wapiso.com — llms.txt & GEO score

WAPI

Enterprise technology company (wapiso.com) building AI, automation and messaging products for businesses. Flagship product: Caretta Assistant, an AI customer representative that learns your website and answers visitors 24/7 on web chat and WhatsApp, with an optional Sales Mode. Site content is available in English, Turkish and German.

4 of 11 checks pass. What is left: every link carries a description, descriptions say something concrete, descriptions add to the title, points at clean markdown copies, link titles are descriptive, list items are markdown links and enough written detail per link.

• Every link carries a description 14 of 18 described (78%)
  8/10
• Descriptions say something concrete Average 35 characters across 14 described links
  3/7
• Descriptions add to the title 1 description just repeat the link title
  3/4
• Points at clean markdown copies 1 of 18 end in .md or .txt (6%, detected by file extension)
  1/10
• Link titles are descriptive 4 weak titles (bare URLs, “here”, one-word labels)
  1/4
• A workable number of links 18 links (12–50 is the sweet spot)
  4/4
• Skippable links marked Optional An ## Optional section is present
  3/3
• No duplicate links All 18 URLs are distinct
  2/2
• List items are markdown links 3 of 21 list items are plain text, not links
  3/4
• Enough written detail per link 15 words per link across 269 words
  1/3
• Links are absolute URLs All 18 links are absolute URLs
  1/1

All 7 checks pass in this group.

• Exactly one H1 project title “WAPI”
  3/3
• Summary directly under the title Present as a blockquote
  3/3
• Summary is a usable length 336 characters
  3/3
• Concrete language, not marketing filler No marketing filler detected
  3/3
• Grouped into balanced sections 5 H2 sections, largest group holds 7 of 18 links
  4/4
• Conforms to the published grammar Markdown only, headings used as the spec defines them
  2/2
• Section names say what is inside All 5 headings are descriptive
  2/2

3 of 5 checks pass. What is left: robots.txt exists and robots.txt points at a sitemap.

• At the root of the domain you typed Found at the standard /llms.txt path
  2/2
• Sent as plain text Content-Type: text/plain; charset=utf-8
  1/1
• robots.txt exists No robots.txt
  0/1
• AI crawlers are not blocked No robots.txt exists, so nothing blocks them — but nothing invites them either
  6/6
• robots.txt points at a sitemap No Sitemap: line
  0/1

5 of 6 checks pass. What is left: title is not padded or repetitive.

• Homepage title is the right length 45 characters, from title
  2/2
• Title is not padded or repetitive “wapi” appears twice — brand padding that spends visible characters
  0/1
• Homepage has a meta description 150 characters, from meta description
  2/2
• Canonical URL declared https://wapiso.com
  1/1
• Language declared lang="en"
  1/1
• Social card image og:image is set
  1/1

All 5 checks pass in this group.

• Publishes llms-full.txt Companion full-text file found
  3/3
• The index points at the full file llms.txt links to llms-full.txt
  1/1
• Index is a sensible size 3.2 KB
  2/2
• Server reports when it last changed Server sends Last-Modified
  1/1
• The index is kept current Last changed 17 days ago
  2/2

• Points at clean markdown copies Content & links +9

  Right now: 1 of 18 end in .md or .txt (6%, detected by file extension)

  Publish a .md version of each page and link to that. The single biggest win here: the model reads your content instead of your navigation and footer.

  Where: Your CMS or docs build — this is the biggest single win here

  1. Publish a .md version of each page you link to, at a predictable URL (page.md next to page).
  2. Point the llms.txt links at the .md copies, not at the HTML pages.
  3. Strip navigation, cookie banners and footers from the markdown — that is the whole point: the model reads your content instead of your chrome.
  4. Declare the pair in your HTML with a link relation so clients can find it without guessing.

  In your file

  line 9

  - [Caretta Assistant](https://wapiso.com/caretta-assistant): AI customer rep and sales assistant trained on your own website

  - [Caretta Assistant](https://wapiso.com/caretta-assistant.md): AI customer rep and sales assistant trained on your own website

  line 10

  - [AI Solutions](https://wapiso.com/ai-solutions): AI integration for businesses

  - [AI Solutions](https://wapiso.com/ai-solutions.md): AI integration for businesses

  line 11

  - [Services](https://wapiso.com/services): enterprise technology services

  - [Services](https://wapiso.com/services.md): enterprise technology services

  Placeholders in { } are yours to write — we do not invent text about your pages.

