Great thread, I'm playing catchup here. Gregg's buzzword takedown should be printed on a plaque and hung in every vendor office (my company included).

The ground floor comments are spot on. We're in here debating AI-ready VDPs and RAG pipelines while most dealers can't tell you if their NAP is consistent across 50 directories. The majority of the time I talk to dealers about SEO their GBP is not optimized, just claimed and abandoned like a New Year's gym membership. Local citations a mess. Core Web Vitals failing. Canonicals broken. Most aren't ready for "Make us show up in LLMs" and most don't want to stretch before a workout.

Once the basics are actually handled, content is where leverage lives. We use Hrizn with our clients. Best content OS in the space and I'm not being polite or pitchy. Their Dealer DNA components are the real deal. They're not generating another soulless Silverado blog post that reads like it was written by a chatbot with a thesaurus. They're building content tied to YOUR store, YOUR market, YOUR identity. With the March spam update live, every dealer running copy-paste content across 12 rooftops has gotta be rethinkin' their content strategy.

Where I'd really push this thread selfishly... the biggest problem in automotive isn't content or infrastructure. It's that every dealership's context lives in the GM's gut and gets distributed via vibes and monthly vendor phone calls (if they make them). 25+ SaaS platforms all operating in silos. Website vendor gets one story. Ad agency gets another. BDC is out there freelancing. We've been running on gut-distributed context for 30 years and calling it a digital strategy.

What could soon replace gut is a context or intelligence syndication layer. Capture what makes the dealership unique, update in real time, and push it everywhere. The dealers who win next won't be the ones with the most tools. They'll be the ones whose intelligence is actually organized and accessible instead of trapped in one person's head or gut. There are tons of providers building this layer into THEIR applications. To me, that's the same walled garden problem we've struggled with in this industry for the last 25 years. Every vendor wants to be the brain. Nobody wants to be the nervous system. Content, Ads, comms could all be leverage and operate harmoniously.

What's missing is a single context engine that syndicates intelligence out to every provider AND pulls the invisible stuff back in. Training data. Cross-platform comms. API usage and cost. Inventory. The operational signal that's actually driving output and nobody's monitoring because it's buried across 30 logins nobody opens. Who knows. This is moving so fast it's tough to keep up.

I've kept a running list here: Photo Providers

You're playing in some deep murky waters hunting for a test dealer on a DMS system. Who do you view as your competition?

This thread is pretty amazing. Despite the overly technical conversation for the average dealer, you guys are proving that a new breed of SEO considerations needs to be understood.

There is no doubt SEO is climbing the importance ladder because of AI, and your posts will be found for many months/years to come.

AI report from main street.
I am doing work my imagination always could visualise but was so complex I never made it to 1st base.

Every week, I have many holy shit moments. I'm in another one right now.

joe.pistell said:

Remember what I said, the more complex the task, the more prone it is to 'hallucinations'. Amiee's example is complex.

AI struggles with complex MATH calculations. ALWAYS VERIFY.

Click to expand...

And... here we are, ONE YEAR LATER...​

WOW, AI is sooooo far ahead of the limitations it had one year ago. Back then, AI was a 6th grader. Today, AI is a masters graduate that is your personal intern.

What is you ONE YEAR FORECAST?
Main street hasn't fully embraced AI yet. At this current pace, where will AI be next year?

I have to give you massive credit here, your diagnosis of the legacy tech bloat is spot on. A 70% 'Poor' PageSpeed rating across the industry is embarrassing, and building a clean, SSR-first infrastructure with pristine schema is exactly what the industry needs to fix the crawl budget issues. I am genuinely looking forward to seeing those technical benchmarks for @DealerInt.

Where I think the architecture still hits a wall is your assumption about how non-Google models acquire data, specifically regarding retail velocity versus index churn.

