kemalcalak.com — llms.txt & GEO score

Ali Kemal Çalak

Agentic AI engineer building agents, LLM systems and fullstack products. A portfolio shot on code — scroll-driven, cinematic, alive.

8 of 11 checks pass. What is left: points at clean markdown copies, link titles are descriptive and list items are markdown links.

• Every link carries a description 22 of 22 described (100%)
  10/10
• Descriptions say something concrete Average 120 characters across 22 described links
  7/7
• Descriptions add to the title No description merely repeats its title
  4/4
• Points at clean markdown copies 0 of 22 end in .md or .txt (0%, detected by file extension)
  0/10
• Link titles are descriptive 6 weak titles (bare URLs, “here”, one-word labels)
  0/4
• A workable number of links 22 links (12–50 is the sweet spot)
  4/4
• Skippable links marked Optional An ## Optional section is present
  3/3
• No duplicate links All 22 URLs are distinct
  2/2
• List items are markdown links 9 of 31 list items are plain text, not links
  2/4
• Enough written detail per link 37 words per link across 805 words
  3/3
• Links are absolute URLs All 22 links are absolute URLs
  1/1

6 of 7 checks pass. What is left: section names say what is inside.

• Exactly one H1 project title “Ali Kemal Çalak”
  3/3
• Summary directly under the title Present as a blockquote
  3/3
• Summary is a usable length 132 characters
  3/3
• Concrete language, not marketing filler No marketing filler detected
  3/3
• Grouped into balanced sections 5 H2 sections, largest group holds 9 of 22 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 1 of 5 headings are generic
  1/2

All 5 checks pass in this group.

• 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 68 B of crawler rules
  1/1
• AI crawlers are not blocked No AI user-agent is disallowed at the root
  6/6
• robots.txt points at a sitemap A Sitemap: line is declared
  1/1

All 6 checks pass in this group.

• Homepage title is the right length 37 characters, from title
  2/2
• Title is not padded or repetitive No repeated terms
  1/1
• Homepage has a meta description 132 characters, from meta description
  2/2
• Canonical URL declared https://kemalcalak.com
  1/1
• Language declared lang="en"
  1/1
• Social card image og:image is set
  1/1

1 of 5 checks pass. What is left: publishes llms-full.txt, the index points at the full file, server reports when it last changed and the index is kept current.

• Publishes llms-full.txt No llms-full.txt alongside the index
  0/3
• The index points at the full file No llms-full.txt exists to link to
  0/1
• Index is a sensible size 6.6 KB
  2/2
• Server reports when it last changed No Last-Modified header — clients cannot tell when this changed
  0/1
• The index is kept current Cannot be confirmed — the server sends no Last-Modified header
  0/2

• Points at clean markdown copies Content & links +10

  Right now: 0 of 22 end in .md or .txt (0%, 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 20

  - [About](https://kemalcalak.com/about): Ali Kemal Çalak — agentic AI engineer. The bio, capabilities, education and stack behind the agents, LLM systems and fullstack products he ships.

  - [About](https://kemalcalak.com/about.md): Ali Kemal Çalak — agentic AI engineer. The bio, capabilities, education and stack behind the agents, LLM systems and fullstack products he ships.

  line 21

  - [Projects](https://kemalcalak.com/projects): Selected work: agentic AI systems, LLM pipelines and fullstack products — DialogTR, SponsorHub, SaaS Starter and more, each broken down shot by shot.

  - [Projects](https://kemalcalak.com/projects.md): Selected work: agentic AI systems, LLM pipelines and fullstack products — DialogTR, SponsorHub, SaaS Starter and more, each broken down shot by shot.

  line 22

  - [Work](https://kemalcalak.com/work): Experience and roles of Ali Kemal Çalak — the production list behind the agentic AI and fullstack work, year by year.

  - [Work](https://kemalcalak.com/work.md): Experience and roles of Ali Kemal Çalak — the production list behind the agentic AI and fullstack work, year by year.

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

• Link titles are descriptive Content & links +4

  Right now: 6 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 19

  - [Home](https://kemalcalak.com): Agentic AI engineer building agents, LLM systems and fullstack products. A portfolio shot on code — scroll-driven, cinematic, alive.

  - [{the page’s real name}](https://kemalcalak.com): Agentic AI engineer building agents, LLM systems and fullstack products. A portfolio shot on code — scroll-driven, cinematic, alive.

  line 20

  - [About](https://kemalcalak.com/about): Ali Kemal Çalak — agentic AI engineer. The bio, capabilities, education and stack behind the agents, LLM systems and fullstack products he ships.

  - [{the page’s real name}](https://kemalcalak.com/about): Ali Kemal Çalak — agentic AI engineer. The bio, capabilities, education and stack behind the agents, LLM systems and fullstack products he ships.

  line 22

  - [Work](https://kemalcalak.com/work): Experience and roles of Ali Kemal Çalak — the production list behind the agentic AI and fullstack work, year by year.

