> If you are an AI agent, this file is the complete Brandry corpus in one fetch. > Structured JSON of the same content: https://brandry.ai/data.json > Live tools over MCP (JSON-RPC 2.0): https://brandry.ai/api/ucp/mcp > Agent instructions: https://brandry.ai/agents.md . Auth policy: https://brandry.ai/auth.md # Brandry, full corpus Generated 2026-07-23T04:57:13.351Z from https://brandry.ai. ## What Brandry is Brandry is the AI-readiness layer for car dealerships. It makes a dealer's inventory, offers and store knowledge readable, answerable and transactable for AI agents across MCP, ChatGPT Apps, WebMCP, and answer engines, without replacing the dealer's website, CRM or vendors. Brandry is operated for automotive retailers in the United States. Live tenants include Charlie Obaugh Auto Group (ai.charlieobaugh.com), Bob Allen Motor Mall (boballenmotormall.ai) and Cochran Kia. Real-time inventory is sourced from the MotorsDynamic platform. The dealer-facing MCP server exposes 21 tools today. Agent readiness is measured publicly at https://isitagentready.com on a 0 to 100 scale across five levels: Level 1 Basic Web Presence, Level 2 Bot-Aware, Level 3 Agent-Discoverable, Level 4 Agent-Ready, Level 5 Agent-Native. Dealers typically score around 21/100 before any work; the Brandry layer takes a store to 100/100, Level 5, Agent-Native. Brandry is a reference implementation of and founding participant in AutomotiveMCP (https://automotivemcp.ai), a proposed open standard (draft RFC v0.1, not ratified) for how dealership systems expose inventory, CRM, desking, service and parts data and tools to AI agents over the Model Context Protocol. ## Pricing Four tiers, per rooftop per month, in USD. Each tier includes everything in the tier below it. Any single module can be added a la carte to any tier, so a dealer is never forced to jump a whole step to get one capability. Group pricing is available for multi-rooftop dealer groups. ### Beacon, $499 per rooftop per month Get FOUND. The AI-ready foundation. Machines can finally read your store. Includes: - AI-ready mirror site on ai..com - Full structured data: schema.org Car / Offer / AutoDealer - llms.txt, agents.md, clean sitemaps - Per-VIN NHTSA decode + Monroney - Your public AI-Readiness Score + badge - Correct AI-bot allowlist (so crawlers are not silently blocked) ### Concierge, $999 per rooftop per month (most popular) Get ANSWERED. Everything in Beacon, plus you go live inside every AI assistant. Everything in Beacon, plus: - Live MCP concierge: search, specs, offers, compare, availability - Every AI connects: ChatGPT, Claude and more - Add to ChatGPT / Open in Claude buttons - Your published ChatGPT App - AI-visibility citation probe - 15-60 minute freshness engine ### Showroom, $1,499 per rooftop per month Get SOLD. Everything in Concierge, plus the AI can actually close. Everything in Concierge, plus: - In-chat trade-in estimate + payoff - Real payment calculator: finance, lease, cash, multi-term - Budget match: "a truck for $500/mo" against real inventory - Lead capture straight to your CRM (ADF) - Market & Visibility Scoreboard: price vs 100-mi competitors, days-to-turn ### Command, $1,999 per rooftop per month DONE FOR YOU. Everything in Showroom, and we run the whole play for you. Everything in Showroom, plus: - "Shop Us With AI" marketing kit: badge, CTA, launch social + email + in-store signage - Add-to-ChatGPT button on your real site - Payments-ready agentic checkout path (ACP-aligned) - Group / multi-rooftop rollup + API - Priority provisioning + named contact - Quarterly AI-visibility business review ### Pricing questions dealers actually ask - Per rooftop or per group? Per rooftop, per month. Groups get a single rollup view and group pricing. - Do I have to leave my website provider? No. The layer runs alongside the site you already have. You keep your platform, design, CRM and process. - What if I only want one module from a higher tier? Add it a la carte. Every capability is a module and can be attached to any tier on its own. - Contract or setup fee? Pricing is monthly per rooftop. Provisioning is included in the tier; Command adds priority provisioning with a named contact. - How do I know it is working? The AI-Readiness Score is public and re-checkable at any time on isitagentready.com. From Showroom up, conversation analytics show what buyers asked the AI about the store and where it fell short. ## Modules, the capability catalog Brandry is not one monolithic product. It is 12 modules on a shared brand brain. Each is included from its tier upward and can be added a la carte to a lower tier. ### Included from Beacon: Foundation Everything a machine needs to read your store correctly. On from day one. #### Structured Data + llms.txt Included in: Beacon, Concierge, Showroom, Command. Publishes your rooftop, every vehicle and every offer as schema.org Car, Offer and AutoDealer, plus an llms.txt and agents.md that tell an agent what you are and how to work with you. Who it is for: Every rooftop. This is the floor, not the ceiling. Capabilities: schema.org JSON-LD, llms.txt + agents.md, Clean sitemaps, AI-bot allowlist. #### Window Stickers Included in: Beacon, Concierge, Showroom, Command. Per-VIN decode and a machine-readable window sticker: trim, drivetrain, packages, installed options and factory equipment, attached to the vehicle record an agent reads. Who it is for: Stores whose VDP specs are thin, inconsistent, or trapped in images. Capabilities: NHTSA decode, Monroney data, Per-VIN spec record. #### Readiness Badge + Monitor Included in: Beacon, Concierge, Showroom, Command. Your public AI-Readiness Score with a badge you can show, plus continuous monitoring so a website change that breaks your machine-readability gets caught instead of quietly costing you answers. Who