You mentioned that GMC feeds and SSR schema are how Perplexity and OpenAI 'know' a car arrived. GMC is fantastic for Google's ecosystem, but Google isn't sharing that structured feed with OpenAI or Anthropic. For those models to discover inventory without an aggregator, they are entirely reliant on their own web crawlers hitting your SSR schema.

Even with a lightning fast site, standard web crawling is fundamentally incompatible with automotive retail velocity. While an average unit might sit for 30 to 60 days, the highly desirable, aggressively priced inventory....the exact cars users are actively querying AI for, often move in a matter of days. If a foundational model's crawler only indexes a specific VDP once a week, the AI is going to confidently send shoppers to 404 pages and sold vehicles. Models cannot tolerate that level of hallucination risk.

The 'Aggregator Tax' isn't just a visibility tax; it's a data-licensing reality. Foundational models are striking massive enterprise data deals with centralized hubs precisely because they need a real-time API firehose, not because they want to rely on crawling decentralized local domains, no matter how fast or clean your pipe is.

I completely agree that your infrastructure will absolutely crush legacy platforms on standard Google crawlability. But until OpenAI decides to trust and query thousands of decentralized MCP endpoints instead of buying a clean, normalized data feed from a centralized network, the aggregators still hold the keys to the non-Google LLM intelligence layers.

DealerInt said:

Joe, you’re right on discovery, but you’re describing the Aggregator Tax model. Global discovery and local execution are two different steps.

Perplexity, OpenAI, and Anthropic already handle global discovery (Top-of-Funnel) through their own web-scale indexes. They don't need to ping 18,000 dealers; they just need a direct handshake with the 5–10 local results that actually matter to the user.

That’s why Bright Data, Arcade.dev (WebMCP), and Hrizn are so critical—they provide the "Bottom-of-Funnel" execution layer.

Discovery tells an agent where a car might be; MCP proves it is there and lets them act. I’d rather give the "keys to the data" back to the dealer via the new W3C WebMCP standard than keep them locked in a centralized hub. Are we building for the aggregators, or for the dealers?

Click to expand...

I’m genuinely glad to see Horizon having success. Frankly, we're essentially the only two players in auto actually helping dealers solve this new AI/SEO visibility problem right now. We just go about it differently, and there’s absolutely nothing wrong with that. We both want to kill the Aggregator Tax.

But architecturally, your premise has a massive Catch-22.

You mentioned in your first post that legacy platforms are blocking non-standard bots. If Perplexity and Anthropic are blocked from crawling, how do their "web-scale indexes" magically know a red SUV arrived yesterday to put that dealer in the top 5 results?

They don't. They rely on search APIs, which rely on centralized, structured feeds. If a dealer skips the central hub and relies purely on AI bots bypassing legacy blocks to crawl their site, they’ll be invisible.

WebMCP is an incredibly exciting future for bottom-of-funnel execution, but let’s be real, it’s still highly experimental. Consumer AI agents aren't natively configured today to wander onto a local site, read an llms.txt, ingest a manifest on the fly, and autonomously execute tool calls.

We can't sell dealers on bypassing centralized discovery today just because WebMCP is the future. An elegant MCP manifest doesn't matter if the AI never knocks on the door because it didn't know the car was there to begin with. Global discovery first, local execution second.

I’d love to connect and see exactly how you guys have engineered around this discovery hurdle in the wild, or let me know if you’re planning on dropping a white paper detailing your approach!

DealerInt said:

You're 100% right that a static llms.txt is the wrong bucket for a 500-unit live feed. My point was more about using the llms.txt as the map rather than the pipe.

In a perfect setup, the llms.txt file points the agent to a dynamic discovery endpoint or an MCP manifest. That way, when an agent hits the site, it knows exactly where the 'live' documentation and toolsets live without having to guess via a standard crawl.

As for the Google documentation—there isn't an 'official' Google stamp on WebMCP for local inventory yet. It’s still very much in the proposal/early preview stage (as Ryan mentioned earlier). The reason it's exciting isn't because it replaces Merchant Center today, but because it offers a path for 'in-browser' agents to interact with a dealer's data directly, potentially bypassing the delays and 'data taxes' often imposed by the big listing aggregators and legacy website providers.

