AigeoRadar · AI Context Benchmark

AI Context Benchmark

Question → sufficient layer(s) → retrieved slice → measured cost → evidence

Anahtar Teslim Mağaza Dekorasyon

https://ankaraanahtarteslim.com.tr/ankara-anahtar-teslim-magaza-tadilat-dekorasyon-ve-magaza-yenileme-firmasi/

13 questions Answer LLM: unknown ai_context_benchmark_v1

Of 13 questions: lowest measured retrieval cost among sufficient layers — HTML 6 · Schema 0 · AIPM 6 · multi-layer 0 · unanswered 1. Descriptive counts only; no overall ranking.

Of 13 questions: lowest measured retrieval cost among sufficient layers — HTML 6 · Schema 0 · AIPM 6 · multi-layer 0 · unanswered 1. Descriptive counts only; no overall ranking. Each question shows: sufficient layer(s) → retrieved slice → measured input tokens → evidence. Readers interpret; the report does not rank formats. Semantic Redundancy 59% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.

Gold mode · Mixed independent + AIPM consistency

Most Understanding/Retrieval gold comes from HTML. Some questions remain AIPM self-consistency checks (tagged) and are excluded from Understanding when possible. Matching a machine card against its own fields is not evidence that that layer outperforms HTML.

Execution provenance

Methodology: AI Context Benchmark Methodology v1.0
Planner Spec: v1.0
Execution Protocol: v1.0
Question pack: universal_v1
Score version: aipm_benchmark_score_v10
Engine: aipm_benchmark_v4
Answer LLM: unknown / unknown (single provider this lab)
Model snapshot: 2026-07
Run id: af162d83-aa79-4392-8106-6e262361a906

Question outcomes

Per question: which layers were sufficient, and what was the lowest measured retrieval cost among them. No overall winner.

Lowest cost: HTML

Lowest cost: Schema

Lowest cost: AIPM

Multi-layer

Unanswered

Manifest design

Semantic Redundancy · 59%

Semantic Redundancy 59% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.

→Merge or differentiate `purpose` and `abstract` (100% overlap).

Field A	Field B	Overlap
`purpose`	`abstract`	100%
`abstract`	`title`	47%
`purpose`	`keyFacts`	45%
`abstract`	`keyFacts`	45%

Structural size (secondary)

Structural size is secondary. A larger AIPM is not a failure if per-question retrieval stays tiny — check Semantic Redundancy instead.

HTML · 0 chars

Schema · 0 chars

AIPM · 0 chars

Routing helper (secondary)

Illustrative card-first vs HTML-always simulation — prefer per-question measured cost above. Not a ranking.

Card-first retrieval would use ~34% fewer tokens than HTML-always on this pack (8 answered from machine card, 5 escalated to HTML). Descriptive only.

Orientation pack

9 questions · all layers scored

HTML 4/9
Schema 0/9
AIPM 7/9

Depth pack

4 questions · all layers scored

HTML 4/4
Schema 0/4
AIPM 1/4

Full-context pack metrics (secondary)

These measure the whole file fed to the model this run — not the minimum slice needed per question.

HTML

9/13 matched

6,884 full-pack tokens

Schema

0/13 matched

1 full-pack tokens

AIPM

8/13 matched

6,275 full-pack tokens

Full-pack resource table (secondary)

Whole-file context fed this run. Prefer Minimal Retrieval Cost on each question.

Metric	HTML	Schema	AIPM
Coverage (matched)	9/13	0/13	8/13
Context size	0 chars	0 chars	0 chars
Total tokens	6,884	1	6,275
Tokens / correct answer	765	—	784
Est. cost / correct answer	$0.000136	—	$0.000132
Matched per 1k tokens	1.307	0.000	1.275
Median latency	1,272 ms	0 ms	1,504 ms
Est. cost (USD)	$0.00122	$0.00000	$0.00106

Six independent scores

Answer Efficiency is the primary cost lens. Accuracy axes remain for research — no combined total or winner.

Answer Efficiency

Matched answers per 1k tokens (and cost per match). The primary efficiency axis — not raw accuracy.

HTML 100
Schema 0
AIPM 97.6

Understanding

Can this layer convey what the page is about — using independent HTML gold?

HTML 40
Schema 0
AIPM 100

Retrieval

Can this layer surface shared facts (location, contact, hours, pricing, FAQ, CTA)?

HTML 100
Schema 0
AIPM 25

Evidence

Answer quality vs independent gold (score strength). Partial credit counts; UNKNOWN scores zero unless gold is UNKNOWN.

HTML 68.5
Schema 0
AIPM 59.2

Metadata

Language, page kind, and freshness from page signals.

HTML 66.7
Schema 0
AIPM 66.7

Compression

Information delivered per token and context size. Higher means more matched answers for less context cost.

