AigeoRadar

AigeoRadar · AI Context Benchmark

AI Context Benchmark

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

20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)

https://aigeoradar.com/blog/20-best-ai-visibility-tools-compared-in-2026-complete-geo-software-guide

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

Of 20 questions: lowest measured retrieval cost among sufficient layers — HTML 5 · Schema 9 · AIPM 4 · multi-layer 0 · unanswered 2. Descriptive counts only; no overall ranking.

Of 20 questions: lowest measured retrieval cost among sufficient layers — HTML 5 · Schema 9 · AIPM 4 · multi-layer 0 · unanswered 2. 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 75% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.

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
2026-08
Run id
8a1eeb1e-af33-4ea9-9d23-f2135d4bf9f1

Question outcomes

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

5

Lowest cost: HTML

9

Lowest cost: Schema

4

Lowest cost: AIPM

0

Multi-layer

2

Unanswered

Manifest design

Semantic Redundancy · 75%

Semantic Redundancy 75% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.

  • →Merge or differentiate `purpose` and `primaryTopic` (75% overlap).
Field A Field B Overlap
purpose primaryTopic 75%

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 · 19,273 chars
Schema · 13,674 chars
AIPM · 23,573 chars

Routing helper (secondary)

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

Card-first retrieval is roughly token-neutral vs HTML-always on this pack.

Orientation pack

10 questions · all layers scored

  • HTML 8/10
  • Schema 7/10
  • AIPM 9/10

Depth pack

10 questions · all layers scored

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

Full-context pack metrics (secondary)

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

HTML

16/20 matched

9,683 full-pack tokens

Schema

14/20 matched

8,533 full-pack tokens

AIPM

16/20 matched

10,489 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) 16/20 14/20 16/20
Context size 19,273 chars 13,674 chars 23,573 chars
Total tokens 9,683 8,533 10,489
Tokens / correct answer 605 610 656
Est. cost / correct answer $0.000098 $0.000100 $0.000106
Matched per 1k tokens 1.652 1.641 1.525
Median latency 1,567 ms 1,350 ms 1,140 ms
Est. cost (USD) $0.00157 $0.00141 $0.00169

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 99.3
  • AIPM 92.3

Understanding

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

  • HTML 85.7
  • Schema 85.7
  • AIPM 85.7

Retrieval

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

  • HTML 77.8
  • Schema 66.7
  • AIPM 66.7

Evidence

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

  • HTML 70.4
  • Schema 61.8
  • AIPM 73.4

Metadata

Language, page kind, and freshness from page signals.

  • HTML 66.7
  • Schema 33.3
  • AIPM 100

Compression

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

  • HTML 100
  • Schema 99.3
  • AIPM 92.3

Coverage map

AIPM matched 16 question(s) (alone on Q5, Q20); HTML matched 16. HTML/Schema (or a gap) still needed on Q6, Q14, Q16, Q17. No layer matched gold on Q14, Q17. Read this as complementary coverage — AIPM orients agents cheaply; HTML supplies depth when the sidecar cannot. HTML 16/20 matched (≈605 tok/match). Schema 14/20 matched (≈610 tok/match). AIPM 16/20 matched (≈656 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, Q7, Q8, Q9, Q10, Q11, Q12, Q13, Q15, Q18, Q19, Q20

Alone: Q5, Q20

AIPM insufficient

Q6, Q14, Q16, Q17

HTML/Schema needed or all layers missed

Unanswered by all

Q14, Q17

HTML layer

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

Context fed: 19,273 chars

Tokens: 9,683 · median 1,567 ms

Matched this pack: 16/20

Stronger on

Understanding (85.7) · Retrieval (77.8) · Evidence (70.4) · 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: 13,674 chars

Tokens: 8,533 · median 1,350 ms

Matched this pack: 14/20

Stronger on

Understanding (85.7) · Compression (99.3) · Answer Efficiency (99.3)

Weaker on

Metadata (33.3)

AIPM layer

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

Context fed: 23,573 chars

Tokens: 10,489 · median 1,140 ms

Matched this pack: 16/20

Stronger on

Understanding (85.7) · Metadata (100) · Evidence (73.4) · Compression (92.3) · Answer Efficiency (92.3)

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: 10,489 tok · $0.00169.
Deep content / research (prose facts, process detail) HTML (with optional machine orientation) HTML pack: 9,683 tok · $0.00157. Use when depth needs body prose.
Structured entity pulls (org, location, typed fields) Schema.org Schema pack: 8,533 tok · $0.00141. Dense JSON-LD tends to score well here.