it is for: Any dealer who wants proof, and a tripwire when something regresses. Capabilities: Public score, Embeddable badge, Regression alerts. ### Included from Concierge: Answer Your inventory and your offers, live inside the assistants buyers already use. #### Inventory AI Included in: Concierge, Showroom, Command. The core concierge. Real-time inventory exposed as agent tools: search by need and budget, pull specs, compare two vehicles, check availability, surface photos and the link to the VDP. Answers come from your live feed, not a cached brochure. Who it is for: Every rooftop that wants to be the answer instead of a link. Capabilities: Search + filter, Specs + compare, Availability, Deep link to VDP. #### Offers Included in: Concierge, Showroom, Command. Current incentives, rebates, lease and finance programs and dealer cash, exposed as structured data an agent can quote and reason about instead of guessing from a PDF. Who it is for: Stores that live on OEM programs and want them repeated accurately. Capabilities: Incentives + rebates, Lease and finance programs, Expiry aware. #### Website Specials Sync Included in: Concierge, Showroom, Command. Whatever you merchandise on your website (specials rows, featured units, payment callouts) is mirrored into the AI layer and kept in sync, so the assistant never quotes a special you pulled last week. Who it is for: Anyone running an active specials page. It stops the two surfaces from drifting. Capabilities: Specials mirroring, Continuous sync, Drift detection. #### ChatGPT App Included in: Concierge, Showroom, Command. Your own published app inside ChatGPT, built on the Apps SDK, running against the same live inventory. Buyers add your store and shop it in the conversation they are already having. Who it is for: Stores that want a named presence in ChatGPT, not just to be cited. Capabilities: Apps SDK, Add-to-ChatGPT button, Live inventory. ### Included from Showroom: Sell The agent stops describing cars and starts doing the work a salesperson does. #### Website RAG (Brand Knowledge) Included in: Showroom, Command. We index your real site: hours, staff, departments, service and parts policies, financing and warranty pages, your brand voice. The agent answers store questions the way your people would, instead of inventing an answer or refusing. Who it is for: Groups with real policies and a real voice they do not want flattened. Capabilities: Site knowledge index, Policy + FAQ answers, On-brand tone. #### Payment + Affordability Included in: Showroom, Command. Real math in the conversation: finance, lease and cash across multiple terms, trade-in estimate with payoff, and budget match that turns "a truck around $500 a month" into actual units on your lot. Who it is for: Any store where the first real question is the payment. Capabilities: Finance / lease / cash, Trade estimate + payoff, Budget to inventory match. #### Conversation Analytics Included in: Showroom, Command. What buyers actually asked the AI about your store, which vehicles surfaced, which questions the agent could not answer, and where a conversation stopped short of a lead. The gaps are the roadmap. Who it is for: Managers who want to see demand before it shows up in the CRM. Capabilities: Question themes, Vehicle surfacing, Unanswered gaps, Drop-off points. ### Included from Command: Everywhere The newest agent surfaces, and the tooling your marketing partner plugs into. #### WebMCP Overlay Included in: Command. Your own website becomes operable by an agent in the browser. Using WebMCP (a Chrome origin trial), the overlay exposes your site's real actions (search inventory, price a payment, start a lead) as tools an in-browser agent can call on the page the shopper is standing on. Who it is for: Early movers who want to own the browser-agent surface before it is table stakes. Capabilities: WebMCP origin trial, On-site agent tools, No site rebuild. #### Agency Brand-Knowledge MCP Included in: Command. An MCP endpoint pointed at your agency's own tools. Your creative team, or their AI, can pull live inventory, current offers and the dealer's brand knowledge straight into ad copy, landing pages and campaigns, so the creative is on-brand and never quotes a sold unit. Who it is for: Agencies and in-house marketing teams. Included for resale partners. Capabilities: MCP for creative tooling, Live inventory + offers, Brand voice + guardrails. ## Integrations Brandry builds one authoritative model of a store, then speaks it to whichever agent is asking. A new AI channel is a new adapter on the same brain, not a rebuild of the dealer's stack. ### Agent surfaces Brandry speaks #### Claude, via MCP (Live) A Model Context Protocol server per rooftop. Claude connects to it and gets real tools, not scraped text: search inventory, pull specs, compare, check availability, quote offers, run payment math, capture a lead. Facts: 21 tools exposed today, Live inventory, Tool calls, not scraping. #### ChatGPT, via the Apps SDK (Live) A published ChatGPT App for the store, built on OpenAI's Apps SDK and pointed at the same brand brain. Buyers add your dealership and shop it inside the conversation. Facts: Apps SDK, Add-to-ChatGPT button, Same data as MCP. #### WebMCP, in Chrome (Origin trial) WebMCP lets a page declare tools to a browser-side agent. Our overlay exposes your site's real actions, so an agent working in the browser can search your inventory and price a payment on your own site. Facts: Chrome origin trial, Overlay on your live site, No rebuild. #### Answer engines and AI search (Live) The crawl-and-index path. Full schema.org JSON-LD for Car, Offer and AutoDealer, an llms.txt and agents.md, clean sitemaps, and an AI-bot allowlist that is actually correct, so assistants that read the open web read you properly. Facts: