All Pages

Every published page on this site (85 pages), grouped by section. This list is generated from the content collections on every build, so it is always complete. The machine-readable version is the XML sitemap at /sitemap-index.xml; AI agents can also start from /llms.txt.

Entries marked advanced are deep reference, machine surfaces, research, and specialized lanes, such as blueprints, signals, the glossary, diagnostics, protocol comparisons, the timeline, open questions, experiments, reference tables, store integrations, and the updates log. Everything else is core: the main reading path, the section hubs, and the tools.

Start Here

AgentMint.net: How to Win AI Agent Selection Why AI shopping agents pick one store over another, and how to win that choice.
Start Here: The 30-Minute Agent Selection Triage New here? A 30-minute triage: which checklist to run first, and the shortest reading path through AgentMint.net for your situation. Updated 2026-07-10.
About the Author Written by Abdalsalaam Halawa, a Senior E-commerce Engineer helping online stores grow and operate at scale. Evidence-typed research on agent selection. Updated 2026-07-10.

Handbook

The Agent Selection Handbook The practitioner handbook in reading order: foundations, the catalog chapters, and the infrastructure chapters.
Agentic Commerce Optimization: The Complete Guide The complete guide to agentic commerce optimization (AEO for ecommerce): make your catalog legible and preferable to AI shopping agents. Updated 2026-07-11.
How AI Shopping Agents Choose Products How AI shopping agents rank products: the structured signals (price, availability, reviews, data completeness) that decide which store gets picked. Updated 2026-08-20.
Make Your Product Feed AI-Readable An AI-readable product feed leads titles with category and use-case and fills every attribute agents parse: the gaps are why agents skip you. Updated 2026-08-20.
Product Schema (JSON-LD) for AI Shopping Product JSON-LD is the machine-readable layer agents trust when your page and feed disagree: ship Offer, price, availability, and review fields. Updated 2026-08-20.
Product Titles That AI Agents Match Agents match shopper queries to titles almost literally. Lead with the words buyers type, not a brand name like 'The Luna'. Updated 2026-07-11.
AI Crawlers, robots.txt & llms.txt for Stores Blocking AI crawlers in robots.txt hides the page data agents read beyond your feed. Here's the allow-list and what llms.txt adds. Updated 2026-08-20.
Anatomy of a Citable, Comparable Product Detail Page What a product detail page needs so an AI agent can cite it and compare it: title, all-in price, availability, specs, reviews, and a legible substrate. Updated 2026-07-11.
Category and Collection Page Legibility for AI Agents Category and collection pages are how agents reach your products. Make them server-rendered, structured, and truthful so an agent can map your catalog. Updated 2026-07-11.
Serving Agent Traffic Without Breaking Your Origin How to afford being open to AI agents: edge-cache the cheap machine surfaces, allowlist verified bots, and measure the load. Not block legit agents. Updated 2026-08-20.
Information Density: Facts Per Token on Machine Surfaces Maximize verifiable facts per token on machine surfaces. Same content, different format at one URL is negotiation; varying it by user-agent is cloaking. Updated 2026-08-20.
The Agent Selection Maturity Model A five-level editorial framework for agent-selection readiness, from unreachable to measured, mapped to the selection checklist and signals. Updated 2026-07-11.
An Agent Selection Audit, Worked Through a Fictional Store Walk the Agent Selection Checklist through a fictional store, category by category, to see what a real audit inspects and what to fix first. Updated 2026-07-11.
Why You're Not in ChatGPT Shoppingadvanced Products missing from ChatGPT shopping? It's almost always data gaps: vague titles, missing availability, blocked crawlers. Diagnose in order. Updated 2026-08-20.
Shown but Not Selected: Why an Agent Picks a Competitoradvanced You appear in AI shopping answers but an agent keeps recommending a competitor. Diagnose which of four selection gaps is yours, then fix it. Updated 2026-07-11.
Lowest Price but Still Not Recommended by AI Agentsadvanced Cheapest for the query but the AI agent recommends a pricier rival? Price is necessary but not sufficient. Diagnose why raw low price does not win selection. Updated 2026-07-11.
Why You Show in One AI Engine but Not Anotheradvanced Showing in ChatGPT but not Gemini or Perplexity for the same search? The cause is a rail, crawler, or data-source gap specific to the missing engine. Updated 2026-07-11.
When AI Shows the Wrong Price or Stock for Your Productsadvanced You appear in AI shopping answers, but an assistant quotes a stale price, an expired sale, or wrong stock. Diagnose which surface drifted, then fix it. Updated 2026-07-11.