Findings

  • —Of 20 questions: lowest measured retrieval cost among sufficient layers — HTML 5 · Schema 9 · AIPM 4 · multi-layer 0 · unanswered 2. Descriptive counts only; no overall ranking.
  • —Semantic Redundancy 75% — the manifest repeats the same ideas across fields. This inflates structural size without helping per-question retrieval.
  • —Manifest design: Merge or differentiate `purpose` and `primaryTopic` (75% overlap).
  • —Structural size is secondary. A larger AIPM is not a failure if per-question retrieval stays tiny — check Semantic Redundancy instead.
  • —AIPM matched 16 question(s) (alone on Q5, Q20); HTML matched 16. HTML/Schema (or a gap) still needed on Q6, Q14, Q16, Q17. No layer matched gold on Q14, Q17. Read this as complementary coverage — AIPM orients agents cheaply; HTML supplies depth when the sidecar cannot. HTML 16/20 matched (≈605 tok/match). Schema 14/20 matched (≈610 tok/match). AIPM 16/20 matched (≈656 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: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)

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

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost HTML · 138 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML title+h1 138 api 1 medium yes
Schema name+headline+description 180 api 1 medium yes
AIPM title+primaryTopic+purpose+abstract+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 710 api 2 medium yes
Execution chain · AIPM · 2 round(s)
  1. Question: What is this page or business?
  2. Planner: Planner mapped question `entity_what` on AIPM to minimal fields: title, primaryTopic.
  3. Slice: title+primaryTopic+purpose+abstract+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.title: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) AIPM.primary...
  4. Actual input tokens: 710
  5. LLM answer: This page is a guide comparing the best AI visibility tools and GEO platforms in 2026.
  6. Evidence: AIPM.title: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) AIPM.primaryTopic: 20 Best AI Visibility Tools Compa...
  7. Confidence: medium · matched yes

Round 1: 136 in-tok · score 0 · miss

Round 2: 574 in-tok · score 70 · match

Execution chain · HTML · 1 round(s)
  1. Question: What is this page or business?
  2. Planner: Planner mapped question `entity_what` on HTML to minimal fields: title, h1.
  3. Slice: title+h1 — HTML.title: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) — AigeoRadar...
  4. Actual input tokens: 138
  5. LLM answer: This page is a guide comparing the 20 best AI visibility tools in 2026.
  6. Evidence: HTML.title: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) — AigeoRadar HTML.h1: 20 Best AI Visibility Tools Co...
  7. Confidence: medium · matched yes
Execution chain · SCHEMA · 1 round(s)
  1. Question: What is this page or business?
  2. Planner: Planner mapped question `entity_what` on SCHEMA to minimal fields: name, headline, description.
  3. Slice: name+headline+description — SCHEMA.name: AigeoRadar SCHEMA.headline: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO...
  4. Actual input tokens: 180
  5. LLM answer: This page compares the best AI visibility tools, GEO platforms, and AI SEO software in 2026, including AigeoRadar.
  6. Evidence: SCHEMA.name: AigeoRadar SCHEMA.headline: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) SCHEMA.description: Co...
  7. Confidence: medium · matched yes

HTML

sufficient

This page is a guide comparing the 20 best AI visibility tools in 2026.

score 74 · 19,273 chars context · 138 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

This page compares the best AI visibility tools, GEO platforms, and AI SEO software in 2026, including AigeoRadar.

score 61 · 13,674 chars context · 180 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

This page is a guide comparing the best AI visibility tools and GEO platforms in 2026.

score 70 · 23,573 chars context · 710 in-tokens

AIPM answered using 23573 chars of layer context (minimum fed this run).

