AigeoRadar · AI Context Benchmark

AI Context Benchmark

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

WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar — sprint re-benchmark

https://aigeoradar.com/blog/wordpress-geo-llms-txt-guide

20 questions Answer LLM: gpt-4o-mini ai_context_benchmark_v1

Of 20 questions: lowest measured retrieval cost among sufficient layers — HTML 4 · Schema 10 · AIPM 5 · multi-layer 0 · unanswered 1. Descriptive counts only; no overall ranking.

Of 20 questions: lowest measured retrieval cost among sufficient layers — HTML 4 · Schema 10 · AIPM 5 · 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 25% — moderate field overlap; trim duplicated purpose/summary/keyFacts wording.

Gold mode · Independent HTML gold

Gold answers are derived from the HTML page (title, h1, lang, prose) — not from AIPM fields. Understanding/Retrieval therefore measure layer capability, not AIPM self-consistency. Human-authored gold.json remains the gold standard for publication-grade claims.

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: openai / gpt-4o-mini (single provider this lab)
Model snapshot: 2026-07
Run id: cab88463-3677-46e9-85b3-daeb98addf7b

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 · 25%

Semantic Redundancy 25% — moderate field overlap; trim duplicated purpose/summary/keyFacts wording.

→Reduce repeated wording across purpose, abstract, keyFacts, and sections.

Field A	Field B	Overlap
`purpose`	`primaryTopic`	25%

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 · 24,284 chars

Schema · 15,430 chars

AIPM · 37,462 chars

Routing helper (secondary)

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

Card-first retrieval would cost ~9% more tokens than HTML-always on this pack — machine card is heavier here.

Orientation pack

10 questions · all layers scored

HTML 8/10
Schema 4/10
AIPM 9/10

Depth pack

10 questions · all layers scored

HTML 7/10
Schema 8/10
AIPM 8/10

Full-context pack metrics (secondary)

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

HTML

15/20 matched

11,394 full-pack tokens

Schema

12/20 matched

9,044 full-pack tokens

AIPM

17/20 matched

14,556 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)	15/20	12/20	17/20
Context size	24,284 chars	15,430 chars	37,462 chars
Total tokens	11,394	9,044	14,556
Tokens / correct answer	760	754	856
Est. cost / correct answer	$0.000126	$0.000123	$0.000141
Matched per 1k tokens	1.316	1.327	1.168
Median latency	1,477 ms	1,172 ms	1,324 ms
Est. cost (USD)	$0.00189	$0.00148	$0.00239

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 99.2
Schema 100
AIPM 88

Understanding

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

HTML 85.7
Schema 28.6
AIPM 85.7

Retrieval

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

HTML 66.7
Schema 77.8
AIPM 77.8

Evidence

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

HTML 66.5
Schema 62.9
AIPM 81.1

Metadata

Language, page kind, and freshness from page signals.

HTML 66.7
Schema 66.7
AIPM 100

Compression

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

HTML 99.2
Schema 100
AIPM 88

Coverage map

AIPM matched 17 question(s) (alone on Q5, Q20); HTML matched 15. HTML/Schema (or a gap) still needed on Q7, Q16, Q18. No layer matched gold on Q18. Read this as complementary coverage — AIPM orients agents cheaply; HTML supplies depth when the sidecar cannot. HTML 15/20 matched (≈760 tok/match). Schema 12/20 matched (≈754 tok/match). AIPM 17/20 matched (≈856 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, Q8, Q9, Q10, Q11, Q12, Q13, Q14, Q15, Q17, Q19, Q20

Alone: Q5, Q20

AIPM insufficient

Q7, Q16, Q18

HTML/Schema needed or all layers missed

Unanswered by all

Q18

HTML layer

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

Context fed: 24,284 chars

Tokens: 11,394 · median 1,477 ms

Matched this pack: 15/20

Stronger on

Understanding (85.7) · Compression (99.2) · Answer Efficiency (99.2)

Weaker on

—

Schema layer

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

Context fed: 15,430 chars

Tokens: 9,044 · median 1,172 ms

Matched this pack: 12/20

Stronger on

Retrieval (77.8) · Compression (100) · Answer Efficiency (100)

Weaker on

Understanding (28.6)

AIPM layer

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

Context fed: 37,462 chars

Tokens: 14,556 · median 1,324 ms

Matched this pack: 17/20

Stronger on

Understanding (85.7) · Retrieval (77.8) · Metadata (100) · Evidence (81.1) · Compression (88) · Answer Efficiency (88)

Weaker on

—

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: 14,556 tok · $0.00239. Machine-card pack is heavier than HTML on this run — densify before relying on card-first retrieval.
Deep content / research (prose facts, process detail)	HTML (with optional machine orientation)	HTML pack: 11,394 tok · $0.00189. Use when depth needs body prose.
Structured entity pulls (org, location, typed fields)	Schema.org	Schema pack: 9,044 tok · $0.00148. Dense JSON-LD tends to score well here.

Findings

—Of 20 questions: lowest measured retrieval cost among sufficient layers — HTML 4 · Schema 10 · AIPM 5 · multi-layer 0 · unanswered 1. Descriptive counts only; no overall ranking.
—Semantic Redundancy 25% — moderate field overlap; trim duplicated purpose/summary/keyFacts wording.
—Manifest design: Reduce repeated wording across purpose, abstract, keyFacts, and sections.
—Structural size is secondary. A larger AIPM is not a failure if per-question retrieval stays tiny — check Semantic Redundancy instead.
—AIPM matched 17 question(s) (alone on Q5, Q20); HTML matched 15. HTML/Schema (or a gap) still needed on Q7, Q16, Q18. No layer matched gold on Q18. Read this as complementary coverage — AIPM orients agents cheaply; HTML supplies depth when the sidecar cannot. HTML 15/20 matched (≈760 tok/match). Schema 12/20 matched (≈754 tok/match). AIPM 17/20 matched (≈856 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 this page or business?