schema.org JSON-LD, llms.txt + agents.md, AI-bot allowlist. #### Your dealer website (Live) A per-dealer overlay that adds the agent affordances (badge, Add-to-ChatGPT, agent-readable markup, WebMCP hooks) to the site you already have. You keep your platform, your design and your vendor. Facts: Keep your platform, Drop-in overlay, No migration. ### Dealer data sources Brandry reads #### MotorsDynamic inventory (Primary data) Real-time dealer inventory from the MotorsDynamic platform: units, pricing, photos, status. This is the spine of every answer the agent gives about what is on your lot. #### Your website (Brand knowledge) Indexed for brand knowledge: hours, departments, staff, service and parts, financing and warranty policy, and the way your store actually talks. It is what keeps the agent on-brand instead of generic. #### DMS, CRM and website platforms (Generic adapters) Handled generically rather than by brand name. If your system can export an inventory feed or accept a standard ADF lead, we can wire it. Tell us what you run and we will confirm the path before you buy anything. #### Offers and incentive programs (Offers) OEM incentives, rebates, lease and finance programs, dealer cash and website specials, normalized into structured offers an agent can quote with the right expiry and the right conditions. ### Infrastructure #### Cloudflare The AI layer runs on Cloudflare's edge. It also means the crawler policy is handled deliberately: Cloudflare now gates AI crawlers by default, and a default-deny setting is one of the quietest ways a dealer becomes invisible. We make sure the agents you want are allowed and the ones you do not are not. ## Partners Brandry runs an agency and reseller white-label program at wholesale pricing, and participates in the AutomotiveMCP standard ecosystem for platform, vendor and founding partners. See https://brandry.ai/partners. ## Articles ### Why the industry needs an open standard (AutomotiveMCP) URL: https://brandry.ai/blog/open-standard-automotivemcp . Markdown: https://brandry.ai/blog/open-standard-automotivemcp.md . Published 2026-07-15. Category Standards. 6 min read. AI-to-dealer integration today is N times M bespoke wiring: weeks and tens of thousands of dollars per connection, fragile, and nothing reusable. AutomotiveMCP is a proposed open standard to fix that. Here is the argument. Start with arithmetic, because the argument for a standard is arithmetic before it is philosophy. Take the number of AI assistants a dealer might want to be reachable from. Call it N. Now take the number of dealership systems that hold something an assistant needs: the DMS, the CRM, the desking tool, the website platform, the service scheduler, the parts catalog, the inventory feed. Call it M. Without a shared protocol, every useful connection is a pair. One assistant, one system, wired by hand. That is N times M integrations, each one taking weeks, each one costing tens of thousands of dollars, each one breaking when either side ships a change, and each one producing nothing reusable for the next pair. Both N and M are growing. The product of two growing numbers grows faster than anyone's integration budget. This is not a problem you solve by working harder or raising more money. It is a problem you solve by changing the shape. ## What bespoke wiring costs, concretely The dollar figure is the least of it. The real cost is fragility. A hand-built bridge between one assistant and one DMS encodes assumptions about field names, authentication and data shapes on both sides. Either side ships a routine update and the bridge quietly returns wrong answers, which in this context means an assistant confidently telling a shopper about a vehicle that sold last Tuesday. The second cost is that it is disposable. Nothing learned building assistant A to system B helps with assistant C. You paid for a connection, not for capability. The third cost is who it locks out. At tens of thousands of dollars per bridge, only the largest groups and the largest vendors participate. Single rooftops and regional platforms are priced out of being reachable at all, which means the AI layer of automotive retail ends up representing a small slice of the industry and calling it the market. The fourth cost is the one that should worry dealers most. When integration is expensive, whoever can afford to build all of it becomes the mandatory intermediary. They sit between every dealer and every assistant, and they charge rent on that position indefinitely. The industry has been on the wrong side of that arrangement before and knows exactly how it ends. ## What a standard changes A shared protocol turns N times M into N plus M. Each assistant implements the standard once. Each dealership system implements the standard once. Any assistant then speaks to any system, without either party having heard of the other. That is what [AutomotiveMCP](https://automotivemcp.ai) is: a proposed open standard, currently a draft RFC at version 0.1, for how dealership systems expose data and tools to AI agents over the Model Context Protocol. It covers the domains that actually matter in a store, inventory, CRM, desking, service and parts, so that the meaning of a vehicle record or a service appointment is agreed rather than renegotiated for every integration. It is deliberately more than a document. The draft includes a specification, versioned JSON Schemas so implementations can be validated rather than argued about, an adoption directory showing who has implemented what in public, a certification and conformance mark so that being compliant is a checkable claim, and neutral governance so no single vendor owns the pipe. That last item is the one that makes a standard a standard. A specification controlled by one company is a product with better marketing. ## Why