HTML 100
Schema 0
AIPM 97.6

Coverage map

AIPM matched 8 question(s) (alone on Q2, Q3, Q5, Q9); HTML matched 8. HTML/Schema (or a gap) still needed on Q7, Q8, Q11, Q12, Q13. No layer matched gold on Q8. Read this as complementary coverage — AIPM orients agents cheaply; HTML supplies depth when the sidecar cannot. HTML 9/13 matched (≈765 tok/match). Schema 0/13 matched (≈— tok/match). AIPM 8/13 matched (≈784 tok/match). Figures are descriptive per layer — not a ranking. See per-question chains for sufficient layers, slice size, and measured cost.

AIPM matched

Q1, Q2, Q3, Q4, Q5, Q6, Q9, Q10

Alone: Q2, Q3, Q5, Q9

AIPM insufficient

Q7, Q8, Q11, Q12, Q13

HTML/Schema needed or all layers missed

Unanswered by all

HTML layer

Visible page text after stripping AIPM sidecars and JSON-LD. Measures what prose alone can answer.

Context fed: 0 chars

Tokens: 6,884 · median 1,272 ms

Matched this pack: 9/13

Stronger on

Retrieval (100) · Compression (100) · Answer Efficiency (100)

Weaker on

—

Schema layer

JSON-LD structured data with minimal page chrome. Measures what schema markup can answer.

Context fed: 0 chars

Tokens: 0 · median 0 ms

Matched this pack: 0/13

Stronger on

—

Weaker on

Understanding (0) · Retrieval (0) · Metadata (0) · Evidence (0) · Compression (0) · Answer Efficiency (0)

AIPM layer

AI Page Manifest (.ai.json) only. Measures what the machine layer can answer without HTML.

Context fed: 0 chars

Tokens: 6,275 · median 1,504 ms

Matched this pack: 8/13

Stronger on

Understanding (100) · Compression (97.6) · Answer Efficiency (97.6)

Weaker on

Retrieval (25)

When to use which layer

AIPM complements HTML — it does not replace full-page prose.

Scenario	Recommended	Why
Fast orientation (title, purpose, brand, intent)	Compare machine card → HTML fallback on this run	Machine-card pack: 6,275 tok · $0.00106. Routing sim saved ~34% tokens vs HTML-always.
Deep content / research (prose facts, process detail)	HTML (with optional machine orientation)	HTML pack: 6,884 tok · $0.00122. Use when depth needs body prose.
Structured entity pulls (org, location, typed fields)	Schema.org	Schema pack: 1 tok · $0.00000. Dense JSON-LD tends to score well here.

Findings

—Of 13 questions: lowest measured retrieval cost among sufficient layers — HTML 6 · Schema 0 · AIPM 6 · multi-layer 0 · unanswered 1. Descriptive counts only; no overall ranking.
—Semantic Redundancy 59% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.
—Manifest design: Merge or differentiate `purpose` and `abstract` (100% overlap).
—Structural size is secondary. A larger AIPM is not a failure if per-question retrieval stays tiny — check Semantic Redundancy instead.
—AIPM matched 8 question(s) (alone on Q2, Q3, Q5, Q9); HTML matched 8. HTML/Schema (or a gap) still needed on Q7, Q8, Q11, Q12, Q13. No layer matched gold on Q8. Read this as complementary coverage — AIPM orients agents cheaply; HTML supplies depth when the sidecar cannot. HTML 9/13 matched (≈765 tok/match). Schema 0/13 matched (≈— tok/match). AIPM 8/13 matched (≈784 tok/match). Figures are descriptive per layer — not a ranking. See per-question chains for sufficient layers, slice size, and measured cost.

Question-by-question layer analysis

Which layer(s) could answer; which need more or different context; minimum context fed this run.

Q1 · Understanding · orientation

What is the page title?

Gold: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme – Ankara Anahtar Teslim

Gold source: html.title · html_independent

Sufficient: HTML, AIPM · Needs more / other context: Schema

Measured retrieval cost (API tokens) · lowest cost AIPM · 123 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`title`	127 api	1	high	yes
Schema	`name`	— api	2	low	no
AIPM	`title`	123 api	1	high	yes

Execution chain · AIPM · 1 round(s)

Question: What is the page title?
Planner: Planner mapped question `title` on AIPM to minimal fields: title.
Slice: title — AIPM.title: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme
Actual input tokens: 123
LLM answer: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme
Evidence: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme
Confidence: high · matched yes

Execution chain · HTML · 1 round(s)

Question: What is the page title?
Planner: Planner mapped question `title` on HTML to minimal fields: title.
Slice: title — HTML.title: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme – Ankara An...
Actual input tokens: 127
LLM answer: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme – Ankara Anahtar Teslim
Evidence: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme – Ankara Anahtar Teslim
Confidence: high · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: What is the page title?
Planner: Planner mapped question `title` on SCHEMA to minimal fields: name, headline.
Slice: name
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

HTML

sufficient

Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme – Ankara Anahtar Teslim

score 100 · 0 chars context · 127 in-tokens

HTML answered using 0 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

sufficient

Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme

score 93 · 0 chars context · 123 in-tokens

AIPM answered using 0 chars of layer context (minimum fed this run).

Q2 · Understanding · orientation

What is the primary topic of this page?