Gold: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026

Gold source: html.h1|title|jsonld.name · html_independent

Sufficient: HTML, AIPM · Partial: Schema

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 517 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`title+h1+meta_description+lead_paragraphs+prose_span+body_excerpt+time`	594 api	2	medium	yes
Schema	`name+headline+description+publisher+@type+block+dateModified+datePublished`	517 api	2	medium	no
AIPM	`title+primaryTopic+purpose+abstract+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	927 api	2	medium	yes

Execution chain · AIPM · 2 round(s)

Question: What is this page or business?
Planner: Planner mapped question `entity_what` on AIPM to minimal fields: title, primaryTopic.
Slice: title+primaryTopic+purpose+abstract+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.title: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar AIPM.primaryTopic: WordPres...
Actual input tokens: 927
LLM answer: This page is about WordPress GEO discovery with llms.txt and aims to publish discovery assets for AI visibility using AigeoRadar.
Evidence: AIPM.title: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar AIPM.primaryTopic: WordPress GEO discovery with llms.txt AIPM.purp...
Confidence: medium · matched yes

Round 1: 130 in-tok · score 0 · miss

Round 2: 797 in-tok · score 69 · match

Execution chain · HTML · 2 round(s)

Question: What is this page or business?
Planner: Planner mapped question `entity_what` on HTML to minimal fields: title, h1.
Slice: title+h1+meta_description+lead_paragraphs+prose_span+body_excerpt+time — HTML.title: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar — AigeoRadar HTML.h1: WordP...
Actual input tokens: 594
LLM answer: This page provides a guide for WordPress owners on how to publish llms.txt and related AI discovery files using AigeoRadar's one-click deploy feature for improv...
Evidence: HTML.title: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar — AigeoRadar HTML.h1: WordPress GEO: llms.txt, llms-full.txt, and A...
Confidence: medium · matched yes

Round 1: 143 in-tok · score 0 · miss

Round 2: 451 in-tok · score 58 · match

Execution chain · SCHEMA · 2 round(s)

Question: What is this page or business?
Planner: Planner mapped question `entity_what` on SCHEMA to minimal fields: name, headline, description.
Slice: name+headline+description+publisher+@type+block+dateModified+datePublished — SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRada...
Actual input tokens: 517
LLM answer: This page is about AigeoRadar, an AI visibility and GEO platform that provides a WordPress GEO publishing workflow and related services.
Evidence: SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar SCHEMA.description: Explains the Word...
Confidence: medium · matched no

Round 1: 168 in-tok · score 50 · miss

Round 2: 349 in-tok · score 50 · miss

HTML

sufficient

This page provides a guide for WordPress owners on how to publish llms.txt and related AI discovery files using AigeoRadar's one-click deploy feature for improved AI visibility.

score 58 · 24,284 chars context · 594 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

partial

This page is about AigeoRadar, an AI visibility and GEO platform that provides a WordPress GEO publishing workflow and related services.

score 50 · 15,430 chars context · 517 in-tokens

Schema was only partially aligned with gold from 15430 chars of context.

AIPM

sufficient

This page is about WordPress GEO discovery with llms.txt and aims to publish discovery assets for AI visibility using AigeoRadar.

score 69 · 37,462 chars context · 927 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q2 · Understanding · orientation

What is the main service or product offered?

Gold: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026

Gold source: html.h1|meta|prose · html_independent

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

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 521 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`h1+title+meta_description+lead_paragraphs+prose_span+body_excerpt+time`	598 api	2	medium	yes
Schema	`name+headline+description+publisher+@type+block+dateModified+datePublished`	521 api	2	low	no
AIPM	`primaryTopic+title+purpose+abstract+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	966 api	2	medium	yes

Execution chain · AIPM · 2 round(s)

Question: What is the main service or product offered?
Planner: Planner mapped question `main_service` on AIPM to minimal fields: primaryTopic, title, purpose.
Slice: primaryTopic+title+purpose+abstract+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.primaryTopic: WordPress GEO discovery with llms.txt AIPM.title: WordPress GEO: llms.txt and AI...
Actual input tokens: 966
LLM answer: The main service offered is the publishing of llms.txt and llms-full.txt on WordPress for AI discovery.
Evidence: AIPM.primaryTopic: WordPress GEO discovery with llms.txt AIPM.title: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar AIPM.purp...
Confidence: medium · matched yes

Round 1: 167 in-tok · score 50 · miss

Round 2: 799 in-tok · score 71 · match

Execution chain · HTML · 2 round(s)

Question: What is the main service or product offered?
Planner: Planner mapped question `main_service` on HTML to minimal fields: h1, title.
Slice: h1+title+meta_description+lead_paragraphs+prose_span+body_excerpt+time — HTML.h1: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026 HTML.title: WordPress GEO...
Actual input tokens: 598
LLM answer: The main service offered is a guide for WordPress owners to publish llms.txt and related AI discovery files using AigeoRadar's one-click deploy.
Evidence: HTML.h1: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026 HTML.title: WordPress GEO: llms.txt and AI Discovery Guide | Aige...
Confidence: medium · matched yes

Round 1: 145 in-tok · score 0 · miss

Round 2: 453 in-tok · score 58 · match

Execution chain · SCHEMA · 2 round(s)

Question: What is the main service or product offered?
Planner: Planner mapped question `main_service` on SCHEMA to minimal fields: name, headline, description.
Slice: name+headline+description+publisher+@type+block+dateModified+datePublished — SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRada...
Actual input tokens: 521
LLM answer: AigeoRadar offers an AI visibility and GEO (Generative Engine Optimization) platform.
Evidence: SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar SCHEMA.description: Explains the Word...
Confidence: low · matched no

Round 1: 170 in-tok · score 0 · miss

Round 2: 351 in-tok · score 24 · miss

HTML

sufficient

The main service offered is a guide for WordPress owners to publish llms.txt and related AI discovery files using AigeoRadar's one-click deploy.

score 58 · 24,284 chars context · 598 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

insufficient

AigeoRadar offers an AI visibility and GEO (Generative Engine Optimization) platform.

score 24 · 15,430 chars context · 521 in-tokens

Schema did not answer from 15430 chars of context — additional or different layer context needed.

AIPM

sufficient

The main service offered is the publishing of llms.txt and llms-full.txt on WordPress for AI discovery.

score 71 · 37,462 chars context · 966 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q3 · Understanding · orientation

Who is the publisher or brand?