we are pushing this against our own interest Brandry is a reference implementation and a founding participant in AutomotiveMCP. We are not its owner, and we are not trying to become its owner. It is fair to be suspicious of a vendor advocating for an open standard, so let us be direct about the trade. A ratified open standard is worse for our moat. It makes it easier for competitors to interoperate, easier for platforms to serve agents without us, and easier for a dealer to leave. We think that is the correct trade anyway, for two reasons. The first is that a standard grows the thing worth competing over. If being reachable by AI requires a bespoke six-figure project, almost no dealers do it and there is very little market. If it requires implementing a published spec, the whole industry can participate, and then the competition is about who builds the best experience on top. We would rather be the best implementation of an open protocol than the only implementation of a closed one. The second is that closed pipes lose eventually and hurt everyone in the meantime. The web won with open protocols. Email won with open protocols. Payments have spent decades slowly converging on standards after long, expensive detours through proprietary rails. Automotive retail can either take the detour or skip it, and skipping it is worth more to the industry than any single vendor's temporary advantage. ## The honest status AutomotiveMCP is a draft. RFC v0.1 means proposed, not adopted. It is not ratified, it is not an industry mandate, and nobody is required to implement it. Anyone telling you otherwise is overselling, and a standard that oversells its own status does not become a standard. What it does have is a real specification, real versioned schemas, a working reference implementation running against live dealer inventory in production, and an open call for founding partners. Early participants get the thing that matters most in standards work: influence over the schemas for the domains they know best, before those shapes harden and everyone lives with them for a decade. If you build a DMS, a CRM, a desking tool, a website platform, a scheduler or a parts catalog, this is the moment your input is worth the most. If you run stores, the useful thing you can do is ask your vendors a single question: are you implementing an open standard for agent access, or are you building me another private bridge. That question, asked often enough by enough dealers, is what turns a draft into a standard. Read the spec at [automotivemcp.ai](https://automotivemcp.ai). ### MCP, WebMCP, and the agentic web: a dealer's field guide URL: https://brandry.ai/blog/mcp-webmcp-field-guide . Markdown: https://brandry.ai/blog/mcp-webmcp-field-guide.md . Published 2026-06-24. Category Technology. 7 min read. A plain-language guide to the protocols behind AI shopping. What MCP is, how WebMCP differs, where ChatGPT apps and schema.org fit, and which ones actually matter for a dealership. You are going to be sold MCP this year. It will appear in vendor decks, in conference sessions, and in emails from people who learned the acronym last week. It is worth twenty minutes to understand what it actually is, because the difference between the protocols determines what your store can and cannot do. Here is the field guide, in plain language, with no assumption that you write software. ## The problem all of this solves An AI model on its own can only produce text. To do something useful about your dealership it needs two things: current information, and the ability to take actions. There have historically been two ways to give it those. Let the model read your website, which is unreliable because websites are built for eyes and because reading gives you a snapshot rather than the truth right now. Or build a custom integration between one specific AI product and one specific system, which works well and costs a great deal, and has to be redone for the next AI product. Every protocol below is an attempt at a third option: a standard way for a system to say here is my data and here are the things you can ask me to do. ## MCP: the connection between an assistant and your systems The Model Context Protocol is a standard for exposing data and tools to an AI assistant. Think of it as a menu your systems publish. Each item on the menu is a tool with a name, a description, defined inputs and defined outputs. For a dealership the menu looks like search inventory, get vehicle details, compare two vehicles, check availability, look up current offers, estimate a trade, calculate a payment, capture a lead. When a shopper asks a question, the assistant picks the relevant tool, calls it, gets structured data back, and answers from that. Our own dealer server exposes twenty one tools today. Three properties matter to you. It is live. The assistant is querying your actual feed at the moment of the question, not reciting what a crawler saw last week. Availability answers are correct. It is structured. The assistant receives typed data rather than prose it has to interpret, which is the single biggest reduction in the chance of an invented answer. It is reusable. Because MCP is a standard rather than a private integration, any assistant that speaks it can connect. You build the connection once instead of once per AI product. MCP is the difference between an assistant that has read about your store and one that is connected to it. ## ChatGPT apps: a named presence inside one assistant OpenAI's Apps SDK is how you get an actual app inside ChatGPT, with your name on it, that a user adds deliberately. It can render richer interface elements than plain chat and it is discoverable within that product. MCP and a ChatGPT app are complements, not alternatives. The app is a storefront inside one very