Platforms

AI Shopping Platforms: How to Get Selected Across Engines One catalog, many agents: the shared signals that surface you across ChatGPT, Gemini, and Perplexity, plus the per-engine tie-breakers. Updated 2026-08-20.
ChatGPT Shopping Optimization Get your products surfaced in ChatGPT shopping: fix feed completeness, title-query match, and crawler access, not an 'enroll' button. Updated 2026-08-20.
Gemini & Google AI Mode Shopping Ranking Google AI Mode likely ranks via UCP and your Merchant Center feed: the lever is feed quality and Shopping Graph coverage, not ad spend. Updated 2026-08-20.
Perplexity Shopping Optimization Perplexity recommends what it can crawl and cite: win visibility with citable, structured product pages and clear crawler access. Updated 2026-08-20.
Markdown Mirror for WooCommerceadvanced A free GPLv2 WooCommerce plugin that serves a read-only Markdown mirror of each product page at the product URL plus .md, with zero telemetry. Updated 2026-07-16.

Tools

Merchant Tools Interactive tools for merchants: two evidence-typed checklists and the client-side Agent Legibility Analyzer.
Agentic Readiness Checklist A self-assessment of whether AI shopping agents can discover, read, and transact with your store: the eligibility layer, linking the validator that machine-checks each item.
Agent Selection Checklist A self-assessment of what wins the agent's choice once you're eligible: the legibility, completeness, and measurement signals no validator checks.
Coding-Agent Workflow Copy a prompt from any checklist, blueprint, or implementation chapter, paste it into your coding agent, and it audits or implements against your store.
Agent Legibility Analyzer Paste product HTML, JSON-LD, or text and see token counts, detected structured fields, and a heuristic legibility self-assessment. Runs entirely in your browser.

Research

The AgentMint.net Research Lab Independent, reproducible tests of what moves agent selection: methodology public, results labeled 'Data collection in progress' until real. Updated 2026-07-07.
How We Test Agent Selectionadvanced A repeatable protocol to measure your agent win rate across ChatGPT, Gemini, and Perplexity: prompts, sampling, and honest error bars. Updated 2026-07-07.
Do Description Rewrites Shift AI Recommendations?advanced A field test replicating the ACES finding that description rewrites shift agent recommendations: methodology now, data as it lands. Updated 2026-07-08.
The Agent Selection Indexadvanced A quarterly, reproducible benchmark of how AI shopping agents choose products and offers; methodology published now, numbers gated until author-verified. Updated 2026-07-08.
Agentic Commerce Timelineadvanced A sourced, reverse-chronological record of agentic-commerce events: protocol launches, model updates, and research that shift how AI shopping agents choose. Updated 2026-08-20.
Open Questions in Agent Selectionadvanced A register of what we do not yet know about agent selection: each open question with the evidence we have, the evidence we are missing, and its status. Updated 2026-07-11.

Reference

Reference Look-up surfaces: the glossary, the AI shopping crawler reference, protocol comparisons, and copy-paste blueprints.
Agentic Commerce Glossaryadvanced Plain-English, sourced definitions for the agentic-commerce stack (agent selection, win rate, AEO, UCP, ACP, product feed), each typed by evidence. Updated 2026-08-20.
Agent Win Rate: Definition & How to Measureadvanced Agent win rate = the share of agent shopping sessions where your product is recommended or bought: here's how to define and measure it honestly. Updated 2026-07-07.
AI Shopping Crawler Reference: Every User-Agent Tokenadvanced The dated reference for every AI shopping-relevant crawler token: OpenAI, Google, Anthropic, Perplexity, Amazon, and Meta, plus what's confirmed absent. Updated 2026-08-20.
UCP vs ACP: Which Gets You Selectedadvanced UCP (Google) vs ACP (OpenAI/Stripe): scope, agent reach, and which one gets your store selected on Gemini vs ChatGPT. Implement both. Updated 2026-08-20.
Agentic Payment Protocols, Explainedadvanced AP2, Visa Trusted Agent, and Mastercard Agent Pay decide whether an agent can complete a purchase with you: table stakes to be selectable. Updated 2026-08-20.
Blueprints Versioned, copy-paste-ready, claim-typed templates for the machine surfaces this handbook teaches.
llms.txt for e-commerce catalogsadvanced A production-shaped llms.txt template for a store catalog, ordered by our reasoned decision weight to put your product feed, offers, and policies first. Updated 2026-08-20.
Product markdown-mirror templateadvanced A copy-paste per-product Markdown mirror template, ordered by our reasoned decision weight to lead with the facts that drive selection. Updated 2026-07-08.
Token-efficient product JSON-LD patternsadvanced Copy-paste product JSON-LD skeletons (single product, multi-variant ProductGroup) grounded in Google's specs, led by the selection-weight fields. Updated 2026-07-08.
Edge worker for machine surfacesadvanced Two Cloudflare Worker variants for caching llms.txt and .md mirrors: the CDN path honors stale-while-revalidate; the Cache API refreshes manually. Updated 2026-07-08.