Gold: AigeoRadar

Gold source: html.jsonld|title · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost AIPM · 103 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`title`	118 api	1	high	yes
Schema	`publisher+name`	111 api	1	high	yes
AIPM	`publisher`	103 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: AigeoRadar
Actual input tokens: 103
LLM answer: AigeoRadar.
Evidence: AIPM.publisher: AigeoRadar
Confidence: high · matched yes

Execution chain · HTML · 1 round(s)

Question: Who is the publisher or brand?
Planner: Planner mapped question `publisher` on HTML to minimal fields: title.
Slice: title — HTML.title: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar — AigeoRadar
Actual input tokens: 118
LLM answer: AigeoRadar.
Evidence: HTML.title: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar — AigeoRadar
Confidence: high · matched yes

Execution chain · SCHEMA · 1 round(s)

Question: Who is the publisher or brand?
Planner: Planner mapped question `publisher` on SCHEMA to minimal fields: publisher, name.
Slice: publisher+name — SCHEMA.publisher: AigeoRadar SCHEMA.name: AigeoRadar
Actual input tokens: 111
LLM answer: AigeoRadar.
Evidence: SCHEMA.publisher: AigeoRadar SCHEMA.name: AigeoRadar
Confidence: high · matched yes

HTML

sufficient

AigeoRadar.

score 100 · 24,284 chars context · 118 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

AigeoRadar.

score 100 · 15,430 chars context · 111 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

AigeoRadar.

score 100 · 37,462 chars context · 103 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q4 · Retrieval · depth

Where does this business operate or which city is mentioned?

Gold: UNKNOWN

Gold source: html.address|prose|jsonld · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 314 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`prose_span+lead_paragraphs+title+h1+meta_description+body_excerpt+time`	616 api	2	low	yes
Schema	`name+headline+description+publisher+@type+block+dateModified+datePublished`	314 api	2	low	yes
AIPM	`purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	801 api	2	low	yes

Execution chain · AIPM · 2 round(s)

Question: Where does this business operate or which city is mentioned?
Planner: Planner mapped question `geo_signal` on AIPM to minimal fields: geo, areaServed, address.
Slice: purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.purpose: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar for ChatGPT, Perplexit...
Actual input tokens: 801
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 801 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)

Question: Where does this business operate or which city is mentioned?
Planner: Planner mapped question `geo_signal` on HTML to minimal fields: prose_span, lead_paragraphs.
Slice: prose_span+lead_paragraphs+title+h1+meta_description+body_excerpt+time — HTML.prose_span: UNKNOWN HTML.lead_paragraphs: This guide shows WordPress owners how to publish llm...
Actual input tokens: 616
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched yes

Round 1: 180 in-tok · score 100 · match

Round 2: 436 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)

Question: Where does this business operate or which city is mentioned?
Planner: Planner mapped question `geo_signal` on SCHEMA to minimal fields: address, addressLocality, areaServed.
Slice: name+headline+description+publisher+@type+block+dateModified+datePublished — SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRada...
Actual input tokens: 314
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 314 in-tok · score 100 · match

HTML

sufficient

UNKNOWN

score 100 · 24,284 chars context · 616 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 15,430 chars context · 314 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 37,462 chars context · 801 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q5 · Understanding · orientation

Who is the intended audience of this page?

Gold: businesses

Gold source: html.prose|meta · html_independent

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

Measured retrieval cost (API tokens) · lowest cost AIPM · 163 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time`	644 api	2	low	no
Schema	`description+name+headline+publisher+@type+block+dateModified+datePublished`	499 api	2	low	no
AIPM	`audience+purpose`	163 api	1	high	yes

Execution chain · AIPM · 1 round(s)

Question: Who is the intended audience of this page?
Planner: Planner mapped question `audience` on AIPM to minimal fields: audience, purpose.
Slice: audience+purpose — AIPM.audience: ["businesses","website owners","WordPress site owners","SEO professionals","digital a...
Actual input tokens: 163
LLM answer: The intended audience of this page includes businesses, website owners, WordPress site owners, SEO professionals, digital agencies, B2B, SMBs, and agencies.
Evidence: AIPM.audience: ["businesses","website owners","WordPress site owners","SEO professionals","digital agencies","B2B","SMBs","agency"] AIPM.pu...
Confidence: high · matched yes

Execution chain · HTML · 2 round(s)

Question: Who is the intended audience of this page?
Planner: Planner mapped question `audience` on HTML to minimal fields: meta_description, lead_paragraphs.
Slice: meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time — HTML.meta_description: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GE...
Actual input tokens: 644
LLM answer: The intended audience of this page is WordPress owners.
Evidence: HTML.meta_description: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GEO deploy for ChatGPT, Perplexity, and Ge...
Confidence: low · matched no

Round 1: 209 in-tok · score 0 · miss

Round 2: 435 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)

Question: Who is the intended audience of this page?
Planner: Planner mapped question `audience` on SCHEMA to minimal fields: description, name.
Slice: description+name+headline+publisher+@type+block+dateModified+datePublished — SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship,...
Actual input tokens: 499
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 148 in-tok · score 0 · miss

Round 2: 351 in-tok · score 0 · miss

HTML

insufficient

The intended audience of this page is WordPress owners.

score 0 · 24,284 chars context · 644 in-tokens

HTML did not answer from 24284 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN.

score 0 · 15,430 chars context · 499 in-tokens

Schema did not answer from 15430 chars of context — additional or different layer context needed.

AIPM

sufficient

The intended audience of this page includes businesses, website owners, WordPress site owners, SEO professionals, digital agencies, B2B, SMBs, and agencies.

score 88 · 37,462 chars context · 163 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q6 · Understanding · orientation

What is the purpose of this page?

Gold: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GEO deploy for ChatGPT, Perplexity, and Gemini visibility.

Gold source: html.page_summary · html_independent

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

Measured retrieval cost (API tokens) · lowest cost AIPM · 129 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time`	673 api	2	medium	yes
Schema	`description+name+headline+publisher+@type+block+dateModified+datePublished`	458 api	2	low	no
AIPM	`purpose`	129 api	1	medium	yes

Execution chain · AIPM · 1 round(s)

Question: What is the purpose of this page?
Planner: Planner mapped question `purpose` on AIPM to minimal fields: purpose.
Slice: purpose — AIPM.purpose: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar for ChatGPT, Perplexit...
Actual input tokens: 129
LLM answer: The purpose of this page is to publish llms.txt and llms-full.txt on WordPress for visibility of ChatGPT, Perplexity, and Gemini.
Evidence: AIPM.purpose: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar for ChatGPT, Perplexity, and Gemini visibility.
Confidence: medium · matched yes