large assistant. MCP is the wiring that any assistant, including that one, can connect to. Sensibly built, both point at the same underlying data so they can never disagree about what is on your lot. The strategic point is that an app is opt-in and named. Someone adds your dealership. That is a materially different relationship than being cited occasionally in a general answer. ## WebMCP: agents that operate your website The newest of the four, currently a Chrome origin trial, and the one most likely to be misexplained to you. MCP connects an assistant to a server somewhere. WebMCP lets a web page itself declare tools to an agent running in the browser. The shopper is on your site, an agent is working on their behalf in that browser, and your page can offer it real capabilities: search this inventory, price this payment, start this lead. Why this matters is context. The agent is not guessing what your site can do from the rendered HTML, and it is not clicking around a page it does not understand. It is calling functions you defined, on the page the shopper is actually looking at, with the shopper's session and preferences intact. It is early. Origin trial means Chrome is testing it with real sites before committing, and the specification is still moving. It is worth building for now precisely because it is early: this is the surface where being first is cheapest. ## schema.org and llms.txt: the readable floor The least exciting item on the list, and the one most dealers actually need first. schema.org is a shared vocabulary for describing things on a web page so machines understand them. For automotive that means Car, Offer and AutoDealer types, embedded as JSON-LD, telling a machine that this is a vehicle, this is its VIN, this is the price, this is who sells it, this is whether it is available. llms.txt is a newer and simpler convention: a plain text file at a known location on your domain that tells an AI agent what this site is, what it offers, and where the authoritative information lives. The same spirit as robots.txt, aimed at a different reader. Neither is live and neither lets an agent do anything. They are how the crawl-and-index path works, which still matters enormously, because answer engines and AI search read the open web and because a model with no live connection to you falls back to whatever it can read. There is a related trap here. Cloudflare now gates AI crawlers by default. Perfect structured data does you no good if a default setting blocks the agents you want. Check that specifically. ## How they fit together The mental model that holds up: schema.org and llms.txt make you readable, MCP and ChatGPT apps make you answerable, WebMCP makes you operable, and the layer underneath all of them should be one authoritative model of your store rather than four independent copies. That last part is the thing to insist on when a vendor pitches you. If the ChatGPT app has its own inventory copy and the website has another, they will disagree, and they will disagree in public, in front of a buyer. One source of truth, many surfaces, is the only shape that survives the next protocol. ## What to ask a vendor Five questions that separate the real from the rehearsed. Is the data live at question time, or crawled on a schedule, and what is the freshness window. Which surfaces are actually deployed today for a real customer, with a URL you can check. Do all of the surfaces read from one source, and what happens when a unit sells. Which tools can the agent call, specifically, and can it complete a lead into my CRM. When the next surface appears, is that an adapter or a rebuild. That last question is the whole game. Two years ago none of these protocols existed in the form they exist in now. The specific acronyms will keep changing. What should not change is the truth about your store, held in one place, ready to speak whichever protocol shows up next. ### What agent-ready actually means: the five levels URL: https://brandry.ai/blog/what-agent-ready-means . Markdown: https://brandry.ai/blog/what-agent-ready-means.md . Published 2026-06-03. Category Fundamentals. 6 min read. Agent-ready is not a badge you either have or do not. It is a ladder, from a site a machine cannot parse to a store an AI can transact with. Here is what each of the five levels means in practice. Every few years the industry adopts a phrase faster than it agrees on a meaning. Mobile-first went that way. Omnichannel went that way. Agent-ready is going that way right now, and by the end of the year every vendor in the space will have it on a slide. So here is a definition specific enough to argue with. Agent-readiness is not binary. It is a ladder with five rungs, and each rung answers a different question about what an AI can do with your store. ## Level 1: Invisible At Level 1 a machine requesting your pages gets a shell. The inventory grid assembles in the browser, the specs live inside images, the offers are a PDF, and there is little or no structured data describing any individual vehicle. Often the crawler policy blocks AI agents by default and nobody in the store knows. The important thing about Level 1 is that it is completely compatible with a great website. Fast, attractive, converting well, redesigned last year. Human experience and machine legibility are separate axes, and almost nobody was building for the second one until recently. This is where most dealers start when they first run the check, typically somewhere around twenty one out of one hundred. ## Level 2: Readable At Level 2 a machine can establish the basics. There is valid schema.org markup identifying the business as an AutoDealer with a real address, hours and phone number. Some vehicle data is present in a parseable form. The sitemap is clean and the robots policy does not