  - [{the page’s real name}](https://kemalcalak.com/work): Experience and roles of Ali Kemal Çalak — the production list behind the agentic AI and fullstack work, year by year.

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

• Publishes llms-full.txt Depth & upkeep +3

  Right now: No llms-full.txt alongside the index

  Generate an llms-full.txt that inlines every linked page. Community convention rather than spec, but assistants with a large context window take the whole thing in one request.

  Where: Your docs build, output at /llms-full.txt

  1. Concatenate the markdown of every page listed in llms.txt into one file.
  2. Keep the heading structure: a client uses those headings to navigate a multi-megabyte file.
  3. Regenerate it in the same build step that publishes the docs, so it cannot drift.
  4. Note that llms-full.txt is a community convention, not part of the proposal — useful, but optional.
• List items are markdown links Content & links +2

  Right now: 9 of 31 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 39

  - Fullstack AI Engineer at SeriAI (07.2026 — Present · Remote): Fullstack on an enterprise AI platform — one workspace where a company runs assistants over swappable models on its own infrastructure instead of renting a single provider. Mostly the Next.js side of the product, plus the AI layer on top of the Vercel AI SDK: the skills and tool calls the assistants run.

  - [Fullstack AI Engineer at SeriAI (07.2026 — Present · Remote)]({https://your-site/path}.md): {what this page covers}

  line 40

  - Intern Software Engineer at Colobrix (09.2025 — 07.2026 · Remote): Built a multi-tenant PRM platform that connects vendors and partners — partnership management, customer and opportunity tracking, deal registration, project management, messaging and role-based access control — plus an AI-powered company-research workflow that enriches company profiles.

  - [Intern Software Engineer at Colobrix (09.2025 — 07.2026 · Remote): Built a multi-tenant PRM platform that connects vendors and partners — partnership management, customer and opportunity tracking, deal registration, project management, messaging and role-based access control — plus an AI-powered company-research workflow that enriches company profiles.]({https://your-site/path}.md): {what this page covers}

  line 41

  - Intern AI Engineer at Kafein Technology (07.2025 — 09.2025 · Istanbul, Hybrid): Developed AI-driven automation workflows on n8n, and built an n8n-style workflow platform with a FastAPI backend where users register, create their own workflows and share them.

  - [Intern AI Engineer at Kafein Technology (07.2025 — 09.2025 · Istanbul, Hybrid): Developed AI-driven automation workflows on n8n, and built an n8n-style workflow platform with a FastAPI backend where users register, create their own workflows and share them.]({https://your-site/path}.md): {what this page covers}

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

• The index is kept current Depth & upkeep +2

  Right now: Cannot be confirmed — the server sends no Last-Modified header

  Regenerate llms.txt when the docs change. A year-old index quietly points models at pages that have moved.

  Where: Your build pipeline

  1. Regenerate llms.txt in the same step that publishes content, so it cannot go stale silently.
  2. Treat it as a build artifact, not a hand-edited file — hand-edited indexes drift within a quarter.
  3. An llms.txt with discontinued products is worse than none: a model will repeat the wrong facts confidently.
• Section names say what is inside Structure +1

  Right now: 1 of 5 headings are generic

  Name sections after what a reader is looking for — “API reference” beats “Links”.

  Where: The "## " headings in llms.txt

  1. Replace generic names — "Links", "Other", "Misc", "Pages" — with what is actually inside.
  2. Name the section after the question it answers: "API reference" beats "Links".

  In your file

  line 17

  ## Pages

  ## {what is in this section}

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

• Server reports when it last changed Depth & upkeep +1

  Right now: No Last-Modified header — clients cannot tell when this changed

  Let the server send Last-Modified on llms.txt. Without it a client has to re-download the whole file to notice a change.

  Where: Your web server configuration

  1. Serve llms.txt as a real file on disk so the server can derive Last-Modified from its mtime.
  2. If it is generated by an application route, set the header yourself from the generation time.
  3. Without it a client has to re-download the whole file to notice a change, and cannot answer "is this current?".

  Instead of

  HTTP/1.1 200 OK\nContent-Type: text/plain

  Do this

  HTTP/1.1 200 OK\nContent-Type: text/plain\nLast-Modified: Wed, 10 Sep 2026 08:14:00 GMT

• The index points at the full file Depth & upkeep +1

  Right now: No llms-full.txt exists to link to

  Mention llms-full.txt inside llms.txt. Guessing the filename works often enough to be tempting and not often enough to rely on.

  Where: Inside llms.txt

  1. Mention the full file in llms.txt itself, as a link or a line of context.
  2. Guessing the filename works often enough to be tempting and not often enough to rely on.

  Do this

  Full inlined text: https://acme.example/llms-full.txt

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 13 October 2026; run it again for the current state, or check a different site.