Q2 · Understanding · orientation

What is the main service or product offered?

Gold: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)

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

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost HTML · 525 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML h1+title+meta_description+lead_paragraphs+prose_span+body_excerpt+time 525 api 2 low yes
Schema name+headline+description 545 api 2 low yes
AIPM primaryTopic+title+purpose+abstract+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 740 api 2 medium yes
Execution chain · AIPM · 2 round(s)
  1. Question: What is the main service or product offered?
  2. Planner: Planner mapped question `main_service` on AIPM to minimal fields: primaryTopic, title, purpose.
  3. Slice: primaryTopic+title+purpose+abstract+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.primaryTopic: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) AIPM....
  4. Actual input tokens: 740
  5. LLM answer: The main service offered is a comparison of the best AI Visibility tools, GEO platforms, and AI SEO software in 2026.
  6. Evidence: AIPM.primaryTopic: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) AIPM.title: 20 Best AI Visibility Tools Compa...
  7. Confidence: medium · matched yes

Round 1: 164 in-tok · score 0 · miss

Round 2: 576 in-tok · score 61 · match

Execution chain · HTML · 2 round(s)
  1. Question: What is the main service or product offered?
  2. Planner: Planner mapped question `main_service` on HTML to minimal fields: h1, title.
  3. Slice: h1+title+meta_description+lead_paragraphs+prose_span+body_excerpt+time — HTML.h1: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) HTML.title: 20...
  4. Actual input tokens: 525
  5. LLM answer: The main service offered is a comparison of AI Visibility tools, GEO platforms, and AI SEO software.
  6. Evidence: HTML.h1: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) HTML.title: 20 Best AI Visibility Tools Compared in 202...
  7. Confidence: low · matched yes

Round 1: 140 in-tok · score 0 · miss

Round 2: 385 in-tok · score 48 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: What is the main service or product offered?
  2. Planner: Planner mapped question `main_service` on SCHEMA to minimal fields: name, headline, description.
  3. Slice: name+headline+description — SCHEMA.name: AigeoRadar SCHEMA.headline: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO...
  4. Actual input tokens: 545
  5. LLM answer: The main service offered is a comparison of AI visibility tools, GEO platforms, and AI SEO software.
  6. Evidence: SCHEMA.name: AigeoRadar SCHEMA.headline: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) SCHEMA.description: Co...
  7. Confidence: low · matched yes

Round 1: 182 in-tok · score 48 · match

Round 2: 363 in-tok · score 25 · miss

HTML

sufficient

The main service offered is a comparison of AI Visibility tools, GEO platforms, and AI SEO software.

score 48 · 19,273 chars context · 525 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

The main service offered is a comparison of AI visibility tools, GEO platforms, and AI SEO software.

score 48 · 13,674 chars context · 545 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

The main service offered is a comparison of the best AI Visibility tools, GEO platforms, and AI SEO software in 2026.

score 61 · 23,573 chars context · 740 in-tokens

AIPM answered using 23573 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+h1+meta_description+lead_paragraphs+prose_span+body_excerpt+time 490 api 2 high yes
Schema publisher+name 111 api 1 high yes
AIPM publisher 103 api 1 high yes
Execution chain · AIPM · 1 round(s)
  1. Question: Who is the publisher or brand?
  2. Planner: Planner mapped question `publisher` on AIPM to minimal fields: publisher.
  3. Slice: publisher — AIPM.publisher: AigeoRadar
  4. Actual input tokens: 103
  5. LLM answer: AigeoRadar
  6. Evidence: AigeoRadar
  7. Confidence: high · matched yes
Execution chain · HTML · 2 round(s)
  1. Question: Who is the publisher or brand?
  2. Planner: Planner mapped question `publisher` on HTML to minimal fields: title.
  3. Slice: title+h1+meta_description+lead_paragraphs+prose_span+body_excerpt+time — HTML.title: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) — AigeoRadar...
  4. Actual input tokens: 490
  5. LLM answer: AigeoRadar.
  6. Evidence: HTML.title: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) — AigeoRadar HTML.h1: 20 Best AI Visibility Tools Co...
  7. Confidence: high · matched yes