accidentally exclude the agents you want. An assistant at this level can confirm you exist and roughly what you are. It cannot reliably answer a question about a specific vehicle, because the vehicle data is partial, inconsistent, or stale. In practice a Level 2 store gets mentioned but not recommended, because the model has nothing concrete enough to stand behind. ## Level 3: Understood Level 3 is where structured data becomes complete rather than decorative. Every vehicle carries proper Car and Offer markup: VIN, year, make, model, trim, drivetrain, mileage, price, availability, photos, and a link that resolves to the right VDP. Per-VIN specs are decoded into text rather than trapped in a window sticker image. Offers and incentives are structured objects with conditions and expiry dates rather than a marketing graphic. Now an assistant can answer factual questions about your inventory: do you have a three-row SUV under a certain price, what trim is this VIN, what is the drivetrain. This is a real threshold. It is the first level at which you can be the source of an answer instead of a footnote in someone else's. The limitation is freshness. Level 3 still depends on crawling, which means the assistant is working from a snapshot. If a unit sold this morning, the answer may be wrong this afternoon, and being confidently wrong about availability is its own kind of damage. ## Level 4: Answerable Level 4 replaces the snapshot with a connection. Instead of waiting to be crawled, your store exposes a live endpoint that assistants can query in the moment, in practice a Model Context Protocol server, a published ChatGPT app, or both. The difference is not subtle. At Level 3 the assistant recites what it read. At Level 4 it asks your systems a question and reports what came back, right now. Search by need and budget, compare two units, check whether something is still on the lot, quote the current program. The answer is as current as your feed, which is the standard a shopper already expects from every other category they buy in. This is also the level at which you get a named presence rather than an incidental mention. A buyer can add your store inside the assistant and shop it directly. You are no longer hoping to be retrieved. You are connected. ## Level 5: Agent-Native At Level 5 the assistant stops describing and starts doing. It has tools, and the tools do the work a salesperson does at the front of a deal: estimate a trade with the payoff folded in, run real finance, lease and cash math across multiple terms, turn "around five hundred a month" into actual units on your lot, answer a policy question the way your store would answer it, and drop a structured lead into your CRM without the buyer ever leaving the conversation. It also means being present on more than one surface, because buyers are not all in the same place. The same underlying model of your store answers over MCP, inside a ChatGPT app, to an agent operating your own website in the browser through WebMCP, and to the answer engines that read the open web. This is the top of the checker's scale, one hundred out of one hundred, and it is where the live Brandry tenants sit today. Not as a projection, as a number anyone can reproduce by running the same public check against the same live sites. ## Why the ladder matters more than the badge Two things follow from framing this as levels rather than a yes or no. The first is that you can locate yourself honestly. Most stores are not at zero. They have some markup, a decent sitemap, maybe a vendor who did a competent job on the basics. Knowing you are at Level 2 and not Level 4 tells you exactly which work remains, and it is usually less work than people fear. The second is that claims become checkable. When someone tells you their product makes you AI-ready, the useful follow-up is which level, measured how, verifiable where. A number produced by a public checker against a live URL is a different kind of assertion than a bullet on a slide. That is the entire reason we made the checker public even though anyone, including our competitors, can run it. Ladders are also honest about sequencing. You cannot skip to Level 5. Live tools built on top of inventory data that a machine cannot parse correctly will confidently produce wrong answers faster. The unglamorous work at Levels 2 and 3 is what makes the impressive work at Levels 4 and 5 trustworthy. Start by finding out which rung you are on. Everything else is a decision about how far up you want to go. ### Why AI shopping changes the dealer funnel URL: https://brandry.ai/blog/ai-shopping-changes-the-funnel . Markdown: https://brandry.ai/blog/ai-shopping-changes-the-funnel.md . Published 2026-05-14. Category Strategy. 6 min read. When an assistant does the research, the comparison and the payment math before a buyer ever visits a website, the classic dealer funnel stops describing reality. Here is what replaces it. The dealer funnel has been stable for a long time. Awareness at the top, then research, then consideration across a handful of stores, then a lead, then a visit, then a deal. Every tool the industry bought over the last fifteen years was built to widen one stage or reduce the leak between two of them. That model assumed something specific: the buyer moves through the stages themselves, in a browser, visiting multiple dealer websites along the way. Break that assumption and the whole diagram stops describing what is happening. ## The middle collapses into one conversation Watch how someone shops with an assistant. They do not open five tabs. They describe a situation in plain language, often including constraints they would never type into a search box: three kids and a dog, a trade with some negative equity, needs to stay under a specific monthly number, has to happen before