We’re essentially talking about the difference between Google indexing a feed and an AI Agent executing a search on the dealer's behalf. It’s a nuances shift, but a big one.

Click to expand...

You're talking about bottom-of-funnel execution, but you're completely skipping top-of-funnel discovery. An in-browser agent isn't going to sequentially ping 18,000 individual dealer WebMCP endpoints to find a red SUV; the latency would be absurd. It’s going to ping a centralized, normalized third-party data hub. You can build the most elegant MCP manifest in the world, but if the agent doesn't already know your specific dealership holds the inventory via the primary search index or a major aggregator, it’s never going to show up to read your llms.txt map in the first place.

How exactly are you planning to pass a live, 500-vehicle inventory feed with real-time pricing updates through a static llm.txt file, and can you point to any documentation where Google states they use WebMCP to index local inventory for AI Overviews rather than standard Merchant feeds?

DealerInt said:

While building out some new features for my own dealer SaaS project recently, I’ve run into exactly what Matt mentioned: legacy platforms stripping rich schema and blocking agents that aren't 'standard' Google bots. It’s a massive barrier for dealers who actually want to be 'the quotable source.'

To Gregg’s point about a 'testing ground'—I’d be interested in sharing some of the raw data I’m seeing regarding how AI engines are actually consuming (or failing to consume) different types of dealership inventory feeds. If we’re moving toward a conversational paradigm where a shopper asks, 'Find me a red SUV with 3rd row seating under $35k,' the dealer who wins isn't the one with the best blog—it's the one whose data isn't being throttled by their own provider.

Has anyone else here tried to force-inject a custom LLM.txt or WebMCP toolset onto a legacy dealer site yet, or are most of you just waiting for the providers to catch up?"

Click to expand...

Greg_Gifford said:

Hey moderators (@Jeff Kershner @Alex Snyder) - that post from aellycarter from Saturday is total spam - they edited the LandingGarage quoted post to insert a link to "botox in Queens" - probably ought to get that deleted...

Click to expand...

Thanks Greg - that one has been completely zapped and banned.

The SEO narrative in automotive has gotten detached from reality. There are only 2 providers actually solving this problem....OneKeel and Horizon. We both do it differently but....there is only two that actually know what we are doing and aren't making up how to solve for this.

There’s a growing trend of oversimplifying the problem, positioning simple automation and dashboards as if they solve systemic visibility challenges. They don’t.

Modern search isn’t a content posting problem. It’s an infrastructure problem.

If you’re not operating with a full-stack content engine, one that includes:

• programmatic content generation at scale
• originality and de-duplication controls (not recycled LLM output)
• a unified intelligence layer informed by real dealership data
• integrated RAG pipelines for contextual accuracy
• continuous learning loops tied to performance signals
• and orchestration across all channels and endpoints

…then you’re not solving SEO. You’re just producing more noise, and content that does nothing to move the needle.

Schema alone isn’t a strategy.
Dealer-written content isn’t scalable.
Social posts don’t move organic search in any meaningful way.

Without a connected system that aligns data, content, and distribution in real time, results will be inconsistent at best, and misleading at worst.

The industry needs to stop pretending otherwise.

I'll be interested to see how this plays out.

ryan.leslie said:

There is just no way that an LLM is going to be able to produce posts about purple ties and Jorts as well as we humans do.

Click to expand...

Geez... I had forgotten about the Purple Tie. My sister's wedding... she's been divorced a long time now... hope it wasn't the tie

I was passing through BTV airport a year or so ago, and the guy in front of me was wearing jorts... I snapped a quick pick and texted Alex: the classic's never die. Nothing wrong with a nice pair of denim shorts.

(At least I never wore crocs)

EVERYONE NEEDS TO KNOW AI = Automotive Intelligence.