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: meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time — HTML.meta_description: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GE...
Actual input tokens: 673
LLM answer: The purpose of this page is to guide WordPress owners on how to publish llms.txt and related AI discovery files using AigeoRadar for improved AI visibility.
Evidence: HTML.meta_description: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GEO deploy for ChatGPT, Perplexity, and Ge...
Confidence: medium · matched yes

Round 1: 208 in-tok · score 53 · match

Round 2: 465 in-tok · score 70 · match

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, name.
Slice: description+name+headline+publisher+@type+block+dateModified+datePublished — SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship,...
Actual input tokens: 458
LLM answer: The purpose of this page is to explain the WordPress GEO publishing workflow and related topics.
Evidence: SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship, how Connector-based deploy works after c...
Confidence: low · matched no

Round 1: 147 in-tok · score 19 · miss

Round 2: 311 in-tok · score 19 · miss

HTML

sufficient

The purpose of this page is to guide WordPress owners on how to publish llms.txt and related AI discovery files using AigeoRadar for improved AI visibility.

score 70 · 24,284 chars context · 673 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

insufficient

The purpose of this page is to explain the WordPress GEO publishing workflow and related topics.

score 19 · 15,430 chars context · 458 in-tokens

Schema did not answer from 15430 chars of context — additional or different layer context needed.

AIPM

sufficient

The purpose of this page is to publish llms.txt and llms-full.txt on WordPress for visibility of ChatGPT, Perplexity, and Gemini.

score 78 · 37,462 chars context · 129 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q7 · Understanding · orientation

Summarize this page in one sentence.

Gold: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GEO deploy for ChatGPT, Perplexity, and Gemini visibility.

Gold source: html.page_summary · html_independent

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

Measured retrieval cost (API tokens) · lowest cost HTML · 209 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`meta_description+lead_paragraphs`	209 api	1	medium	yes
Schema	`description+name`	460 api	2	low	no
AIPM	`abstract+purpose+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	974 api	2	low	no

Execution chain · AIPM · 2 round(s)

Question: Summarize this page in one sentence.
Planner: Planner mapped question `abstract` on AIPM to minimal fields: abstract, purpose.
Slice: abstract+purpose+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.abstract: Explains the WordPress GEO publishing workflow: which discovery assets to ship, how C...
Actual input tokens: 974
LLM answer: The page explains the WordPress GEO publishing workflow using llms.txt and other discovery assets for AI visibility with AigeoRadar.
Evidence: AIPM.abstract: Explains the WordPress GEO publishing workflow: which discovery assets to ship, how Connector-based deploy works after crawl,...
Confidence: low · matched no

Round 1: 175 in-tok · score 35 · miss

Round 2: 799 in-tok · score 44 · miss

Execution chain · HTML · 1 round(s)

Question: Summarize this page in one sentence.
Planner: Planner mapped question `abstract` on HTML to minimal fields: meta_description, lead_paragraphs.
Slice: meta_description+lead_paragraphs — HTML.meta_description: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GE...
Actual input tokens: 209
LLM answer: This guide explains how WordPress owners can publish llms.txt and related AI discovery files using AigeoRadar for improved AI visibility.
Evidence: HTML.meta_description: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GEO deploy for ChatGPT, Perplexity, and Ge...
Confidence: medium · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: Summarize this page in one sentence.
Planner: Planner mapped question `abstract` on SCHEMA to minimal fields: description, name.
Slice: description+name — SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship,...
Actual input tokens: 460
LLM answer: The page explains the WordPress GEO publishing workflow, including discovery assets, Connector-based deployment, the Starter plan for one site, and the relevanc...
Evidence: SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship, how Connector-based deploy works after c...
Confidence: low · matched no

Round 1: 148 in-tok · score 20 · miss

Round 2: 312 in-tok · score 14 · miss

Root cause · Partial semantic match

Tighten primaryTopic/purpose/abstract so wording overlaps independent HTML gold.

HTML

sufficient

This guide explains how WordPress owners can publish llms.txt and related AI discovery files using AigeoRadar for improved AI visibility.

score 70 · 24,284 chars context · 209 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

insufficient

The page explains the WordPress GEO publishing workflow, including discovery assets, Connector-based deployment, the Starter plan for one site, and the relevance of Shopify GEO compared to WordPress.

score 20 · 15,430 chars context · 460 in-tokens

Schema did not answer from 15430 chars of context — additional or different layer context needed.

AIPM

partial

The page explains the WordPress GEO publishing workflow using llms.txt and other discovery assets for AI visibility with AigeoRadar.

score 44 · 37,462 chars context · 974 in-tokens

AIPM was only partially aligned with gold from 37462 chars of context.

Q8 · Understanding · orientation

What is the primary topic or headline of this page?

Gold: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026

Gold source: html.h1|title · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost HTML · 147 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`h1+title`	147 api	1	high	yes
Schema	`name+headline+description`	172 api	1	medium	yes
AIPM	`primaryTopic+title+purpose`	169 api	1	medium	yes

Execution chain · AIPM · 1 round(s)

Question: What is the primary topic or headline of this page?
Planner: Planner mapped question `primary_topic` on AIPM to minimal fields: primaryTopic, title, purpose.
Slice: primaryTopic+title+purpose — AIPM.primaryTopic: WordPress GEO discovery with llms.txt AIPM.title: WordPress GEO: llms.txt and AI...
Actual input tokens: 169
LLM answer: WordPress GEO discovery with llms.txt
Evidence: WordPress GEO discovery with llms.txt
Confidence: medium · matched yes

Execution chain · HTML · 1 round(s)

Question: What is the primary topic or headline of this page?
Planner: Planner mapped question `primary_topic` on HTML to minimal fields: h1, title.
Slice: h1+title — HTML.h1: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026 HTML.title: WordPress GEO...
Actual input tokens: 147
LLM answer: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026.
Evidence: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026
Confidence: high · matched yes

Execution chain · SCHEMA · 1 round(s)

Question: What is the primary topic or headline of this page?
Planner: Planner mapped question `primary_topic` on SCHEMA to minimal fields: name, headline, description.
Slice: name+headline+description — SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRada...
Actual input tokens: 172
LLM answer: The primary topic or headline of this page is "WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar."
Evidence: SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar SCHEMA.description: Explains the Word...
Confidence: medium · matched yes

HTML

sufficient

WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026.

score 100 · 24,284 chars context · 147 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

The primary topic or headline of this page is "WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar."

score 69 · 15,430 chars context · 172 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

WordPress GEO discovery with llms.txt

score 77 · 37,462 chars context · 169 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q9 · Metadata · orientation

What language is this page written in?