Gold: Ankara Mağaza Tadilat ve Dekorasyon Firması

Gold source: html.h1 · html_independent

Sufficient: AIPM · Needs more / other context: HTML, Schema

Measured retrieval cost (API tokens) · lowest cost AIPM · 111 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`h1+title+lead_paragraphs+prose_span+body_excerpt`	792 api	2	low	no
Schema	`name`	— api	2	low	no
AIPM	`primaryTopic`	111 api	1	medium	yes

Execution chain · AIPM · 1 round(s)

Question: What is the primary topic of this page?
Planner: Planner mapped question `primary_topic` on AIPM to minimal fields: primaryTopic.
Slice: primaryTopic — AIPM.primaryTopic: Ankara Anahtar Teslim Tadilat
Actual input tokens: 111
LLM answer: Ankara Anahtar Teslim Tadilat.
Evidence: Ankara Anahtar Teslim Tadilat
Confidence: medium · matched yes

Execution chain · HTML · 2 round(s)

Question: What is the primary topic of this page?
Planner: Planner mapped question `primary_topic` on HTML to minimal fields: h1, title.
Slice: h1+title+lead_paragraphs+prose_span+body_excerpt — HTML.h1: Hizmetlerimiz HTML.title: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağ...
Actual input tokens: 792
LLM answer: The primary topic of this page is professional store renovation and decoration services in Ankara.
Evidence: HTML.h1: Hizmetlerimiz HTML.title: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme – Ankara Anahtar Teslim HT...
Confidence: low · matched no

Round 1: 140 in-tok · score 20 · miss

Round 2: 652 in-tok · score 20 · miss

Execution chain · SCHEMA · 2 round(s)

Question: What is the primary topic of this page?
Planner: Planner mapped question `primary_topic` on SCHEMA to minimal fields: name, description.
Slice: name
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

HTML

insufficient

The primary topic of this page is professional store renovation and decoration services in Ankara.

score 20 · 0 chars context · 792 in-tokens

HTML did not answer from 0 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

sufficient

Ankara Anahtar Teslim Tadilat.

score 70 · 0 chars context · 111 in-tokens

AIPM answered using 0 chars of layer context (minimum fed this run).

Q3 · Understanding · orientation

What is the purpose of this page?

Gold: Ankara Anahtar Teslim: Ankara Mağaza Tadilat ve Dekorasyon Firması — page overview from HTML signals.

Gold source: html.page_summary · html_independent

Sufficient: AIPM · Needs more / other context: HTML, Schema

Measured retrieval cost (API tokens) · lowest cost AIPM · 673 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+title+h1+prose_span+body_excerpt`	943 api	2	low	no
Schema	`description`	— api	2	low	no
AIPM	`purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent`	673 api	2	medium	yes

Execution chain · AIPM · 2 round(s)

Question: What is the purpose of this page?
Planner: Planner mapped question `purpose` on AIPM to minimal fields: purpose.
Slice: purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent — AIPM.purpose: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nın...
Actual input tokens: 673
LLM answer: The purpose of this page is to provide information about Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması.
Evidence: AIPM.purpose: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nın tüm semtlerinde — Çayyolu, Yaşamkent, İ...
Confidence: medium · matched yes

Round 1: 158 in-tok · score 11 · miss

Round 2: 515 in-tok · score 78 · match

Execution chain · HTML · 2 round(s)

Question: What is the purpose of this page?
Planner: Planner mapped question `purpose` on HTML to minimal fields: meta_description, lead_paragraphs.
Slice: lead_paragraphs+title+h1+prose_span+body_excerpt — HTML.lead_paragraphs: Ankara’nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı, Beysukent, Üm...
Actual input tokens: 943
LLM answer: The purpose of this page is to offer professional store renovation, decoration, and turnkey store renewal services in Ankara.
Evidence: HTML.lead_paragraphs: Ankara’nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı, Beysukent, Ümitköy, Bağlıca, Eryaman, Etimesgut, Batı...
Confidence: low · matched no

Round 1: 280 in-tok · score 11 · miss

Round 2: 663 in-tok · score 11 · miss

Execution chain · SCHEMA · 2 round(s)

Question: What is the purpose of this page?
Planner: Planner mapped question `purpose` on SCHEMA to minimal fields: description.
Slice: description
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

HTML

insufficient

The purpose of this page is to offer professional store renovation, decoration, and turnkey store renewal services in Ankara.

score 11 · 0 chars context · 943 in-tokens

HTML did not answer from 0 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

sufficient

The purpose of this page is to provide information about Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması.

score 78 · 0 chars context · 673 in-tokens

AIPM answered using 0 chars of layer context (minimum fed this run).

Q4 · Understanding · orientation

Summarize the page in one sentence.

Gold: Ankara Anahtar Teslim: Ankara Mağaza Tadilat ve Dekorasyon Firması — page overview from HTML signals.

