scanned Jun 11, 2026

Kepler

trykepler.ai

Kepler helps e-commerce sites understand and monetize AI-driven traffic by providing an intelligence layer that bridges digital and agentic funnels

42/100

Tier 3 · Agent-Accessible

Content answers39/100

Protocol plumbing50/1008 of 16 checks pass

Re-audit2152h ago· 1 credit

Scored by asking 15 questions a buyer of a ai-ml product asks, then grading this site’s own pages: answered, hedged (partial or vague), or silent (no page answers it). How scoring works

15 buyer questions · graded against the site’s own pages

0 of 15 come back answered. 9 get a hedge. 6 meet silence.

0 answerable9 half-answers6 silent

Goes silent · pricing · high importance

What happens if my store has a viral month and I blow past my plan's pageview limit—do you bill me for overages at a per-1,000 rate, or do you automatically bump me to the next tier?

Goes silent · pricing · high importance

I'm running a mid-size Shopify store doing about 50k sessions a month. Does Kepler's entry-level plan cover that traffic volume, or would I need to jump to the Growth tier?

This report is public. Own trykepler.ai? Claiming is free: crawl every page, re-audit as you fix, and track your score over time.

The fix queue

58 points sit between trykepler.ai and 100: 15 open questions and 8 missing protocol checks, ordered by estimated payoff.

Point estimates are per fix under scoring v2. They are not additive to a promised total.

01pricing · importance highGoes silent+7 content pts est.

What happens if my store has a viral month and I blow past my plan's pageview limit—do you bill me for overages at a per-1,000 rate, or do you automatically bump me to the next tier?

What the pages say

No page on the site addresses this.

The fix

Add a dedicated pricing page that explains plan limits, overage policies, and whether exceeding pageview limits triggers automatic tier upgrades or per-1,000 overage fees.

confidence high · grounding world-knowledge · weight 0.00 · Absent

02pricing · importance highGoes silent+7 content pts est.

I'm running a mid-size Shopify store doing about 50k sessions a month. Does Kepler's entry-level plan cover that traffic volume, or would I need to jump to the Growth tier?

What the pages say

The retrieved website content does not include any information about Kepler pricing plans, plan tiers (such as an entry-level plan or Growth tier), or traffic/session volume limits. All retrieved chunks consist of marketing pages and a blog post describing product features and benefits.

The fix

Create a dedicated pricing page that clearly outlines plan tiers, session or traffic limits, and which plan fits different store sizes (e.g., ~50k monthly sessions).

Where we looked: www.trykepler.ai, www.trykepler.ai, /blog/meet-kepler

confidence high · grounding world-knowledge · weight 0.00 · Page missing

03legal · importance mediumGoes silent+7 content pts est.

I run a small e-commerce agency managing five Shopify brands. Under your Terms of Service, can I use a single Kepler account across all five client stores, or does each merchant need their own paid seat?

What the pages say

No page on the site addresses this.

The fix

Publish the Terms of Service and add a section or FAQ that explicitly addresses whether agencies or multi-brand operators may use a single Kepler account across multiple client stores, or if each merchant requires a separate paid seat.

Where we looked: /blog/meet-kepler, /blog/unlocking-agentic-commerce

confidence high · grounding synthesized · weight 0.00 · Absent

04security · importance mediumGoes silent+7 content pts est.

If I cancel my Kepler subscription, how long do you keep my store's historical analytics and Agent Score data before it's permanently deleted?

What the pages say

No page on the site addresses this.

The fix

Add a data retention and deletion policy to the privacy policy or terms of service that specifies how long historical analytics and Agent Score data are retained after a customer cancels their subscription.

Where we looked: /legal/privacy-policy, /legal/privacy-policy, /old/legal-old

confidence high · grounding synthesized · weight 0.00 · Absent

05limits · importance lowGoes silent+7 content pts est.

I want to pipe my daily Agent Score and traffic data into our internal Looker dashboard. What is the API rate limit for pulling that aggregate data, and is it available on all plans or just Enterprise?

What the pages say

No page on the site addresses this.

The fix

Publish API documentation or a developer portal that specifies rate limits for aggregate data endpoints, and add a pricing/plans page clarifying which features are available on each tier.

Where we looked: www.trykepler.ai, /agent-score, /blog/meet-kepler, /blog/unlocking-agentic-commerce

confidence high · grounding world-knowledge · weight 0.00 · Absent

06technical · importance lowGoes silent+7 content pts est.