Gold: en

Gold source: html.lang · html_independent

Sufficient: HTML, Schema, AIPM

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`	101 api	1	high	yes
AIPM	`inLanguage`	102 api	1	high	yes

Execution chain · AIPM · 1 round(s)

Question: What language is this page written in?
Planner: Planner mapped question `language` on AIPM to minimal fields: inLanguage.
Slice: inLanguage — AIPM.inLanguage: en
Actual input tokens: 102
LLM answer: The page is written in English.
Evidence: AIPM.inLanguage: en
Confidence: high · matched yes

Execution chain · HTML · 1 round(s)

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

Execution chain · SCHEMA · 1 round(s)

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

HTML

sufficient

English

score 100 · 24,284 chars context · 100 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

The page is written in English.

score 88 · 15,430 chars context · 101 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

The page is written in English.

score 88 · 37,462 chars context · 102 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q10 · Retrieval · depth

What phone number or contact detail is listed?

Gold: UNKNOWN

Gold source: html.title|prose|jsonld.telephone · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 553 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`title+lead_paragraphs+h1+meta_description+prose_span+body_excerpt+time`	630 api	2	low	yes
Schema	`block+description+name+headline+publisher+@type+dateModified+datePublished`	553 api	2	low	yes
AIPM	`keyFacts+publisher+abstract+purpose+primaryTopic+title+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	1,034 api	2	low	yes

Execution chain · AIPM · 2 round(s)

Question: What phone number or contact detail is listed?
Planner: Planner mapped question `contact_phone` on AIPM to minimal fields: keyFacts, publisher, abstract.
Slice: keyFacts+publisher+abstract+purpose+primaryTopic+title+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: GEO (Generative Engine Optimization) is the layer after SEO that uses machine-readabl...
Actual input tokens: 1,034
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 235 in-tok · score 100 · match

Round 2: 799 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)

Question: What phone number or contact detail is listed?
Planner: Planner mapped question `contact_phone` on HTML to minimal fields: title, lead_paragraphs.
Slice: title+lead_paragraphs+h1+meta_description+prose_span+body_excerpt+time — HTML.title: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRadar — AigeoRadar HTML.lead_para...
Actual input tokens: 630
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched yes

Round 1: 196 in-tok · score 100 · match

Round 2: 434 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)

Question: What phone number or contact detail is listed?
Planner: Planner mapped question `contact_phone` on SCHEMA to minimal fields: telephone, block, description.
Slice: block+description+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.block: { "@context": "https://schema.org", "@graph": [ { "@type":...
Actual input tokens: 553
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 241 in-tok · score 100 · match

Round 2: 312 in-tok · score 100 · match

HTML

sufficient

UNKNOWN

score 100 · 24,284 chars context · 630 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 15,430 chars context · 553 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 37,462 chars context · 1,034 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q11 · Retrieval · depth

What physical address is listed for this business?

Gold: UNKNOWN

Gold source: html.prose|jsonld.address · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 312 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`prose_span+lead_paragraphs+title+h1+meta_description+body_excerpt+time`	612 api	2	low	yes
Schema	`name+headline+description+publisher+@type+block+dateModified+datePublished`	312 api	2	low	yes
AIPM	`purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	799 api	2	low	yes

Execution chain · AIPM · 2 round(s)

Question: What physical address is listed for this business?
Planner: Planner mapped question `address` on AIPM to minimal fields: address, geo, areaServed.
Slice: purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.purpose: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar for ChatGPT, Perplexit...
Actual input tokens: 799
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 799 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)

Question: What physical address is listed for this business?
Planner: Planner mapped question `address` on HTML to minimal fields: prose_span, lead_paragraphs.
Slice: prose_span+lead_paragraphs+title+h1+meta_description+body_excerpt+time — HTML.prose_span: UNKNOWN HTML.lead_paragraphs: This guide shows WordPress owners how to publish llm...
Actual input tokens: 612
LLM answer: UNKNOWN
Evidence: —
Confidence: low · matched yes

Round 1: 178 in-tok · score 100 · match

Round 2: 434 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)

Question: What physical address is listed for this business?
Planner: Planner mapped question `address` on SCHEMA to minimal fields: address, addressLocality, areaServed.
Slice: name+headline+description+publisher+@type+block+dateModified+datePublished — SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI Discovery Guide | AigeoRada...
Actual input tokens: 312
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 312 in-tok · score 100 · match

HTML

sufficient

UNKNOWN

score 100 · 24,284 chars context · 612 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 15,430 chars context · 312 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 37,462 chars context · 799 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q12 · Retrieval · depth

What are the opening hours or availability?

Gold: UNKNOWN

Gold source: html.prose|jsonld.openingHours · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 551 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time`	768 api	2	low	yes
Schema	`block+description+name+headline+publisher+@type+dateModified+datePublished`	551 api	2	low	yes
AIPM	`keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	1,057 api	2	low	yes

Execution chain · AIPM · 2 round(s)

Question: What are the opening hours or availability?
Planner: Planner mapped question `hours` on AIPM to minimal fields: keyFacts, abstract, purpose.
Slice: keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: GEO (Generative Engine Optimization) is the layer after SEO that uses machine-readabl...
Actual input tokens: 1,057
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 259 in-tok · score 100 · match

Round 2: 798 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)

Question: What are the opening hours or availability?
Planner: Planner mapped question `hours` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI disco...
Actual input tokens: 768
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 335 in-tok · score 100 · match

Round 2: 433 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)

Question: What are the opening hours or availability?
Planner: Planner mapped question `hours` on SCHEMA to minimal fields: openingHours, block, description.
Slice: block+description+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.block: { "@context": "https://schema.org", "@graph": [ { "@type":...
Actual input tokens: 551
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 240 in-tok · score 100 · match

Round 2: 311 in-tok · score 100 · match

HTML

sufficient

UNKNOWN.

score 100 · 24,284 chars context · 768 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 15,430 chars context · 551 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 37,462 chars context · 1,057 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q13 · Retrieval · depth

Is pricing or package information mentioned, and what is it?