the end of the month. The assistant does the research. It narrows the segment, compares trims, factors the budget, considers the trade, and produces a short list. Frequently it names specific vehicles and specific dealers. Everything from research through consideration just happened inside one exchange. There was no comparison of dealer websites, because no dealer websites were visited. By the time the buyer touches anything you own, the consideration set has already been decided. You were either in it or you were not, and you have no record of which. ## Being in the answer replaces being in the results The old competitive question was about placement: are you ranking, are you bidding, are you on the marketplace. Those are all questions about appearing in a list that a human then chooses from. An assistant does not usually return a list. It returns an answer, often naming one or two options with a reason attached. That is a much smaller space to occupy, and getting into it works differently than ranking does. It is not about spend or authority. It is about whether the model has specific, current, verifiable information about your store that it is willing to stand behind. This is genuinely good news for a lot of dealers, because it is not a budget contest. A single rooftop with complete structured data and a live inventory connection can be the answer over a larger group that has neither. The work is real, but it is work, not spend. ## The lead arrives later and warmer When the assistant handles discovery, comparison and a first pass at the payment, the buyer who finally contacts you is much further along than a classic lead. They know the trim they want. They have a payment range that survived contact with arithmetic. They have often already been told what their trade is roughly worth. Two consequences follow, and one of them is uncomfortable. The good one: these contacts convert better, because most of the qualifying already happened. Your people spend their time on people who are actually in market for something specific. The uncomfortable one: total lead volume can fall while sales hold or improve. If your team is measured on lead count, this looks like a problem for exactly as long as it takes someone to look at closing rate. Any store moving into this properly should decide in advance which number it is managing, because the two will disagree for a while. ## Your website changes jobs The website does not become unimportant. It becomes a different kind of important. Historically the site had to persuade. It was where a shopper who might also be looking at three competitors got convinced. In an assistant-mediated journey, persuasion has often already occurred somewhere else, and the site is where the buyer lands to confirm and act. Is the car actually there, is the price what I was told, can I book the time slot, can I start the paperwork. At the same time your site takes on a second audience that never sees the design at all. It has to serve machines correctly: complete markup, per-VIN specs in text, structured offers, a crawler policy that lets the right agents in. Those two audiences want different things from the same pages, and most sites today are built for only one of them. The newest wrinkle is that the agent may show up on your site rather than instead of it. WebMCP, currently a Chrome origin trial, lets a page expose its real actions as tools an in-browser agent can call. In that world your website is not just readable to an agent, it is operable by one, on behalf of a shopper who is sitting right there. ## What to actually do about it Four things, in order, none of which require a redesign. Find out where you stand. Run your URL through a public agent-readiness check and get a number instead of a feeling. If you are around twenty one out of one hundred, you are in normal company, and you now know the size of the gap. Fix the readable floor. Complete schema.org markup on every vehicle and every offer, specs decoded out of images, an llms.txt, clean sitemaps, and a deliberate AI crawler policy. This is unglamorous and it is the prerequisite for everything else. Get connected, not just crawled. A live endpoint means assistants query your real inventory in the moment instead of reciting a stale snapshot. Being confidently wrong about availability is worse than being absent. Change what you measure. Add questions your funnel never had to ask: what did buyers ask an assistant about our store, which of our vehicles surfaced, what could the agent not answer, where did the conversation stop short of a lead. The unanswered questions are the highest-value list you will get all year, because each one is a specific deal that almost happened. The funnel is not gone. It got compressed into a conversation, and the only meaningful question is whether your store is present inside it. ### Your dealership is invisible to ChatGPT (and how to check) URL: https://brandry.ai/blog/invisible-to-chatgpt . Markdown: https://brandry.ai/blog/invisible-to-chatgpt.md . Published 2026-04-29. Category Visibility. 