Our product descriptions are loaded dynamically via JavaScript after the initial page load. Does your 'Evaluate Your Site' crawler render JavaScript when calculating the Agent Score, or will it miss that content?

What the pages say

No page on the site addresses this.

The fix

Add a technical methodology or FAQ section to the Agent Score / Evaluate Your Site page explaining whether the crawler renders JavaScript and how it handles dynamically loaded content.

Where we looked: /agent-score, /evaluate-your-site

confidence high · grounding synthesized · weight 0.00 · Absent

Hedged · 9 of 15 questions

A buyer gets something, then has to guess the rest. Expand any row for the evidence and the fix.

07We rebuilt our storefront as a headless Next.js app using Shopify Hydrogen. Does Kepler provide a JavaScript SDK or API that works with headless architectures, or is it only a standard Shopify app?integrationHedges+3 pts est.

We rebuilt our storefront as a headless Next.js app using Shopify Hydrogen. Does Kepler provide a JavaScript SDK or API that works with headless architectures, or is it only a standard Shopify app?

What the pages say

The retrieved chunks do not specify whether Kepler provides a JavaScript SDK or API for headless architectures such as Next.js and Shopify Hydrogen, nor do they state that Kepler is only a standard Shopify app. The homepage states that Kepler "connects easily to your current stack" and "runs alongside your existing site" without engineering lift, but it does not detail the integration mechanism. A "ChatGPT Apps SDK" is listed as "Coming Soon," though this appears unrelated to headless storefront integration.

The fix

Publish a technical integrations or developers page that explicitly states whether Kepler offers a JavaScript SDK, REST API, or Shopify app, and clarify support for headless architectures like Next.js and Shopify Hydrogen. Also expand the FAQ answer for 'How does Kepler connect to my current e-commerce stack?' to include these specifics.

Where we looked: www.trykepler.ai, www.trykepler.ai, /blog/meet-kepler

confidence low · grounding synthesized · weight 0.55 · Vague

08Does adding Kepler to my site require swapping out my existing Google Tag Manager setup, or do I just drop an async JavaScript snippet in the head and keep everything else as-is?technicalCollapsed+3 pts est.

Does adding Kepler to my site require swapping out my existing Google Tag Manager setup, or do I just drop an async JavaScript snippet in the head and keep everything else as-is?

What the pages say

The retrieved chunks do not specifically mention Google Tag Manager or an async JavaScript snippet installation method. The site states that Kepler ‘runs alongside your existing site’ and ‘connects easily to your current stack, upgrading intelligence without engineering lift,’ but the exact integration mechanism is not detailed in the captured content. The homepage includes FAQ questions such as ‘How does Kepler connect to my current e-commerce stack?’ and ‘What is required to get started?’, yet their answers were not retrieved.

The fix

Ensure the FAQ accordion or collapsible sections on the homepage (e.g., under ‘Answers to your questions’) are expanded for crawlers so that answers to integration questions like ‘How does Kepler connect to my current e-commerce stack?’ are captured.

Where we looked: www.trykepler.ai, www.trykepler.ai, www.trykepler.ai

confidence low · grounding synthesized · weight 0.55 · Collapsed

09My revenue depends on your script loading correctly. Do you publish an uptime SLA for the Kepler tag delivery, and what service credit do I get if availability drops below that threshold?operationsHedges+2 pts est.

My revenue depends on your script loading correctly. Do you publish an uptime SLA for the Kepler tag delivery, and what service credit do I get if availability drops below that threshold?

What the pages say

Trykepler.ai's status page shows 100% historical uptime for Kepler from March 2026 through June 2026, but none of the retrieved chunks publish an uptime SLA specifically for tag delivery or outline service credits for availability drops.

The fix

Add a dedicated SLA page or section to the Terms of Service that specifies the uptime guarantee for tag delivery and the service credit schedule for outages.

Where we looked: status.trykepler.ai

confidence medium · grounding synthesized · weight 0.65 · Vague

11I ran my site through your Agent Score tool and got a 72. What are the exact criteria—like metadata completeness, schema markup, or something else—that make up that score so I know what to fix first?getting-startedHedges+2 pts est.

I ran my site through your Agent Score tool and got a 72. What are the exact criteria—like metadata completeness, schema markup, or something else—that make up that score so I know what to fix first?