Gold: UNKNOWN

Gold source: html.prose|jsonld.offers · html_independent

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

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 559 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time`	776 api	2	low	no
Schema	`block+description+name+headline+publisher+@type+dateModified+datePublished`	559 api	2	low	yes
AIPM	`keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	1,030 api	2	low	yes

Execution chain · AIPM · 2 round(s)

Question: Is pricing or package information mentioned, and what is it?
Planner: Planner mapped question `pricing` on AIPM to minimal fields: keyFacts, sections, abstract.
Slice: keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: GEO (Generative Engine Optimization) is the layer after SEO that uses machine-readabl...
Actual input tokens: 1,030
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 228 in-tok · score 100 · match

Round 2: 802 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)

Question: Is pricing or package information mentioned, and what is it?
Planner: Planner mapped question `pricing` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI disco...
Actual input tokens: 776
LLM answer: Yes, the starter plan is $9.90 per month and includes one WordPress site with plugin sync.
Evidence: HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI discovery files, and how AigeoRadar one-click...
Confidence: low · matched no

Round 1: 339 in-tok · score 0 · miss

Round 2: 437 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)

Question: Is pricing or package information mentioned, and what is it?
Planner: Planner mapped question `pricing` on SCHEMA to minimal fields: offers, price, block, description.
Slice: block+description+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.block: { "@context": "https://schema.org", "@graph": [ { "@type":...
Actual input tokens: 559
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 244 in-tok · score 100 · match

Round 2: 315 in-tok · score 100 · match

HTML

insufficient

Yes, the starter plan is $9.90 per month and includes one WordPress site with plugin sync.

score 0 · 24,284 chars context · 776 in-tokens

HTML did not answer from 24284 chars of context — additional or different layer context needed.

Schema

sufficient

UNKNOWN.

score 100 · 15,430 chars context · 559 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 37,462 chars context · 1,030 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q14 · Retrieval · depth

What makes this offer different or stand out?

Gold: UNKNOWN

Gold source: html.prose|meta · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 562 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time`	770 api	2	low	yes
Schema	`description+block+name+headline+publisher+@type+dateModified+datePublished`	562 api	2	low	yes
AIPM	`keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	1,059 api	2	low	yes

Execution chain · AIPM · 2 round(s)

Question: What makes this offer different or stand out?
Planner: Planner mapped question `differentiator` on AIPM to minimal fields: keyFacts, abstract, purpose.
Slice: keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: GEO (Generative Engine Optimization) is the layer after SEO that uses machine-readabl...
Actual input tokens: 1,059
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 260 in-tok · score 100 · match

Round 2: 799 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)

Question: What makes this offer different or stand out?
Planner: Planner mapped question `differentiator` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI disco...
Actual input tokens: 770
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 336 in-tok · score 100 · match

Round 2: 434 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)

Question: What makes this offer different or stand out?
Planner: Planner mapped question `differentiator` on SCHEMA to minimal fields: description, block, name.
Slice: description+block+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship,...
Actual input tokens: 562
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 250 in-tok · score 100 · match

Round 2: 312 in-tok · score 100 · match

HTML

sufficient

UNKNOWN.

score 100 · 24,284 chars context · 770 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 15,430 chars context · 562 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 37,462 chars context · 1,059 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q15 · Evidence · depth

What trust signals are present (reviews, certificates, guarantees, years of experience)?

Gold: UNKNOWN

Gold source: html.prose|jsonld · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 576 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time`	784 api	2	low	yes
Schema	`description+block+name+headline+publisher+@type+dateModified+datePublished`	576 api	2	low	yes
AIPM	`keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	1,073 api	2	low	yes

Execution chain · AIPM · 2 round(s)

Question: What trust signals are present (reviews, certificates, guarantees, years of experience)?
Planner: Planner mapped question `trust` on AIPM to minimal fields: keyFacts, abstract, purpose.
Slice: keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: GEO (Generative Engine Optimization) is the layer after SEO that uses machine-readabl...
Actual input tokens: 1,073
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 267 in-tok · score 100 · match

Round 2: 806 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)

Question: What trust signals are present (reviews, certificates, guarantees, years of experience)?
Planner: Planner mapped question `trust` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI disco...
Actual input tokens: 784
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 343 in-tok · score 100 · match

Round 2: 441 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)

Question: What trust signals are present (reviews, certificates, guarantees, years of experience)?
Planner: Planner mapped question `trust` on SCHEMA to minimal fields: description, block, name.
Slice: description+block+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship,...
Actual input tokens: 576
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 257 in-tok · score 100 · match

Round 2: 319 in-tok · score 100 · match

HTML

sufficient

UNKNOWN.

score 100 · 24,284 chars context · 784 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 15,430 chars context · 576 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 37,462 chars context · 1,073 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q16 · Retrieval · depth

What frequently asked questions or FAQ topics are covered?

Gold: What steps can I take to monitor my GEO score on a day-to-day basis?; What common mistakes should I avoid while using AigeoRadar?; What are the plan limits for AigeoRadar?

Gold source: html.faq|jsonld.FAQPage · html_independent

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

Measured retrieval cost (API tokens) · lowest cost HTML · 378 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+body_excerpt+prose_span`	378 api	1	medium	yes
Schema	`block+description+name+headline+publisher+@type+dateModified+datePublished`	633 api	2	low	no
AIPM	`faqEntity+keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate`	1,234 api	2	low	no

Execution chain · AIPM · 2 round(s)

Question: What frequently asked questions or FAQ topics are covered?
Planner: Planner mapped question `faq` on AIPM to minimal fields: faqEntity, keyFacts.
Slice: faqEntity+keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate — AIPM.faqEntity: [{"name":"What files should I publish for WordPress GEO?","@type":"Question","accept...
Actual input tokens: 1,234
LLM answer: The FAQ topics covered include publishing files for WordPress GEO, deploying AI discovery files to WordPress with AigeoRadar, the importance of llms-full.txt, a...
Evidence: AIPM.faqEntity: [{"name":"What files should I publish for WordPress GEO?","@type":"Question","acceptedAnswer":{"text":"Publish llms.txt, llm...
Confidence: low · matched no

Round 1: 434 in-tok · score 11 · miss

Round 2: 800 in-tok · score 11 · miss

Execution chain · HTML · 1 round(s)