AI powered Car Shopping assistants will be all over your inventory. Your VDP has never been more important.

Equipment Analysis: The Huebner unit is loaded. Carvana's Onyx listings at similar mileage are priced $2,490 to$5,490 higher for fewer miles.

The equipment gap is real and the price gap is meaningful.

VALUE SUMMARY Huebner's $33,100 price on this 37k-mile Onyx Edition represents the strongest documented valuein the current market.

Now we just need to send a list of ALL of our VDP's to Claude Cowork to analyze with this prompt while we sleep, so we can wake up and fix any issues quicker! This was only the 1st and only vehicle I picked, and sure it seemed to do fine, but I can guarantee you I'd find plenty of others that need to be improved content wise.

Big finding is we need to make our UX / UI much easier for customers on mobile, and unfortunately for most franchise sites, that's hard to do with the vendors we are able to use.

jscole86 said:

The big finding: Huebner has a genuinely strong vehicle at a genuinely strong price — $2,490 below the closest Carvana Onyx Edition — but the mobile SRP is bleeding shoppers before they ever see that deal. Carvana wins the "find the car" test handily because their filter flow is built for a thumb, not a cursor.

Click to expand...

Hey Josh, this is pretty bad ass! DISC? Hell Yea!

DR Forum peeps, @jscole86 and I have been swaping best practices for a decade. Josh and the team at Huebner execute at a level that few get to. Wayyy back in the day, back in the Uncle Joe Diary 1.0 days, Josh and I built the most bad ass comment generators using php and tags and car guy logic.

much respect!

p.s. Josh, Let me know what mods you'd like (or your making

Used 2024 Subaru Ascent Onyx Edition For Sale in Carrollton, OH | #72852
2024 Subaru Ascent Onyx Edition - 37336 miles


Fetched: 2024 Subaru Ascent Onyx Edition

Fetched: 2024 Subaru Ascent Onyx Edition

Phase 2 — INVENTORY GATE: ✅ PASS
Real listing confirmed:

• VIN: 4S4WMAHDXR3405043
• Stock: #72852
• Price: $33,100
• Mileage: 37,336
• Trim: 2024 Subaru Ascent Onyx Edition, Magnetite Gray Metallic

Now fetching the Carvana comparison listing.
Searched the web

Searched the web

Good — I have enough confirmed Carvana data from search results to use as the closest comparable. The best Carvana match for a 2024 Ascent Onyx Edition nearest to 37k miles is the 29k-mile unit at $35,590 (from search result index 4). Now building the full audit.
Reading frontend design skill

Reading frontend design skill

Now I have everything I need. Building the full HTML audit file.
Created a file, read a file

Created a file, read a file

The audit is ready. Save the file as audit.html and open it in any browser.
Here's what the audit found at a glance:
Phase 2 — PASS. Real inventory confirmed: VIN 4S4WMAHDXR3405043, $33,100, 37,336 miles, Stock #72852.
The big finding: Huebner has a genuinely strong vehicle at a genuinely strong price — $2,490 below the closest Carvana Onyx Edition — but the mobile SRP is bleeding shoppers before they ever see that deal. Carvana wins the "find the car" test handily because their filter flow is built for a thumb, not a cursor.
Overall scores: Carvana 8/10 — Huebner 7/10. Not a blowout, but driven entirely by SRP friction. The VDP content at Huebner actually edges Carvana out because the listing is better documented.
The one move to make today: Stop sending buyers to the SRP. Every text, email, and social post should link directly to the VDP URL. One tap, straight to 43 photos and the full story. That alone eliminates the biggest friction point without touching the website.

DjSec said:

You quoted my post and dropped a link to a casino, now that was some pretty good spamming ... never seen that before.

Click to expand...

Good catch. They have been banned and cleaned.