Signals

The Signals Database The structured catalog of agent-selection signals: what makes AI shopping agents pick one store, product, or offer over another, each evidence-typed with honest per-platform status.
ACP feed and checkout readinessadvanced Whether a store targeting ChatGPT checkout ships the ACP feed with correct eligibility flags and the return fields checkout-eligible items require. Updated 2026-07-08.
Agent infrastructure reachabilityadvanced Whether a crawler you allow in robots.txt actually receives your full page - a 200 over HTTPS, not a WAF challenge, rate-limit, or geoblock - rather than being silently turned away. Updated 2026-07-08.
Agent-readiness monitoring and ownershipadvanced Whether you actually watch that agents reach, read, and buy, by confirming agent user-agents in logs, segmenting AI-referred traffic, and giving readiness a named owner who re-checks it. Updated 2026-07-08.
Defined agent win-rate measurementadvanced You define agent win rate for your catalog and measure it with a fixed prompt set across ChatGPT, Gemini and Perplexity, reporting a range with stated sampling rather than a single confident number. Updated 2026-07-08.
Track AI-answer presence, not just referralsadvanced Beyond referral traffic, you track whether each engine names or links your store for your top category queries, since answer-presence is the leading indicator of whether you're even in the consideration set. Updated 2026-07-08.
Descriptions answer relayed buyer questionsadvanced Product copy answers, in buyer language, the concrete questions agents relay from users (fit, compatibility, use-case) rather than marketing fluff that dodges them. Updated 2026-07-08.
Content equivalence (no cloaking)advanced Serving equivalent facts in different formats at one URL is legitimate content negotiation, but serving materially different content by user-agent is cloaking, a spam violation that reduces ranking eligibility. Updated 2026-07-08.
Crawl directives (robots.txt + sitemap)advanced Whether your robots.txt and XML sitemap let AI search and citation crawlers find and reach your product URLs at all. Updated 2026-07-08.
Server-rendered, crawlable contentadvanced Commerce-critical fields and full policy text appear in the raw server HTML, not behind JavaScript, a PDF, or a click-to-fetch accordion, so a non-executing crawler can read them. Updated 2026-07-08.
Delivery ETA is computable per destinationadvanced Concrete handling time, transit time, order cutoff and per-destination shipping data let an agent answer 'when will it arrive?' and 'can it arrive by [date]?' rather than defer to a competitor that can. Updated 2026-07-08.
Query-conditional rewrites are a targeted experimentadvanced Rewriting descriptions to match likely queries produces concentrated, not universal, gains, so treat it as a measured experiment on candidate SKUs rather than a blanket promise. Updated 2026-07-08.
Earn endorsement, never self-label sponsoredadvanced Agents reportedly penalize a self-applied 'Sponsored' tag and reward legitimate platform endorsements, so the durable play is earning genuine editor's-pick or verified-seller status, not faking badge markup. Updated 2026-07-08.
Facts per token, complete against peersadvanced Your listing packs specific, verifiable facts per token (specs, price, GTIN, availability, policy) and fills the comparable attributes the top listings in your category expose, so an agent has real substance to decide on rather than superlatives. Updated 2026-07-08.
Guest checkout completabilityadvanced Whether an agent with no account credentials can complete a purchase, because no forced signup, password, or email verification blocks the path. Updated 2026-07-08.
llms.txt priority orderingadvanced The llms.txt spec exposes only two prioritization levers: the order of the link lists and reserving the 'Optional' H2 for URLs an agent may skip. Updated 2026-07-08.
Machine-readable page representationadvanced Serving a token-light Markdown copy of a page, either via same-URL Accept negotiation or a distinct .md mirror, and advertising it with rel=alternate, hands agents a cheaper-to-read representation of the same facts. Updated 2026-07-08.
Price sensitivity varies by modeladvanced The same discount moves engines differently, so a markdown that shifts share on one engine may barely move another and price strategy should be tested per engine, not blended. Updated 2026-07-08.