Question: What frequently asked questions or FAQ topics are covered?
Planner: Planner mapped question `faq` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
Slice: lead_paragraphs+body_excerpt+prose_span — HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI disco...
Actual input tokens: 378
LLM answer: The FAQ topics covered include monitoring GEO score, common mistakes to avoid while using AigeoRadar, and plan limits for AigeoRadar.
Evidence: HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI discovery files, and how AigeoRadar one-click...
Confidence: medium · matched yes

Execution chain · SCHEMA · 2 round(s)

Question: What frequently asked questions or FAQ topics are covered?
Planner: Planner mapped question `faq` on SCHEMA to minimal fields: block, description.
Slice: block+description+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.block: { "@context": "https://schema.org", "@graph": [ { "@type":...
Actual input tokens: 633
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 281 in-tok · score 0 · miss

Round 2: 352 in-tok · score 0 · miss

Root cause · Depth gap (expected)

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

HTML

sufficient

The FAQ topics covered include monitoring GEO score, common mistakes to avoid while using AigeoRadar, and plan limits for AigeoRadar.

score 61 · 24,284 chars context · 378 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN.

score 0 · 15,430 chars context · 633 in-tokens

Schema did not answer from 15430 chars of context — additional or different layer context needed.

AIPM

insufficient

The FAQ topics covered include publishing files for WordPress GEO, deploying AI discovery files to WordPress with AigeoRadar, the importance of llms-full.txt, and AigeoRadar's support for Shopify.

score 11 · 37,462 chars context · 1,234 in-tokens

AIPM did not answer from 37462 chars of context — additional or different layer context needed.

Q17 · Retrieval · depth

What action should the visitor take (call, buy, contact, book)?

Gold: UNKNOWN

Gold source: html.cta|prose · html_independent

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

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 574 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time`	782 api	2	low	no
Schema	`description+block+name+headline+publisher+@type+dateModified+datePublished`	574 api	2	low	yes
AIPM	`purpose+abstract+keyFacts+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity`	1,071 api	2	low	yes

Execution chain · AIPM · 2 round(s)

Question: What action should the visitor take (call, buy, contact, book)?
Planner: Planner mapped question `cta` on AIPM to minimal fields: purpose, abstract, keyFacts.
Slice: purpose+abstract+keyFacts+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.purpose: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar for ChatGPT, Perplexit...
Actual input tokens: 1,071
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 266 in-tok · score 100 · match

Round 2: 805 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)

Question: What action should the visitor take (call, buy, contact, book)?
Planner: Planner mapped question `cta` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI disco...
Actual input tokens: 782
LLM answer: Enter your domain on aigeoradar.com for an instant AI visibility preview.
Evidence: Enter your domain on aigeoradar.com for an instant AI visibility preview. No credit card required.
Confidence: low · matched no

Round 1: 342 in-tok · score 0 · miss

Round 2: 440 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)

Question: What action should the visitor take (call, buy, contact, book)?
Planner: Planner mapped question `cta` on SCHEMA to minimal fields: description, block, name.
Slice: description+block+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship,...
Actual input tokens: 574
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched yes

Round 1: 256 in-tok · score 100 · match

Round 2: 318 in-tok · score 100 · match

HTML

insufficient

Enter your domain on aigeoradar.com for an instant AI visibility preview.

score 0 · 24,284 chars context · 782 in-tokens

HTML did not answer from 24284 chars of context — additional or different layer context needed.

Schema

sufficient

UNKNOWN.

score 100 · 15,430 chars context · 574 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 37,462 chars context · 1,071 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q18 · Retrieval · depth

What related products, services, or pages are mentioned?

Gold: Features, What is AigeoRadar?, Pricing

Gold source: html.nav|prose · html_independent

No layer provided a sufficient answer from its context alone.

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 566 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time`	792 api	2	low	no
Schema	`description+block+name+headline+publisher+@type+dateModified+datePublished`	566 api	2	low	no
AIPM	`relatedPages+keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent+dateModified+datePublished+reviewDate+faqEntity`	1,141 api	2	low	no

Execution chain · AIPM · 2 round(s)

Question: What related products, services, or pages are mentioned?
Planner: Planner mapped question `related` on AIPM to minimal fields: relatedPages, sections, keyFacts.
Slice: relatedPages+keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent+dateModified+datePublished+reviewDate+faqEntity — AIPM.relatedPages: WordPress plugin setup guide — https://aigeoradar.com/help/wordpress-plugin-setup...
Actual input tokens: 1,141
LLM answer: The related products, services, or pages mentioned are the WordPress plugin setup guide, AigeoRadar Connector WordPress GEO plugin, AI Page Manifest (AIPM) spec...
Evidence: AIPM.relatedPages: WordPress plugin setup guide — https://aigeoradar.com/help/wordpress-plugin-setup AigeoRadar Connector WordPress GEO plug...
Confidence: low · matched no

Round 1: 340 in-tok · score 7 · miss

Round 2: 801 in-tok · score 7 · miss

Execution chain · HTML · 2 round(s)

Question: What related products, services, or pages are mentioned?
Planner: Planner mapped question `related` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.txt and related AI disco...
Actual input tokens: 792
LLM answer: AigeoRadar one-click deploy, WordPress plugin, and Shopify app for GEO discovery deploy are mentioned.
Evidence: This guide shows WordPress owners how to publish llms.txt and related AI discovery files, and how AigeoRadar one-click deploy works.
Confidence: low · matched no

Round 1: 347 in-tok · score 12 · miss

Round 2: 445 in-tok · score 14 · miss

Execution chain · SCHEMA · 2 round(s)

Question: What related products, services, or pages are mentioned?
Planner: Planner mapped question `related` on SCHEMA to minimal fields: description, block, name.
Slice: description+block+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.description: Explains the WordPress GEO publishing workflow: which discovery assets to ship,...
Actual input tokens: 566
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 252 in-tok · score 0 · miss

Round 2: 314 in-tok · score 0 · miss

Root cause · Depth gap (expected)

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

HTML

insufficient

AigeoRadar one-click deploy, WordPress plugin, and Shopify app for GEO discovery deploy are mentioned.

score 14 · 24,284 chars context · 792 in-tokens

HTML did not answer from 24284 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN.

score 0 · 15,430 chars context · 566 in-tokens

Schema did not answer from 15430 chars of context — additional or different layer context needed.

AIPM

insufficient

The related products, services, or pages mentioned are the WordPress plugin setup guide, AigeoRadar Connector WordPress GEO plugin, AI Page Manifest (AIPM) specification, Free AI Bot Checker vs robots.txt, Shopify GEO app, and AigeoRadar llms-full.txt.

score 7 · 37,462 chars context · 1,141 in-tokens

AIPM did not answer from 37462 chars of context — additional or different layer context needed.