• Descriptions say something concrete Content & links +4

  Right now: Average 35 characters across 14 described links

  Write 60+ characters that add information the title does not: numbers, limits, formats, names.

  Where: The text after ": " on each link

  1. Write 60 characters or more, and make them add information the title does not.
  2. Cover every link: this is measured per LINK, not per description, so an undescribed line counts as zero.
  3. Name the concrete things on the page: numbers, limits, formats, model names.
  4. If the description could be pasted under any other link, it is not a description yet.

  In your file

  line 10

  - [AI Solutions](https://wapiso.com/ai-solutions): AI integration for businesses

  - [AI Solutions](https: {what is on the page — numbers, limits, formats}

  line 11

  - [Services](https://wapiso.com/services): enterprise technology services

  - [Services](https: {what is on the page — numbers, limits, formats}

  line 13

  - [Help Center](https://wapiso.com/help-center): support articles

  - [Help Center](https: {what is on the page — numbers, limits, formats}

  Placeholders in { } are yours to write — we do not invent text about your pages.

• Link titles are descriptive Content & links +3

  Right now: 4 weak titles (bare URLs, “here”, one-word labels)

  Replace bare URLs and “click here” with the page’s real name — the title is half the signal.

  Where: The "[Title]" part of each link

  1. Replace bare URLs, "here", "click here" and one-word labels with the page’s real name.
  2. The title is half the signal — a model reads it before it reads your description.

  In your file

  line 14

  - [Blog](https://wapiso.com/blog): articles in English, Turkish and German

  - [{the page’s real name}](https://wapiso.com/blog): articles in English, Turkish and German

  line 15

  - [Contact](https://wapiso.com/contact): sales and support

  - [{the page’s real name}](https://wapiso.com/contact): sales and support

  line 20

  - [Wix app](https://www.wix.com/app-market/821c74bf-8af6-4612-9342-b27db2c5ce44?referral=unlisted-app-821c74bf-8af6-4612-9342-b27db2c5ce44): Wix App Market

  - [{the page’s real name}](https://www.wix.com/app-market/821c74bf-8af6-4612-9342-b27db2c5ce44?referral=unlisted-app-821c74bf-8af6-4612-9342-b27db2c5ce44): Wix App Market

  Placeholders in { } are yours to write — we do not invent text about your pages.

• Enough written detail per link Content & links +2

  Right now: 15 words per link across 269 words

  A list of names is not documentation. Aim for 30+ words per link across the file — summary, section context and descriptions together. For an exhaustive map what matters instead is that the list is grouped so a model can skip whole branches.

  Where: The descriptions and section context in llms.txt

  1. Count the words in your file against the number of links — aim for 30 or more per link.
  2. A list of page names is an index, not documentation; the descriptions are what a model actually reads.
  3. Add a line of context under each "## " heading saying what that group covers.
• Every link carries a description Content & links +2

  Right now: 14 of 18 described (78%)

  Add ": " and one short line after every link. An undescribed link is a coin flip — the model has to open it to find out what it is.

  Where: Each "- [Title](url)" line

  1. Add ": " and one short line after every link — not most of them, every one.
  2. Describe what the page answers, not what it is called.
  3. An undescribed link is a coin flip: the model has to open it to find out.

  In your file

  line 38

  - [Full context file](https://wapiso.com/llms-full.txt)

  - [Full context file](https://wapiso.com/llms-full.txt): {one line on what this page covers}

  line 39

  - [About](https://wapiso.com/about)

  - [About](https://wapiso.com/about): {one line on what this page covers}

  line 40

  - [Privacy Policy](https://wapiso.com/privacy-policy)

  - [Privacy Policy](https://wapiso.com/privacy-policy): {one line on what this page covers}

  Placeholders in { } are yours to write — we do not invent text about your pages.

• Descriptions add to the title Content & links +1

  Right now: 1 description just repeat the link title

  A description that echoes the title costs context and adds nothing. Say what is on the page, not what it is called.