AI Shopping Test: https://www.drivemb.com/
2022 Mercedes-Benz GLC 300 4MATIC® SUV under 35000 miles

╔══════════════════════════════════════════════════════════╗
║ 911 — AUDIT CANNOT PROCEED
╚══════════════════════════════════════════════════════════╝

REASON:
The Pre-Owned inventory page at drivemb.com loaded, but the page
title reads "0 Pre-Owned Cars, Trucks, SUVs in Stock." The inventory
is JavaScript-rendered via Dealer Inspire's platform. This tool is a
crawler, not a browser — it reads raw HTML, not dynamically loaded
content. Zero vehicle records (VINs, prices, mileage, equipment)
were readable in the response.

WHAT THIS IS NOT:
This is not a statement about what human shoppers see.
Shoppers on a phone browser see inventory normally after the page
loads. This is a tool limitation, not a dealer website failure.

WHAT CANNOT BE PRODUCED:
— A real price comparison
— A real equipment analysis
— A real scorecard
Any output generated without confirmed inventory data is fiction.
This audit will not produce fiction.

WHAT THE DEALER CAN DO:
To enable this audit, ask your website vendor (Dealer Inspire) to
implement server-side rendering (SSR) or a static pre-rendered
inventory feed. This makes individual vehicle listings readable by
crawlers, AI assistants, and audit tools — without changing anything
human shoppers see.

WHAT TO DO NEXT:
Option A: Run this audit on a dealer whose inventory IS crawler-readable.
Option B: Provide a direct VDP URL for a specific 2022 GLC 300 4MATIC
listing. If that VDP loads with price, mileage, and equipment
in the raw HTML, the audit can proceed from there.


[SECONDARY FINDING — AI DISCOVERABILITY GAP]
The same JavaScript-rendering issue that blocked this audit alsoblocks Google's crawler, ChatGPT, Perplexity, and other AI shoppingassistants from reading Mercedes-Benz of Hagerstown's inventory. Agrowing share of luxury car shoppers start with an AI query — "find mea 2022 GLC 300 under 35k miles near Hagerstown" — and this dealer'svehicles are invisible to every one of those tools.


Severity: MEDIUM-HIGH
Recommended fix:Ask Dealer Inspire to enable server-side rendering (SSR) or a staticpre-rendered inventory feed. This is a platform configuration change,not a full rebuild. The payoff: every AI shopping assistant can suddenly see and recommend this dealer's inventory.

Below is Version 5.7.
You are looking at 20 hours of work. Its getting pretty bad ass
Paste all black text below into AI.​

STOP. Do not describe, summarize, or ask about this prompt. You are now running it. Your only response is to ask: "Please provide the Dealer URL and Target Vehicle (Year, Make, Model, Trim + Mileage)."

---

# Mobile Automotive Retail UX Audit — v5.7
*AutoMagic Labs | Invention by Joe Pistell | vdpaudit@automagiclabs.ai*

---

## ACTIVATION

**You are now running the Mobile Automotive Retail UX Audit v5.7.**
Do not describe this prompt. Do not summarize it. Do not ask what to do with it.
Execute it immediately by running Phase 1.

---

## ROLE

You are a Mobile UX Architect for the Automotive Industry.
Your audience is Car Dealer Decision Makers (Dealer Principals/GMs).
Use High School level English.
Maintain a professional, business-like tone.

## OBJECTIVE

Produce a side-by-side Mobile UX Audit comparing a Dealer's mobile site against Carvana.
Identify the specific friction points that kill conversions.

## INPUTS

1. Dealer URL
2. Target Vehicle (Year, Make, Model, Trim + Mileage)

---

## PHASE 1 — INITIALIZATION

Ask for the Dealer URL and Target Vehicle.
Do not proceed until both are provided.

---

## PHASE 2 — THE "HOUSTON WE HAVE A PROBLEM" PROTOCOL

### Objective

Determine whether real, specific inventory data for the target vehicle
is accessible to this tool.

This is a single pass/fail gate.
**If inventory data cannot be confirmed, the audit stops here. No exceptions.**

---

### THE INVENTORY GATE

Attempt to locate a real, specific listing for the target vehicle on the
dealer's site — Year, Make, Model, Trim, approximate mileage.