Gold source: html.page_summary · html_independent

Sufficient: HTML, AIPM · Needs more / other context: Schema

Measured retrieval cost (API tokens) · lowest cost AIPM · 674 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+title+h1+prose_span+body_excerpt`	945 api	2	medium	yes
Schema	`description`	— api	2	low	no
AIPM	`abstract+purpose+primaryTopic+title+publisher+keyFacts+audience+contentIntent`	674 api	2	medium	yes

Execution chain · AIPM · 2 round(s)

Question: Summarize the page in one sentence.
Planner: Planner mapped question `abstract` on AIPM to minimal fields: abstract.
Slice: abstract+purpose+primaryTopic+title+publisher+keyFacts+audience+contentIntent — AIPM.abstract: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nı...
Actual input tokens: 674
LLM answer: Ankara Anahtar Teslim Mağaza Tadilat is a firm specializing in store renovation, decoration, and remodeling services across various neighborhoods in Ankara.
Evidence: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı,...
Confidence: medium · matched yes

Round 1: 158 in-tok · score 11 · miss

Round 2: 516 in-tok · score 70 · match

Execution chain · HTML · 2 round(s)

Question: Summarize the page in one sentence.
Planner: Planner mapped question `abstract` on HTML to minimal fields: meta_description, lead_paragraphs.
Slice: lead_paragraphs+title+h1+prose_span+body_excerpt — HTML.lead_paragraphs: Ankara’nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı, Beysukent, Üm...
Actual input tokens: 945
LLM answer: Ankara'da profesyonel mağaza tadilat, dekorasyon ve anahtar teslim yenileme hizmetleri sunan firma, 2005'ten beri müşteri çekici ve modern mağaza tasarımları ol...
Evidence: HTML.lead_paragraphs: Ankara’nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı, Beysukent, Ümitköy, Bağlıca, Eryaman, Etimesgut, Batı...
Confidence: medium · matched yes

Round 1: 281 in-tok · score 33 · miss

Round 2: 664 in-tok · score 55 · match

Execution chain · SCHEMA · 2 round(s)

Question: Summarize the page in one sentence.
Planner: Planner mapped question `abstract` on SCHEMA to minimal fields: description.
Slice: description
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

HTML

sufficient

Ankara'da profesyonel mağaza tadilat, dekorasyon ve anahtar teslim yenileme hizmetleri sunan firma, 2005'ten beri müşteri çekici ve modern mağaza tasarımları oluşturuyor.

score 55 · 0 chars context · 945 in-tokens

HTML answered using 0 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

sufficient

Ankara Anahtar Teslim Mağaza Tadilat is a firm specializing in store renovation, decoration, and remodeling services across various neighborhoods in Ankara.

score 70 · 0 chars context · 674 in-tokens

AIPM answered using 0 chars of layer context (minimum fed this run).

Q5 · Understanding · orientation

Who is the publisher or brand?

Gold: Ankara Anahtar Teslim

Gold source: html.jsonld|title · html_independent

Sufficient: AIPM · Needs more / other context: HTML, Schema

Measured retrieval cost (API tokens) · lowest cost AIPM · 105 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`title+h1+lead_paragraphs+prose_span+body_excerpt`	770 api	2	low	no
Schema	`publisher`	— api	2	low	no
AIPM	`publisher`	105 api	1	high	yes

Execution chain · AIPM · 1 round(s)

Question: Who is the publisher or brand?
Planner: Planner mapped question `publisher` on AIPM to minimal fields: publisher.
Slice: publisher — AIPM.publisher: Ankara Anahtar Teslim
Actual input tokens: 105
LLM answer: Ankara Anahtar Teslim.
Evidence: Ankara Anahtar Teslim
Confidence: high · matched yes

Execution chain · HTML · 2 round(s)

Question: Who is the publisher or brand?
Planner: Planner mapped question `publisher` on HTML to minimal fields: title.
Slice: title+h1+lead_paragraphs+prose_span+body_excerpt — HTML.title: Ankara Mağaza Tadilat ve Dekorasyon Firması | Anahtar Teslim Mağaza Yenileme – Ankara An...
Actual input tokens: 770
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 128 in-tok · score 0 · miss

Round 2: 642 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)

Question: Who is the publisher or brand?
Planner: Planner mapped question `publisher` on SCHEMA to minimal fields: publisher, name.
Slice: publisher
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

HTML

insufficient

UNKNOWN.

score 0 · 0 chars context · 770 in-tokens

HTML did not answer from 0 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

sufficient

Ankara Anahtar Teslim.

score 100 · 0 chars context · 105 in-tokens

AIPM answered using 0 chars of layer context (minimum fed this run).

Q6 · Metadata · orientation

What language is this page in?