  Where: The text after ": " on each link

  1. Find the descriptions that just repeat the link title and rewrite them.
  2. Say what is ON the page — the numbers, limits, formats or names a reader would come for.
  3. If the description and the title carry the same information, one of them is wasted context.

  In your file

  line 20

  - [Wix app](https://www.wix.com/app-market/821c74bf-8af6-4612-9342-b27db2c5ce44?referral=unlisted-app-821c74bf-8af6-4612-9342-b27db2c5ce44): Wix App Market

  - [Wix app](https: {what is on the page — numbers, limits, formats}

  Placeholders in { } are yours to write — we do not invent text about your pages.

• List items are markdown links Content & links +1

  Right now: 3 of 21 list items are plain text, not links

  A file list needs `- [Title](url): description`. A plain line gives a model something to read but nowhere to go — it cannot follow it, quote it, or check it.

  Where: Every "- " line in llms.txt

  1. Turn each plain line into a markdown link: "- [Title](https://your-site/page.md): description".
  2. A line without a URL gives a model something to read but nowhere to go — it cannot follow, quote or verify it.
  3. If a fact has no page behind it (an address, a phone number), put it in the free-text body above the sections, not in a file list.
  4. Note that "#" is a heading in markdown, not a comment — lines starting with # become H1/H2 headings.

  In your file

  line 22

  - Any other website: one-line embed snippet (see [API Docs](https://wapiso.com/api-docs))

  - [Any other website]({https://your-site/path}.md): {what this page covers}

  line 28

  - Chrome extensions: [Proxy Pilot](https://chromewebstore.google.com/detail/proxy-pilot/iojppobpmcfdfbgifhplacljbgflmnea) · [Devsly Network Tools](https://chromewebstore.google.com/detail/devsly-network-tools/lcminojmjdgkkleeioccbmoijiggnlmb) · [HookFlow Webhook Tester](https://chromewebstore.google.com/detail/hookflow-webhook-tester-i/bdmjhglkoanbclcdmndbepoiigpgcnch)

  - [Chrome extensions]({https://your-site/path}.md): {what this page covers}

  line 29

  - Other products (Anyto Pro, Cawra, Click2Dial, B2B Lead Marketplace) — dedicated pages rolling out.

  - [Other products (Anyto Pro, Cawra, Click2Dial, B2B Lead Marketplace) — dedicated pages rolling out.]({https://your-site/path}.md): {what this page covers}

  Placeholders in { } are yours to write — we do not invent text about your pages.

• Title is not padded or repetitive Search-engine basics +1

  Right now: “wapi” appears twice — brand padding that spends visible characters

  Say the brand once. Use the freed characters to describe what the product does.

  Where: The <title> tag on your homepage

  1. Say the brand once. The repeated word this check found is spending visible characters for nothing.
  2. Use the freed characters to describe what the product does.

  Instead of

  <title>Hurdacı — İstanbul Hurdacı | Hurdacı</title>

  Do this

  <title>Scrap metal collection in Istanbul — same-day payment</title>

• robots.txt exists Discovery & access +1

  Right now: No robots.txt

  Publish a /robots.txt. Even a permissive one is a signal that the site is deliberately crawlable.

  Where: Your site root: /robots.txt

  1. Create /robots.txt even if you allow everything — silence is not the same as permission.
  2. Declare your sitemap in it so crawlers find the full URL list.
  3. Keep it short: a long rule list is easier to get wrong than a small one.

  Do this

  User-agent: *
  Allow: /
  
  Sitemap: https://yourdomain.com/sitemap.xml

• robots.txt points at a sitemap Discovery & access +1

  Right now: No Sitemap: line

  Add a Sitemap: line to robots.txt. llms.txt says what matters; the sitemap says what exists.

  Where: /robots.txt

  1. Add one Sitemap: line with the absolute URL of your sitemap.
  2. llms.txt tells a model what matters; the sitemap tells a crawler what exists. They are not substitutes.

  Do this

  Sitemap: https://yourdomain.com/sitemap.xml

This score is Devsly’s own heuristic, not an official standard — llms.txt has no scoring body. It measures how well a file serves an AI assistant, and it does not predict whether any assistant will cite the site. The reading is a snapshot from 19 September 2026; run it again for the current state, or check a different site.