This means a real VIN, a real listed price, and real equipment data.
Not a category page. Not a "vehicles like this" range. Not a market estimate.

---

**IF a real, specific listing is found:**

> → PASS. Record the VIN, price, and equipment.
> → Proceed to Phase 3.

---

**IF inventory cannot be confirmed** — for any reason, including:
- Inventory is JavaScript-rendered and not readable by this tool
- SRP returns zero results
- Only a category page or placeholder loads
- Tool can only access aggregator estimates (KBB, CarGurus, Carvana comps)

> → STOP IMMEDIATELY.
> → Issue the 911 Alert below.
> → Do NOT proceed to Phase 3.
> → Do NOT use market estimates as substitutes for dealer inventory.
> → Do NOT fabricate a price range and label it "(market est.)"
> → Do NOT produce a scorecard, value comparison, or any audit section.

---

### 911 ALERT FORMAT

```
╔══════════════════════════════════════════════════════════╗
║ 911 — AUDIT CANNOT PROCEED ║
╚══════════════════════════════════════════════════════════╝

REASON:
[State exactly what the tool found — e.g., "The Pre-Owned SRP at
[dealer URL] loaded but inventory is JavaScript-rendered. This tool
is a crawler, not a browser. Zero vehicle records were readable."]

WHAT THIS IS NOT:
This is not a statement about what human shoppers see.
Shoppers on a phone browser see inventory normally after the
page loads. This is a tool limitation, not a dealer website failure.

WHAT CANNOT BE PRODUCED:
— A real price comparison
— A real equipment analysis
— A real scorecard
Any output generated without confirmed inventory data is fiction.
This audit will not produce fiction.

WHAT THE DEALER CAN DO:
To enable this audit, ask your website vendor to implement
server-side rendering (SSR) or a static pre-rendered inventory
feed. This makes individual vehicle listings readable by crawlers,
AI assistants, and audit tools — without changing anything
human shoppers see.

WHAT TO DO NEXT:
Option A: Run this audit on a dealer whose inventory IS crawler-readable.
Option B: Provide a direct VDP URL for the target vehicle.
If a specific VDP URL loads with price, mileage, and
equipment in the raw HTML, the audit can proceed from there.
```

---

### SECONDARY FINDING — AI DISCOVERABILITY GAP

If the 911 Alert fires, append this finding once:

```
[SECONDARY FINDING — AI DISCOVERABILITY GAP]

The same JavaScript-rendering issue that blocked this audit also
blocks Google's crawler, ChatGPT, Perplexity, and other AI shopping
assistants from reading this dealer's inventory. A growing share of
car shoppers start with an AI query. Invisible inventory = zero AI
referrals.

Severity: MEDIUM-HIGH

Recommended fix:
Ask your website vendor to implement server-side rendering (SSR)
or a static pre-rendered inventory feed. This is a platform
configuration change, not a full rebuild.
```

---

### WHAT PHASE 2 IS NOT

Phase 2 is not a UX test.
Phase 2 is not a bot-vs-human comparison.
Phase 2 is one question: **Do we have real data to work with?**
If yes → build the audit.
If no → stop, explain why, show the path forward.

---

## PHASE 3 — THE EXECUTIVE ARTIFACT

If Phase 2 passes, output the complete audit as a single HTML file
inside a fenced code block (```html ... ```).

The user will copy the code block, paste it into a blank text file,
save it as audit.html, and open it in any browser.

Do not output markdown. Do not output plain text.
Output only the HTML code block — nothing before it, nothing after it
except the closing fence.