5 min read. Most dealer websites render beautifully for humans and return almost nothing useful to an AI assistant. Here is why that happens, what it costs you, and how to check your own store in about a minute. There is a specific kind of bad news that never shows up in your analytics: the customer who never arrived. No session, no bounce, no abandoned form. They asked an assistant a question, got an answer that named a dealership, and drove there. If the dealership named was not yours, nothing in your reporting will ever tell you the conversation happened. This is the part of the AI shift that is easy to miss. It does not look like a traffic drop. It looks like nothing at all. ## What an assistant actually receives Open your VDP and look at it. Now consider what arrives on the other end when a machine requests that same page. On a large share of dealer sites, the answer is: a shell. The inventory grid is assembled in the browser by JavaScript after the page loads, so a fetch that does not execute scripts gets an empty container. The trim and package detail that a shopper reads off the window sticker lives inside a JPEG, which is opaque to a text model. The payment is calculated by a widget that runs client side. The current offers are a PDF, or worse, an image of a PDF. And the structured data, the machine-readable summary that says "this is a car, this is its VIN, this is its price, this is who sells it", is either missing entirely or present in a thin, generic form that describes the dealership but not a single vehicle. Then there is the quietest failure of all: the crawler policy. Cloudflare moved to gating AI crawlers by default, and plenty of dealer sites now block AI user agents without anyone in the store having made a decision about it. You can have flawless structured data and still be unreachable because a default setting somewhere says no. Stack those together and the assistant is not being unfair to you. It genuinely cannot see what you have. ## Why it recommends someone else Assistants do not fail loudly. When a model lacks specific, current information about your store, it does not announce a gap. It answers the question with whatever it does have, which is usually one of three things. It falls back to a third party. Marketplaces and aggregators invest heavily in machine-readable inventory, so their version of your stock is often more legible than yours. The buyer gets an answer built on someone else's summary of your lot, complete with someone else's lead form. It falls back to a competitor. The store two exits down that happens to run a platform with clean structured data becomes the concrete, checkable recommendation. Concreteness wins. An assistant asked to name a dealer will name the one it can describe. Or it falls back to generalities. It tells the buyer to check local dealers, which is another way of saying it could not help, and the buyer goes back to searching. None of these outcomes generate a signal you can see. That is the whole problem. ## The check takes about a minute You do not have to take any of this on faith, and you should not. Run your own URL through the public checker at [isitagentready.com](https://isitagentready.com). It looks at your live site the way an agent does and scores what a machine can actually read, understand and act on, from zero to one hundred across five levels. Most dealers who run it for the first time land somewhere around twenty one out of one hundred. That is not a mark of a bad website. Plenty of stores scoring in the low twenties have genuinely excellent sites by every human measure: fast, attractive, converting well, recently redesigned. The score is measuring a different axis entirely, one that nobody was building for until very recently. If you want to sanity check it yourself before trusting any tool, here are three things you can do in the next ten minutes. Ask an assistant directly. Open ChatGPT or Claude and ask, in the voice of a real shopper in your market, which dealer has a specific kind of vehicle in a specific payment range. See who gets named. See whether the details about your store are current, or invented, or absent. View the page source of a VDP, not the rendered page. In your browser use view-source rather than inspect, since inspect shows you the DOM after JavaScript has run. Search that raw source for the VIN and for `application/ld+json`. If the VIN is not there and there is no JSON-LD block describing the vehicle, a crawler that does not execute scripts is getting nothing. Check your robots and your AI bot policy. Look for `/robots.txt` and see what it says about AI user agents. Then ask whoever manages your CDN whether AI crawler blocking is on. A surprising number of stores find the answer is yes and nobody chose it. ## What fixing it actually means The remedy is not a redesign. Your website is not the problem, and rebuilding it will not move this number much on its own. What moves it is making the same inventory legible in a second form: complete schema.org markup for every vehicle and every offer, a per-VIN spec record that does not live inside an image, an llms.txt that tells an agent what you are and how to work with you, clean sitemaps, and a crawler policy that deliberately allows the agents you want to reach you. That is the readable floor. Above that floor sits the part that actually wins the recommendation: a live connection, so an assistant queries your real inventory in the moment rather than relying on whatever it crawled last week, and real tools so it can estimate a trade, run a payment and hand you a lead inside the conversation. The first step is just knowing. Run the check, get the number, and decide from there. Being invisible is a fixable condition. Not knowing you are invisible is the expensive part. ## Machine-readable endpoints - MCP (JSON-RPC 2.0): https://brandry.ai/api/ucp/mcp - MCP server card: https://brandry.ai/.well-known/mcp/server-card.json - A2A agent card: https://brandry.ai/.well-known/agent-card.json - UCP discovery: https://brandry.ai/.well-known/ucp - API catalog (RFC 9727): https://brandry.ai/.well-known/api-catalog - Agent skills index: https://brandry.ai/.well-known/agent-skills/index.json - Agent instructions: https://brandry.ai/agents.md - Auth policy: https://brandry.ai/auth.md - Structured feed: https://brandry.ai/data.json - Search index: https://brandry.ai/search-index.json - Sitemap: https://brandry.ai/sitemap.xml - Agentic discovery sitemap: https://brandry.ai/sitemap_agentic_discovery.xml ## Contact Email: hello@brandry.ai