Gold: tr

Gold source: html.lang|script · html_independent

Sufficient: HTML, AIPM · Needs more / other context: Schema

Measured retrieval cost (API tokens) · lowest cost HTML · 100 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lang`	100 api	1	high	yes
Schema	`inLanguage`	— api	2	low	no
AIPM	`inLanguage`	101 api	1	high	yes

Execution chain · AIPM · 1 round(s)

Question: What language is this page in?
Planner: Planner mapped question `language` on AIPM to minimal fields: inLanguage.
Slice: inLanguage — AIPM.inLanguage: tr
Actual input tokens: 101
LLM answer: tr
Evidence: tr
Confidence: high · matched yes

Execution chain · HTML · 1 round(s)

Question: What language is this page in?
Planner: Planner mapped question `language` on HTML to minimal fields: lang.
Slice: lang — HTML.lang: lang=tr
Actual input tokens: 100
LLM answer: The page is in Turkish (tr).
Evidence: HTML.lang: lang=tr
Confidence: high · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: What language is this page in?
Planner: Planner mapped question `language` on SCHEMA to minimal fields: inLanguage.
Slice: inLanguage
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

HTML

sufficient

The page is in Turkish (tr).

score 88 · 0 chars context · 100 in-tokens

HTML answered using 0 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

sufficient

score 100 · 0 chars context · 101 in-tokens

AIPM answered using 0 chars of layer context (minimum fed this run).

Q7 · Metadata · orientation

What is the content intent?

Gold: commercial

Gold source: html.heuristic · html_independent

Sufficient: HTML · Partial: AIPM · Needs more / other context: Schema

Measured retrieval cost (API tokens) · lowest cost HTML · 278 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs`	278 api	1	high	yes
Schema	`name`	— api	2	low	no
AIPM	`contentIntent`	614 api	2	low	no

Execution chain · AIPM · 2 round(s)

Question: What is the content intent?
Planner: Planner mapped question `content_intent` on AIPM to minimal fields: contentIntent.
Slice: contentIntent — AIPM.contentIntent: informational
Actual input tokens: 614
LLM answer: The content intent is informational.
Evidence: AIPM.contentIntent: informational
Confidence: low · matched no

Round 1: 101 in-tok · score 40 · miss

Round 2: 513 in-tok · score 0 · miss

Execution chain · HTML · 1 round(s)

Question: What is the content intent?
Planner: Planner mapped question `content_intent` on HTML to minimal fields: meta_description, lead_paragraphs.
Slice: lead_paragraphs — HTML.lead_paragraphs: Ankara’nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı, Beysukent, Üm...
Actual input tokens: 278
LLM answer: The content intent is to promote professional store renovation, decoration, and turnkey store renewal services in various districts of Ankara.
Evidence: HTML.lead_paragraphs: Ankara’nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı, Beysukent, Ümitköy, Bağlıca, Eryaman, Etimesgut, Batı...
Confidence: high · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: What is the content intent?
Planner: Planner mapped question `content_intent` on SCHEMA to minimal fields: name, description.
Slice: name
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

Root cause · Wrong contentIntent

Set AIPM contentIntent to match page intent (commercial vs informational).

HTML

sufficient

The content intent is to promote professional store renovation, decoration, and turnkey store renewal services in various districts of Ankara.

score 88 · 0 chars context · 278 in-tokens

HTML answered using 0 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

partial

The content intent is informational.

score 40 · 0 chars context · 614 in-tokens

AIPM was only partially aligned with gold from 0 chars of context.

Q8 · Understanding · orientation

Who is the intended audience declared in AIPM?

Gold: Ev sahipleri, daire sahipleri, villa sahipleri, iş yeri sahipleri, ofis yöneticileri, mağaza işletmeleri, eczane sahipleri, diş klinikleri, yatırım amaçlı gayrimenkul sahipleri, müteahhitler, mimarlar, iç mimarlar, site yönetimleri, Ankara'da profesyonel anahtar teslim tadilat

Gold source: audience · aipm_consistency

No layer provided a sufficient answer from its context alone.

Measured retrieval cost (API tokens) · lowest cost AIPM · 706 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+title+h1+prose_span+body_excerpt`	1,002 api	2	high	no
Schema	`name`	— api	2	low	no
AIPM	`audience`	706 api	2	low	no

Execution chain · AIPM · 2 round(s)

Question: Who is the intended audience declared in AIPM?
Planner: Planner mapped question `audience` on AIPM to minimal fields: audience.
Slice: audience — AIPM.audience: ["Ev sahipleri","daire sahipleri","villa sahipleri","iş yeri sahipleri","ofis yönetic...
Actual input tokens: 706
LLM answer: The intended audience declared in AIPM includes property owners, office managers, store operators, pharmacy owners, dental clinics, real estate investors, contr...
Evidence: AIPM.audience: ["Ev sahipleri","daire sahipleri","villa sahipleri","iş yeri sahipleri","ofis yöneticileri","mağaza işletmeleri","eczane sahi...
Confidence: low · matched no

Round 1: 188 in-tok · score 8 · miss

Round 2: 518 in-tok · score 0 · miss

Execution chain · HTML · 2 round(s)

