriterionWhat it checks
GEOCrawler allow rulesrobots.txt permits GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot, Applebot-Extended.
llms.txt presenceValid llms.txt at the root with product-relevant sections.
AI Agent AccessEach bot returns 200 with content (not 403 / not blocked).
Robots meta tagNo noindex or noai directives that conflict with crawl rules.
Sitemap inclusionThe PDP URL appears in a referenced sitemap.
ContentTitle clarityTitle contains brand, product name, and at least one differentiator.
Description completenessDescription covers what it is, who it is for, and at least one feature in plain prose.
Bullet specificityBullets quote concrete specs and use cases, not marketing adjectives.
FAQ presenceAt least four shopper-language Q&A pairs visible in text.
Review aggregationReview count, star rating, and at least three quoted reviews visible in plain text.
SemanticProduct JSON-LD validityValid Product schema with name, image, description, brand.
Offer schemaOffer with price, priceCurrency, availability, and itemCondition.
AggregateRatingAggregateRating with reviewCount and ratingValue.
BreadcrumbListBreadcrumbList connecting the PDP to category and home.
Entity consistencyBrand name spelled identically across title, schema, alt text, OG tags.
VisualImage alt textEach product image has descriptive alt text including product name.
Image filenameImage filenames contain the SKU or product name (not IMG_4302.jpg).
Open Graph imageog:image present at recommended dimensions.
Twitter Card imagetwitter:image present.
Image countAt least three distinct product images, including one feature shot.
TechnicalResponse timeHTML response < 1500 ms p50 from a US data centre.
Mobile renderingContent visible without JS execution; viewport meta tag present.
Canonical handlingCanonical URL self-referential; no canonical chains.
JS renderingCore content is in initial HTML (not JS-dependent for retrieval).
Page weightTotal page weight < 2 MB on mobile.

Running an audit

  1. From the Products table

    Click any row. The detail view opens with the score recomputed if it is older than seven days, served from cache otherwise.

  2. From a Shopify webhook

    If the Shopify integration is connected, eCommerce Insights re-audits the SKU when product:update fires. The audit runs asynchronously and the score is updated on the table.

  3. Bulk

    Settings → Catalog → Re-audit all. Useful after a site-wide template change. Runs in batches of 25 with backoff.

  4. On a schedule

    Configure in Scheduler. Daily / weekly / monthly cadences supported.

Reading the result

The detail view stacks the five buckets vertically. Each bucket shows its composite (0-20) and the five criteria with pass / partial / fail markers. Click any criterion to expand the underlying observation (e.g. for "Image alt text" you see the actual alt-text strings the audit found).

The header strip shows three numbers: total score, delta since last run, and the timestamp of the last successful audit. Hover the delta to see a sparkline of the last twelve runs.

Recommendations

Below the bucket detail is the recommendation list. Each recommendation has three properties.

Priority
High / medium / low. High means the criterion has high predicted citation impact and is currently failing. Low means it is a nice-to-have or the criterion has small impact.
Effort
5 min / 15 min / 1 hr / multi-day. Effort is computed from the criterion type — JSON-LD updates are 15 min, robots.txt edits are 5 min, image regeneration is multi-day.
Action
The actual change to make. For content recommendations, the action links to the Listing rewrite capsule with the proposed diff. For technical recommendations, the action gives the exact line of code.

Re-running and tracking drift

The Score column on the Products table shows the latest score with a small trend indicator. Open the detail to see the twelve-run sparkline. Drift downward is usually a signal that the underlying PDP template changed or a metafield got cleared during an inventory sync.

Common questions

What is a passing PDP Score?
70 and up is what we call "AI-ready." 50-70 is recoverable with focused work. Below 50 means the page is structurally hard for an AI to cite. The benchmark is calibrated against PDPs that get cited in our weekly Prompt Runs panels.
How long does a PDP audit take?
Ten to thirty seconds per SKU on first run, cached on rerun. Bulk audits across a 1,000-SKU catalogue typically finish in 8-15 minutes depending on response time.
Does PDP Score apply to Amazon SKUs?
No. Amazon SKUs use Rufus Score instead. See channel-aware scoring for the routing logic.
Can I customise the bucket weights?
Not in the public product yet. The default weights are calibrated against citation outcomes (more weight on Semantic and Content because those drive citation most strongly). If you want custom weighting for a specific brand standard, contact support.
What if a PDP is blocked by Cloudflare?
The PdpFetcher falls back to ScrapingBee for 403 / Cloudflare challenges. The score is computed off the fetched HTML regardless of which fetcher succeeded. If both fail, the SKU is flagged "unable to fetch" with no score until the next retry.

Ask AI about this page

Open this topic directly in your favourite AI assistant — the prompt is prefilled.

Was this page helpful?
Thanks — recorded.

Try this yourself

See eCommerce Insights on your own catalog. The free trial covers your full SKU set across five AI engines.

Start free trial
LLM-friendly summary of this page
PDP Score is the channel-resolved AI-readability score for D2C and retailer-hosted product-detail pages. 0-100. Five buckets: GEO (crawler access, robots.txt allow rules for GPTBot/ClaudeBot/PerplexityBot/Google-Extended/CCBot/Applebot-Extended, llms.txt presence and validity, AI Agent Access verdict, robots meta tag, sitemap inclusion), Content (title clarity, description completeness, bullet specificity, FAQ presence, review aggregation visible in plain text), Semantic (Product JSON-LD validity, Offer schema, AggregateRating, BreadcrumbList, entity consistency), Visual (image alt text, image filename, Open Graph image, Twitter Card image, image count), Technical (response time, mobile rendering, canonical handling, JavaScript rendering dependency, page weight). Each bucket has five criteria scored pass/partial/fail. Total score is a weighted sum; weights favour Semantic and Content. Passing threshold around 70. Audit takes 10-30 seconds per SKU. Recommendations ranked high/medium/low by predicted citation impact. Re-run on schedule or on demand. Cloudflare fallback via ScrapingBee. Score is cached for 7 days, refresh on Shopify webhook or manual refresh button.