What the pages say

The chunks show that Agent Score is based on six high-level scoring variables—Speed Score, Effort Score, Failure Rate, Total Tasks Performed, Average Task Durations, and Average Interactions—and that a 72 falls in the “Good” range (65–79). However, none of the retrieved chunks break down the exact technical criteria (such as metadata completeness, schema markup, or similar factors) that feed into those variables or how to prioritize fixes.

The fix

Add a methodology or ‘How it works’ section to the Agent Score page that details the exact technical criteria (e.g., metadata completeness, schema markup, page speed, structured data) that feed into each scoring variable so buyers know what to fix first.

Where we looked: www.trykepler.ai, /agent-score

confidence medium · grounding synthesized · weight 0.65 · Vague

12Is there a minimum Agent Score my site needs to hit before Kepler actually starts monetizing AI-driven traffic, or does the intelligence layer begin working regardless of the score?technicalHedges+2 pts est.

Is there a minimum Agent Score my site needs to hit before Kepler actually starts monetizing AI-driven traffic, or does the intelligence layer begin working regardless of the score?

What the pages say

The retrieved chunks do not state whether there is a minimum Agent Score required before Kepler begins monetizing AI-driven traffic. The site describes Agent Score as a 0-100 readiness diagnostic (with <50 Poor, 50-64 Average, 65-79 Good, and 80+ Excellent) and says Kepler acts as an intelligence layer that monetizes AI traffic and automatically enriches product data, but they do not specify a score threshold for the intelligence layer to activate.

The fix

Add a clear explanation on the Agent Score or FAQ page stating whether Kepler requires a minimum Agent Score to begin monetizing traffic, or confirm that the intelligence layer activates regardless of the initial score.

Where we looked: www.trykepler.ai, www.trykepler.ai, www.trykepler.ai

confidence high · grounding synthesized · weight 0.70 · Vague

13When I install the Kepler app from the Shopify App Store, does it request access to customer names and emails, or can I run it with only product catalog and order permissions?integrationHedges+2 pts est.

When I install the Kepler app from the Shopify App Store, does it request access to customer names and emails, or can I run it with only product catalog and order permissions?

What the pages say

The site mentions that Kepler "connects easily to your current stack, upgrading intelligence without engineering lift" and runs alongside your existing site, but it does not specify what permissions the Shopify App Store app requests—such as access to customer names and emails versus only product catalog and order permissions.

The fix

Publish a dedicated Shopify integration or App Store listing page that explicitly lists required OAuth scopes and data permissions (e.g., read_products, read_orders, read_customers) so merchants know what access is requested.

Where we looked: www.trykepler.ai, www.trykepler.ai

confidence high · grounding synthesized · weight 0.70 · Vague

14We use Shopify Markets to show localized pricing in EUR for EU visitors and USD for US visitors. Does Kepler ingest the localized prices seen by the shopper, or does it only read the store's base currency?integrationCollapsed+2 pts est.

We use Shopify Markets to show localized pricing in EUR for EU visitors and USD for US visitors. Does Kepler ingest the localized prices seen by the shopper, or does it only read the store's base currency?

What the pages say

The retrieved chunks include an FAQ question, "How does Kepler connect to my current e-commerce stack?" under "Answers to your questions," but the answer body appears collapsed or empty and was not captured. None of the retrieved chunks mention Shopify Markets, localized pricing, EUR/USD, or whether Kepler ingests localized prices versus the store's base currency.

The fix

Ensure the 'Answers to your questions' FAQ accordion is crawlable so the answer to 'How does Kepler connect to my current e-commerce stack?' is captured; add explicit documentation on Shopify Markets and multi-currency pricing ingestion.

Where we looked: www.trykepler.ai, www.trykepler.ai

confidence medium · grounding synthesized · weight 0.65 · Collapsed

15Our products rely heavily on Shopify Metafields for technical specs like wattage and compatibility. Does Kepler's AI layer index those metafields to answer shopper questions, or is it limited to the standard title, description, and tags?integrationHedges+2 pts est.

Our products rely heavily on Shopify Metafields for technical specs like wattage and compatibility. Does Kepler's AI layer index those metafields to answer shopper questions, or is it limited to the standard title, description, and tags?

What the pages say

Kepler’s homepage states that it is ‘enriching and structuring your product data’ so agents and LLMs can represent your brand, and that it ‘connects easily to your current stack’ without engineering lift. The homepage also lists an FAQ question, ‘How does Kepler connect to my current e-commerce stack?’, but the answer was not retrieved. None of the retrieved content mentions Shopify Metafields specifically, nor does it clarify whether Kepler is limited to standard fields like title, description, and tags.