Question: Who is the intended audience declared in AIPM?
Planner: Planner mapped question `audience` on HTML to minimal fields: lead_paragraphs.
Slice: lead_paragraphs+title+h1+prose_span+body_excerpt — HTML.lead_paragraphs: Ankara’nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı, Beysukent, Üm...
Actual input tokens: 1,002
LLM answer: Ev sahipleri, daire sahipleri, villa sahipleri, iş yeri sahipleri, ofis yöneticileri, mağaza işletmeleri, eczane sahipleri, diş klinikleri, yatırım amaçlı gayri...
Evidence: Ev sahipleri, daire sahipleri, villa sahipleri, iş yeri sahipleri, ofis yöneticileri, mağaza işletmeleri, eczane sahipleri, diş klinikleri,...
Confidence: high · matched no

Round 1: 283 in-tok · score 0 · miss

Round 2: 719 in-tok · score 87 · match

Execution chain · SCHEMA · 2 round(s)

Question: Who is the intended audience declared in AIPM?
Planner: Planner mapped question `audience` on SCHEMA to minimal fields: name, description.
Slice: name
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

Root cause · Self-consistency miss

AIPM failed to read its own declared field — check serialization.

HTML

skipped

Ev sahipleri, daire sahipleri, villa sahipleri, iş yeri sahipleri, ofis yöneticileri, mağaza işletmeleri, eczane sahipleri, diş klinikleri, yatırım amaçlı gayrimenkul sahipleri, müteahhitler, mimarlar, iç mimarlar ve site yönetimleri.

score 0 · 0 chars context · 0 in-tokens

Skipped (AIPM-only).

Schema

skipped

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Skipped (AIPM-only).

AIPM

insufficient

The intended audience declared in AIPM includes property owners, office managers, store operators, pharmacy owners, dental clinics, real estate investors, contractors, architects, interior designers, site management, and professional renovation services in Ankara.

score 8 · 0 chars context · 706 in-tokens

AIPM did not answer from 0 chars of context — additional or different layer context needed.

Q9 · Metadata · orientation

What page type is declared in the machine layer?

Gold: blog

Gold source: pageType · aipm_consistency

Sufficient: AIPM

Measured retrieval cost (API tokens) · lowest cost AIPM · 104 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+title+h1+prose_span+body_excerpt`	922 api	2	low	no
Schema	`@type`	— api	2	low	no
AIPM	`pageType`	104 api	1	high	yes

Execution chain · AIPM · 1 round(s)

Question: What page type is declared in the machine layer?
Planner: Planner mapped question `page_type` on AIPM to minimal fields: pageType.
Slice: pageType — AIPM.pageType: blog
Actual input tokens: 104
LLM answer: blog
Evidence: blog
Confidence: high · matched yes

Execution chain · HTML · 2 round(s)

Question: What page type is declared in the machine layer?
Planner: Planner mapped question `page_type` on HTML to minimal fields: lead_paragraphs.
Slice: lead_paragraphs+title+h1+prose_span+body_excerpt — HTML.lead_paragraphs: Ankara’nın tüm semtlerinde — Çayyolu, Yaşamkent, İncek, Gölbaşı, Beysukent, Üm...
Actual input tokens: 922
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 282 in-tok · score 0 · miss

Round 2: 640 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)

Question: What page type is declared in the machine layer?
Planner: Planner mapped question `page_type` on SCHEMA to minimal fields: @type.
Slice: @type
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

HTML

skipped

UNKNOWN.

score 0 · 0 chars context · 0 in-tokens

Skipped (AIPM-only).

Schema

skipped

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Skipped (AIPM-only).

AIPM

sufficient

blog

score 100 · 0 chars context · 104 in-tokens

AIPM answered using 0 chars of layer context (minimum fed this run).

Q10 · Retrieval · depth

Which location or city is mentioned for this business?

Gold: Ankara

Gold source: html.address|prose · html_independent

Sufficient: HTML, AIPM · Needs more / other context: Schema

Measured retrieval cost (API tokens) · lowest cost HTML · 104 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`prose_span`	104 api	1	high	yes
Schema	`address`	— api	2	low	no
AIPM	`purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent`	446 api	2	high	yes

Execution chain · AIPM · 2 round(s)

Question: Which location or city is mentioned for this business?
Planner: Planner mapped question `geo_signal` on AIPM to minimal fields: geo, areaServed, address.
Slice: purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent — AIPM.purpose: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nın...
Actual input tokens: 446
LLM answer: Ankara.
Evidence: AIPM.purpose: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nın tüm semtlerinde — Çayyolu, Yaşamkent, İ...
Confidence: high · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 446 in-tok · score 100 · match

Execution chain · HTML · 1 round(s)

Question: Which location or city is mentioned for this business?
Planner: Planner mapped question `geo_signal` on HTML to minimal fields: prose_span.
Slice: prose_span — HTML.prose_span: Ankara
Actual input tokens: 104
LLM answer: Ankara
Evidence: Ankara
Confidence: high · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: Which location or city is mentioned for this business?
Planner: Planner mapped question `geo_signal` on SCHEMA to minimal fields: address, addressLocality, areaServed.
Slice: address
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

HTML

sufficient

Ankara

score 100 · 0 chars context · 104 in-tokens

HTML answered using 0 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

sufficient

Ankara.

score 100 · 0 chars context · 446 in-tokens

AIPM answered using 0 chars of layer context (minimum fed this run).