Q19 · Metadata · orientation

When was this page published or last updated?

Gold: 2026-07-30

Gold source: html.time|jsonld.dateModified · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost AIPM · 134 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`time+lead_paragraphs+body_excerpt`	339 api	1	high	yes
Schema	`dateModified+datePublished+block`	260 api	1	high	yes
AIPM	`dateModified+datePublished+reviewDate`	134 api	1	high	yes

Execution chain · AIPM · 1 round(s)

Question: When was this page published or last updated?
Planner: Planner mapped question `freshness` on AIPM to minimal fields: dateModified, datePublished, reviewDate.
Slice: dateModified+datePublished+reviewDate — AIPM.dateModified: 2026-07-30 AIPM.datePublished: 2026-07-30 AIPM.reviewDate: 2026-07-30
Actual input tokens: 134
LLM answer: The page was published and last updated on 2026-07-30.
Evidence: AIPM.dateModified: 2026-07-30 AIPM.datePublished: 2026-07-30 AIPM.reviewDate: 2026-07-30
Confidence: high · matched yes

Execution chain · HTML · 1 round(s)

Question: When was this page published or last updated?
Planner: Planner mapped question `freshness` on HTML to minimal fields: time, lead_paragraphs, body_excerpt.
Slice: time+lead_paragraphs+body_excerpt — HTML.time: 2026-07-30 HTML.lead_paragraphs: This guide shows WordPress owners how to publish llms.t...
Actual input tokens: 339
LLM answer: 2026-07-30
Evidence: 2026-07-30
Confidence: high · matched yes

Execution chain · SCHEMA · 1 round(s)

Question: When was this page published or last updated?
Planner: Planner mapped question `freshness` on SCHEMA to minimal fields: dateModified, datePublished, block.
Slice: dateModified+datePublished+block — SCHEMA.dateModified: 2026-07-30 SCHEMA.datePublished: 2026-07-30 SCHEMA.block: { "@context": "...
Actual input tokens: 260
LLM answer: The page was published and last updated on 2026-07-30.
Evidence: SCHEMA.dateModified: 2026-07-30 SCHEMA.datePublished: 2026-07-30 SCHEMA.block: { "@context": "https://schema.org", "@graph": [...
Confidence: high · matched yes

HTML

sufficient

2026-07-30

score 100 · 24,284 chars context · 339 in-tokens

HTML answered using 24284 chars of layer context (minimum fed this run).

Schema

sufficient

The page was published and last updated on 2026-07-30.

score 88 · 15,430 chars context · 260 in-tokens

Schema answered using 15430 chars of layer context (minimum fed this run).

AIPM

sufficient

The page was published and last updated on 2026-07-30.

score 88 · 37,462 chars context · 134 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

Q20 · Metadata · orientation

What kind of page is this (article, product, local service, company page, FAQ, other)?

Gold: blog

Gold source: html.heuristic|jsonld.@type · html_independent

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

Measured retrieval cost (API tokens) · lowest cost AIPM · 124 input tokens

Layer	Planner fields	Input tokens	Rounds	Confidence	OK?
HTML	`meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time`	667 api	2	low	no
Schema	`@type+name+headline+description+publisher+block+dateModified+datePublished`	477 api	2	low	no
AIPM	`contentIntent+pageType`	124 api	1	high	yes

Execution chain · AIPM · 1 round(s)

Question: What kind of page is this (article, product, local service, company page, FAQ, other)?
Planner: Planner mapped question `page_kind` on AIPM to minimal fields: contentIntent, pageType.
Slice: contentIntent+pageType — AIPM.contentIntent: informational AIPM.pageType: blog
Actual input tokens: 124
LLM answer: blog
Evidence: blog
Confidence: high · matched yes

Execution chain · HTML · 2 round(s)

Question: What kind of page is this (article, product, local service, company page, FAQ, other)?
Planner: Planner mapped question `page_kind` on HTML to minimal fields: meta_description, lead_paragraphs.
Slice: meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time — HTML.meta_description: Publish llms.txt and llms-full.txt on WordPress with AigeoRadar. One-click GE...
Actual input tokens: 667
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 221 in-tok · score 0 · miss

Round 2: 446 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)

Question: What kind of page is this (article, product, local service, company page, FAQ, other)?
Planner: Planner mapped question `page_kind` on SCHEMA to minimal fields: @type.
Slice: @type+name+headline+description+publisher+block+dateModified+datePublished — SCHEMA.@type: Organization SCHEMA.name: AigeoRadar SCHEMA.headline: WordPress GEO: llms.txt and AI...
Actual input tokens: 477
LLM answer: UNKNOWN.
Evidence: —
Confidence: low · matched no

Round 1: 114 in-tok · score 0 · miss

Round 2: 363 in-tok · score 0 · miss

HTML

insufficient

UNKNOWN.

score 0 · 24,284 chars context · 667 in-tokens

HTML did not answer from 24284 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN.

score 0 · 15,430 chars context · 477 in-tokens

Schema did not answer from 15430 chars of context — additional or different layer context needed.

AIPM

sufficient

blog

score 100 · 37,462 chars context · 124 in-tokens

AIPM answered using 37462 chars of layer context (minimum fed this run).

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 · Thu, Jul 30, 2026 11:49 PM · aipm_benchmark_score_v10

Per-question context chain across layers.

Post on X LinkedIn WhatsApp

About the lab →

Question outcomes

Semantic Redundancy · 25%

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 this page or business?

What is the main service or product offered?

Who is the publisher or brand?

Where does this business operate or which city is mentioned?

Who is the intended audience of this page?

What is the purpose of this page?

Summarize this page in one sentence.

What is the primary topic or headline of this page?

What language is this page written in?

What phone number or contact detail is listed?

What physical address is listed for this business?

What are the opening hours or availability?

Is pricing or package information mentioned, and what is it?

What makes this offer different or stand out?

What trust signals are present (reviews, certificates, guarantees, years of experience)?

What frequently asked questions or FAQ topics are covered?

What action should the visitor take (call, buy, contact, book)?

What related products, services, or pages are mentioned?

When was this page published or last updated?

What kind of page is this (article, product, local service, company page, FAQ, other)?

Methodology

Share