Offer consistency and freshness across surfacesadvanced Price, availability, shipping, and return values show identical, current numbers across the product page, structured data, feed, and checkout, so an agent never arbitrates a conflict or quotes an offer you no longer honor. Updated 2026-07-08.
Offer cost legibilityadvanced An agent can read your full cost on a cold product page - the current price and any sale in parseable text with currency and tax, plus shipping, fees, unit price, and any free-shipping threshold - and every figure matches checkout. Updated 2026-07-08.
Offer markup completeness and truthfulnessadvanced Whether the Product/Offer JSON-LD carries a valid price and currency, truthful availability and condition, a resolvable image, and present return/shipping objects that match what the shopper and checkout see. Updated 2026-07-08.
Origin serve-ability for agentsadvanced Keeping your origin open and cheap to serve, by edge-caching the near-static machine surfaces and allowlisting verified bots while rate-limiting only unverified spoofers, so a verified agent always gets a fast 200 instead of a block. Updated 2026-07-08.
Agent-payment rail readinessadvanced Whether your payment stack can complete an agent-initiated purchase over rails like AP2, Visa Trusted Agent Protocol, or Mastercard Agent Pay. Updated 2026-07-08.
Audit grid position bias per provideradvanced Grid position is a reported, provider-specific selection lever, so you record your rendered on-screen position per engine to avoid mistaking a position swing for a content win or loss. Updated 2026-07-08.
Competitive price awareness with parityadvanced Price is a real selection lever whose weight varies by model (ACES measures per-model price elasticity), so you track where your total landed cost ranks for target queries and hold price parity between agents and humans. Updated 2026-07-08.
Product identity and canonical URLadvanced Whether each product has one stable canonical URL matching the feed link plus real manufacturer identifiers, so an agent can match your item to the same product across competing stores. Updated 2026-07-08.
Re-test after every major model updateadvanced Model updates can drastically reshuffle market shares, so a win measured last quarter can silently evaporate and the win-rate protocol should re-run within a set window on each major release. Updated 2026-07-08.
Return terms are fully legibleadvanced The return window, who pays return cost, the return method, and the refund type are each stated in plain prose that matches the structured-data fields, leaving nothing for the agent to infer. Updated 2026-07-08.
Review depth: count, recency, distributionadvanced Rating is a reported selection lever, so complete review data (a truthful count, recent reviews, and a full star distribution shown on the PDP) gives a rating-sensitive agent more credible depth to weigh than a bare average. Updated 2026-07-08.
Seller identity reachable in two hopsadvanced A crawlable path to seller identity, address and contact within two hops of a product page signals a real, accountable merchant that trust-weighting agents won't discount. Updated 2026-07-08.
UCP profile and order-management readinessadvanced Whether a store targeting Google/UCP surfaces publishes a public /.well-known/ucp profile and can return order status for the capabilities it declares. Updated 2026-07-08.
Validation hygiene (use existing validators)advanced Whether structured data, feeds, and protocol manifests are run through existing maintained validators rather than a homegrown checker. Updated 2026-07-08.
Variants and titles use the words shoppers typeadvanced Variant names and product titles lead with explicit, literal attributes (category, size, color, material, use-case) an agent can map to a user's query, not internal codes or brand-only names. Updated 2026-07-08.

Site

Agent Selection Updatesadvanced A dated log of changes to how AI shopping agents select products and stores, and to the protocols merchants track. Updated 2026-08-20.
Abdalsalaam Halawa Abdalsalaam Halawa: Palestinian Senior E-commerce Engineer, 14+ years building online stores, deepest in WordPress and WooCommerce. Author of AgentMint.net. Updated 2026-07-09.
Privacy Policy How AgentMint.net handles your data: no analytics and no cross-site ad tracking, plus an optional email newsletter. We never sell your data. Updated 2026-07-08.
All Pages Every published page on AgentMint.net, grouped by section.