Q11 · Retrieval · depth

According to the page, what does it say about: "Ev, ofis ve iş yerlerinizde profesyonel ve güven…"?

Gold: Ev, ofis ve iş yerlerinizde profesyonel ve güvenilir çözümler için hemen bize ulaşın.

Gold source: html.prose · html_independent

Sufficient: HTML · Needs more / other context: Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost HTML · 145 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`prose_span`	145 api	1	high	yes
Schema	`description`	— api	2	low	no
AIPM	`keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent`	786 api	2	low	no

Execution chain · AIPM · 2 round(s)

Question: According to the page, what does it say about: "Ev, ofis ve iş yerlerinizde profesyonel ve güven…"?
Planner: Planner mapped question `page_fact_1` on AIPM to minimal fields: keyFacts, sections.
Slice: keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent — AIPM.keyFacts: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nı...
Actual input tokens: 786
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 250 in-tok · score 0 · miss

Round 2: 536 in-tok · score 0 · miss

Execution chain · HTML · 1 round(s)

Question: According to the page, what does it say about: "Ev, ofis ve iş yerlerinizde profesyonel ve güven…"?
Planner: Planner mapped question `page_fact_1` on HTML to minimal fields: prose_span.
Slice: prose_span — HTML.prose_span: Ev, ofis ve iş yerlerinizde profesyonel ve güvenilir çözümler için hemen bize ulaşı...
Actual input tokens: 145
LLM answer: Ev, ofis ve iş yerlerinizde profesyonel ve güvenilir çözümler için hemen bize ulaşın.
Evidence: Ev, ofis ve iş yerlerinizde profesyonel ve güvenilir çözümler için hemen bize ulaşın.
Confidence: high · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: According to the page, what does it say about: "Ev, ofis ve iş yerlerinizde profesyonel ve güven…"?
Planner: Planner mapped question `page_fact_1` on SCHEMA to minimal fields: description, block.
Slice: description
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

Root cause · Depth gap (expected)

Prose/detail questions belong to HTML — escalate after AIPM orientation.

HTML

sufficient

Ev, ofis ve iş yerlerinizde profesyonel ve güvenilir çözümler için hemen bize ulaşın.

score 100 · 0 chars context · 145 in-tokens

HTML answered using 0 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

insufficient

UNKNOWN.

score 0 · 0 chars context · 786 in-tokens

AIPM did not answer from 0 chars of context — additional or different layer context needed.

Q12 · Retrieval · depth

According to the page, what does it say about: "2005’ten bu yana edindiğimiz tecrübeyle ma…"?

Gold: 2005’ten bu yana edindiğimiz tecrübeyle mağazanızı müşteri çeken, satışa dönüştüren ve markanızı yansıtan modern bir görünüme kavuşturuyoruz.

Gold source: html.prose · html_independent

Sufficient: HTML · Needs more / other context: Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost HTML · 169 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`prose_span`	169 api	1	high	yes
Schema	`description`	— api	2	low	no
AIPM	`keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent`	790 api	2	low	no

Execution chain · AIPM · 2 round(s)

Question: According to the page, what does it say about: "2005’ten bu yana edindiğimiz tecrübeyle ma…"?
Planner: Planner mapped question `page_fact_2` on AIPM to minimal fields: keyFacts, sections.
Slice: keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent — AIPM.keyFacts: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nı...
Actual input tokens: 790
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 252 in-tok · score 0 · miss

Round 2: 538 in-tok · score 0 · miss

Execution chain · HTML · 1 round(s)

Question: According to the page, what does it say about: "2005’ten bu yana edindiğimiz tecrübeyle ma…"?
Planner: Planner mapped question `page_fact_2` on HTML to minimal fields: prose_span.
Slice: prose_span — HTML.prose_span: 2005’ten bu yana edindiğimiz tecrübeyle mağazanızı müşteri çeken, satışa dönü...
Actual input tokens: 169
LLM answer: 2005'ten bu yana edindiğimiz tecrübeyle mağazanızı müşteri çeken, satışa dönüştüren ve markanızı yansıtan modern bir görünüme kavuşturuyoruz.
Evidence: HTML.prose_span: 2005’ten bu yana edindiğimiz tecrübeyle mağazanızı müşteri çeken, satışa dönüştüren ve markanızı yansıtan modern bir...
Confidence: high · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: According to the page, what does it say about: "2005’ten bu yana edindiğimiz tecrübeyle ma…"?
Planner: Planner mapped question `page_fact_2` on SCHEMA to minimal fields: description, block.
Slice: description
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

Root cause · Depth gap (expected)

Prose/detail questions belong to HTML — escalate after AIPM orientation.

HTML

sufficient

2005'ten bu yana edindiğimiz tecrübeyle mağazanızı müşteri çeken, satışa dönüştüren ve markanızı yansıtan modern bir görünüme kavuşturuyoruz.

score 97 · 0 chars context · 169 in-tokens

HTML answered using 0 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

insufficient

UNKNOWN.

score 0 · 0 chars context · 790 in-tokens

AIPM did not answer from 0 chars of context — additional or different layer context needed.