The fix

Add a dedicated integrations or data-sources page that explicitly lists which Shopify fields and metafields Kepler indexes, or expand the homepage FAQ to detail platform-specific data ingestion capabilities.

Where we looked: www.trykepler.ai, www.trykepler.ai, www.trykepler.ai, www.trykepler.ai

confidence medium · grounding synthesized · weight 0.65 · Vague

Protocol plumbing · 50/1008 of 16 checks pass · each fix +6 protocol pts est.

The other half of the score: 16 checks for the files and headers agents look for. The 8 below are installs, not judgment calls, and most are an afternoon. Expand any for the snippet and the standard it follows. They sit after the queue because none of them changes what your pages say.

llms.txtDiscoverability+6 pts est.

Sitedex generates this file from your crawl. Grab it in Files from this audit below.

Standardllmstxt.orgCommunity spec

Content signalAccess+6 pts est.

Install snippet

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

StandardCloudflare proposalVendor proposal

MCP cardInteraction+6 pts est.

Sitedex generates this file from your crawl. Grab it in Files from this audit below.

StandardModel Context ProtocolCommunity spec

OpenAPI specInteraction+6 pts est.

StandardOpenAPI SpecIndustry standard

WebMCP widgetInteraction+6 pts est.

Sitedex generates this file from your crawl. Grab it in Files from this audit below.

StandardW3C WebMCP draftW3C / WHATWG

Meta descriptionsHygiene+6 pts est.

Install snippet

<meta name="description" content="trykepler.ai: [outcome you deliver] for [who you help]. One sentence, 50-160 characters." />

StandardHTML Living StandardW3C / WHATWG

Organization schemaIdentity+6 pts est.

Sitedex generates this file from your crawl. Grab it in Files from this audit below.

StandardSchema.org + JSON-LDIndustry standard

Sitemap lastmodDiscoverability+6 pts est.

Standardsitemaps.orgIndustry standard

Already passing 8 of 16: robots.txt, sitemap.xml, AI crawler access, Clean crawl, Markdown negotiation, Server-rendered content, Canonical URLs, HTML lang attribute.

Ask this site’s index

Sitedex already serves trykepler.ai as an MCP endpoint. Ask trykepler.ai anything an AI agent might ask, and see what its index returns. (To score your own site, use the form below.)

Snippets & configs

For developers and the engineer-on-call: copy these into your tools or your site.

Files from this audit

Built from this crawl. Download or copy each, then install it at the path noted.

llms.txt

Built from this crawl. Install at /llms.txt so agents start here.

organization.json

Organization JSON-LD, pre-filled from this crawl. Wrap in a ld+json script.

server-card.json

MCP server card built from this crawl. Host at /.well-known/mcp/server-card.json.

webmcp.json

WebMCP discovery manifest built from this crawl. Host at /.well-known/webmcp.json.

MCP endpoint

https://mcp.sitedex.dev/s/trykepler-ai/mcp

The URL anyone's agent points at. Read-only; safe to share.

Claude Code

claude mcp add trykepler --transport http https://mcp.sitedex.dev/s/trykepler-ai/mcp

One command, then the agent has it.

Cursor / Continue

{
  "mcpServers": {
    "trykepler": {
      "url": "https://mcp.sitedex.dev/s/trykepler-ai/mcp"
    }
  }
}

Drop into mcp.json.

WebMCP: two parts

WebMCP-capable browsers run the widget at runtime. Crawlers without JS rendering need the discovery manifest to find your tool surface. Install both.

1 · Widget script

<script async src="https://sitedex.dev/widget.js"></script>

Drop in <head>. WebMCP-capable browsers (Chrome 146+ Origin Trial) call navigator.modelContext.provideContext() via this script.

2 · Discovery manifest

{
  "$schema": "https://wellknownmcp.org/schemas/webmcp.json",
  "name": "trykepler.ai",
  "tools": [
    { "name": "search", "description": "Search trykepler.ai's indexed content." },
    { "name": "get_page", "description": "Fetch a page from trykepler.ai as markdown." }
  ]
}

Host alongside the script at /.well-known/webmcp.json. Crawlers that don't render JS rely on this.

Your turn

See which of these questions your site goes silent on.

Free, about 5 minutes. We crawl your site, test it against the buyer questions your category asks, and name what’s vague, contradictory, or missing, plus the files AI agents look for.

ComingEmbeddable grade badgeScore history and deltasOpt-in public board