---

### HTML OUTPUT REQUIREMENTS

The HTML file must:

1. Be fully self-contained — no external stylesheets, no external fonts,
no images. Everything inline.

2. Use this color palette:
- Header background: #1E5C6B (AML teal)
- Header text: #FFFFFF
- Section title bars: #1E5C6B text on #EAF4F6 background
- Winner badges: white text on #1E5C6B background, pill shape
- Table header rows: #1E5C6B background, white text
- Alternating table rows: #F7FBFC and #FFFFFF
- Body text: #1A1A1A on #FFFFFF page background
- Accent / callout boxes: #EAF4F6 background, #0D3D47 border-left 4px
- Footer: #1E5C6B background, white text

3. Use these fonts (system stack, no imports):
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Arial, sans-serif

4. Include these sections in order:

HEADER
- Large title: MOBILE AUTOMOTIVE RETAIL UX AUDIT — v5.7
- Subtitle: [DEALER NAME] vs. CARVANA
- Target Vehicle and Date on one line
- AML tagline: "Invention by Joe Pistell | vdpaudit@automagiclabs.ai"

SECTION 1 — THE BOTTOM LINE: VALUE COMPARISON
- Side-by-side comparison table with columns:
Feature | [DEALER NAME] | CARVANA | WINNER
- Rows: Price, Mileage, Equipment, The Promise, Transparency
- WINNER column shows a teal pill badge with the winner's name
- Below table: Equipment Analysis paragraph (bold label, normal text)
- Below that: Value Summary paragraph in a callout box

SECTION 2 — AUDIT SCORECARD
- Scorecard table: Test | Dealer Score | Carvana Score | Winner
- Rows: Test 1 Narrowing (SRP), Test 2 Trust (VDP), OVERALL MOBILE SCORE
- Overall row is bold, teal background, white text
- Scoring note below table in italic

SECTION 3 — TEST 1: FINDING THE CAR (THE "TAP" TEST)
- Bold dealer name label, then finding paragraph
- Bold CARVANA label, then finding paragraph
- THE GAP: in a teal callout box

SECTION 4 — TEST 2: BUILDING TRUST (THE "TRUTH" TEST)
- Same structure as Section 3

SECTION 5 — ARCHITECT'S RECOVERY SUMMARY
- Primary conversion killer: bold label + finding
- NEXT MOVE: large callout box, teal border, bold heading,
one specific action the dealer can take today

FOOTER
- "Invention by Joe Pistell."
- "For a one-on-one deep dive and a custom merchandising strategy,"
- "contact the founder at vdpaudit@automagiclabs.ai"
- Footer background: #1E5C6B, white text, centered

5. Typography rules:
- Page title: 28px bold
- Section titles: 18px bold, all caps
- Body text: 15px, line-height 1.7
- Table text: 14px
- Bold labels: font-weight 700
- Italic notes: font-style italic, color #555
- Max page width: 860px, centered, padding 40px

6. Mobile responsive:
- Single column below 600px
- Tables scroll horizontally on small screens
- Wrap in: overflow-x: auto on table containers

---

## CONSTRAINTS

- Lead with the conclusion in every section.
- Use ONLY High School level English. No "Architect-speak."
- No mentions of 360-spinners or expensive hardware.
- Focus on transparency and "thumb-room."
- Use active verbs. Cut filler words.
- Never conflate bot/crawler limitations with human mobile UX.
- Never imply human shoppers see a blank page when the only issue is machine crawler access.
- Never fabricate prices, mileage, or equipment. If data is not confirmed, the 911 Alert fires and the audit stops.
- Market comparables are NOT a substitute for confirmed dealer inventory. No exceptions.

@craigh in my circles ppl have not connected AI to 'getting shit done'.

I had a 40yr old that wanted instructions on how to figure out what was wrong with their home theater (I use to own a HT company). I told her "do you have GPT?" Of course she did, I walked her thru the steps of talking to it " tell it only what you know, nothing more, and GPT will walk you thru this" She had the app, and the idea never crossed her mind lol!

I'm thinking in the early days of AI will be like in the early Internet days. The AI shopper will be a different breed and we'll need a special pay lan for that traffic (just like the internet did back when)