Q13 · Retrieval · depth

According to the page, what does it say about: "Ücretsiz Keşif ve Ön Proje: Uzman ekibimiz mağaz…"?

Gold: Ücretsiz Keşif ve Ön Proje: Uzman ekibimiz mağaza alanınıza gelir, ölçüm yapar ve markanıza özel iç mekan konsepti ile maliyet planı hazırlar.

Gold source: html.prose · html_independent

Sufficient: HTML · Needs more / other context: Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost HTML · 164 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`prose_span`	164 api	1	high	yes
Schema	`description`	— api	2	low	no
AIPM	`keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent`	790 api	2	low	no

Execution chain · AIPM · 2 round(s)

Question: According to the page, what does it say about: "Ücretsiz Keşif ve Ön Proje: Uzman ekibimiz mağaz…"?
Planner: Planner mapped question `page_fact_3` on AIPM to minimal fields: keyFacts, sections.
Slice: keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent — AIPM.keyFacts: Ankara Anahtar Teslim Mağaza Tadilat, Dekorasyon ve Mağaza Yenileme Firması Ankara'nı...
Actual input tokens: 790
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 252 in-tok · score 0 · miss

Round 2: 538 in-tok · score 0 · miss

Execution chain · HTML · 1 round(s)

Question: According to the page, what does it say about: "Ücretsiz Keşif ve Ön Proje: Uzman ekibimiz mağaz…"?
Planner: Planner mapped question `page_fact_3` on HTML to minimal fields: prose_span.
Slice: prose_span — HTML.prose_span: Ücretsiz Keşif ve Ön Proje: Uzman ekibimiz mağaza alanınıza gelir, ölçüm yapar ve m...
Actual input tokens: 164
LLM answer: Uzman ekibimiz mağaza alanınıza gelir, ölçüm yapar ve markanıza özel iç mekan konsepti ile maliyet planı hazırlar.
Evidence: Ücretsiz Keşif ve Ön Proje: Uzman ekibimiz mağaza alanınıza gelir, ölçüm yapar ve markanıza özel iç mekan konsepti ile maliyet planı hazırla...
Confidence: high · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: According to the page, what does it say about: "Ücretsiz Keşif ve Ön Proje: Uzman ekibimiz mağaz…"?
Planner: Planner mapped question `page_fact_3` on SCHEMA to minimal fields: description, block.
Slice: description
Actual input tokens: 0
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched no

Round 1: 0 in-tok · score 0 · miss

Round 2: 0 in-tok · score 0 · miss

Root cause · Depth gap (expected)

Prose/detail questions belong to HTML — escalate after AIPM orientation.

HTML

sufficient

Uzman ekibimiz mağaza alanınıza gelir, ölçüm yapar ve markanıza özel iç mekan konsepti ile maliyet planı hazırlar.

score 94 · 0 chars context · 164 in-tokens

HTML answered using 0 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN

score 0 · 0 chars context · 0 in-tokens

Schema did not answer from 0 chars of context — additional or different layer context needed.

AIPM

insufficient

UNKNOWN.

score 0 · 0 chars context · 790 in-tokens

AIPM did not answer from 0 chars of context — additional or different layer context needed.

Methodology

AI Context Benchmark: Planner → Slice → LLM with measured API input tokens.
Reports describe sufficient layers, slice size, cost, and evidence — they do not declare a winning format.
Layers under test today: HTML, Schema.org, AIPM (extensible to RSS, Markdown, PDF, …).
Engine aipm_benchmark_v4 · Wed, Jul 29, 2026 12:55 PM · aipm_benchmark_score_v10

Per-question context chain across layers.

Post on X LinkedIn WhatsApp

About the lab →

Question outcomes

Semantic Redundancy · 59%

Structural size (secondary)

Routing helper (secondary)

Orientation pack

Depth pack

Full-context pack metrics (secondary)

Full-pack resource table (secondary)

Six independent scores

Answer Efficiency

Understanding

Retrieval

Evidence

Metadata

Compression

Coverage map

HTML layer

Schema layer

AIPM layer

When to use which layer

Findings

Question-by-question layer analysis

What is the page title?

What is the primary topic of this page?

What is the purpose of this page?

Summarize the page in one sentence.

Who is the publisher or brand?

What language is this page in?

What is the content intent?

Who is the intended audience declared in AIPM?

What page type is declared in the machine layer?

Which location or city is mentioned for this business?

According to the page, what does it say about: "Ev, ofis ve iş yerlerinizde profesyonel ve güven…"?

According to the page, what does it say about: "2005&#8217;ten bu yana edindiğimiz tecrübeyle ma…"?

According to the page, what does it say about: "Ücretsiz Keşif ve Ön Proje: Uzman ekibimiz mağaz…"?

Methodology

Share

According to the page, what does it say about: "2005’ten bu yana edindiğimiz tecrübeyle ma…"?