Round 1: 118 in-tok · score 0 · miss

Round 2: 372 in-tok · score 100 · match

Execution chain · SCHEMA · 1 round(s)
  1. Question: Who is the publisher or brand?
  2. Planner: Planner mapped question `publisher` on SCHEMA to minimal fields: publisher, name.
  3. Slice: publisher+name — SCHEMA.publisher: AigeoRadar SCHEMA.name: AigeoRadar
  4. Actual input tokens: 111
  5. LLM answer: AigeoRadar.
  6. Evidence: SCHEMA.publisher: AigeoRadar SCHEMA.name: AigeoRadar
  7. Confidence: high · matched yes

HTML

sufficient

AigeoRadar.

score 100 · 19,273 chars context · 490 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

AigeoRadar.

score 100 · 13,674 chars context · 111 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

AigeoRadar

score 100 · 23,573 chars context · 103 in-tokens

AIPM answered using 23573 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 · 326 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML prose_span+lead_paragraphs+title+h1+meta_description+body_excerpt+time 536 api 2 low yes
Schema name+headline+description+publisher+@type+block+dateModified+datePublished 326 api 2 low yes
AIPM purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 578 api 2 low yes
Execution chain · AIPM · 2 round(s)
  1. Question: Where does this business operate or which city is mentioned?
  2. Planner: Planner mapped question `geo_signal` on AIPM to minimal fields: geo, areaServed, address.
  3. Slice: purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.purpose: Help readers understand 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Sof...
  4. Actual input tokens: 578
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 578 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)
  1. Question: Where does this business operate or which city is mentioned?
  2. Planner: Planner mapped question `geo_signal` on HTML to minimal fields: prose_span, lead_paragraphs.
  3. Slice: prose_span+lead_paragraphs+title+h1+meta_description+body_excerpt+time — HTML.prose_span: UNKNOWN HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms,...
  4. Actual input tokens: 536
  5. LLM answer: UNKNOWN
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 163 in-tok · score 100 · match

Round 2: 373 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: Where does this business operate or which city is mentioned?
  2. Planner: Planner mapped question `geo_signal` on SCHEMA to minimal fields: address, addressLocality, areaServed.
  3. Slice: name+headline+description+publisher+@type+block+dateModified+datePublished — SCHEMA.name: AigeoRadar SCHEMA.headline: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO...
  4. Actual input tokens: 326
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 326 in-tok · score 100 · match

HTML

sufficient

UNKNOWN

score 100 · 19,273 chars context · 536 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 13,674 chars context · 326 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 23,573 chars context · 578 in-tokens

AIPM answered using 23573 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 · 140 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time 583 api 2 low no
Schema description+name+headline+publisher+@type+block+dateModified+datePublished 524 api 2 low no
AIPM audience+purpose 140 api 1 high yes
Execution chain · AIPM · 1 round(s)
  1. Question: Who is the intended audience of this page?
  2. Planner: Planner mapped question `audience` on AIPM to minimal fields: audience, purpose.
  3. Slice: audience+purpose — AIPM.audience: ["B2B","agency","SMBs","businesses"] AIPM.purpose: Help readers understand 20 Best A...
  4. Actual input tokens: 140
  5. LLM answer: The intended audience of this page includes B2B, agency, SMBs, and businesses.
  6. Evidence: AIPM.audience: ["B2B","agency","SMBs","businesses"] AIPM.purpose: Help readers understand 20 Best AI Visibility Tools Compared in 2026 (Com...
  7. Confidence: high · matched yes
Execution chain · HTML · 2 round(s)
  1. Question: Who is the intended audience of this page?
  2. Planner: Planner mapped question `audience` on HTML to minimal fields: meta_description, lead_paragraphs.
  3. Slice: meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time — HTML.meta_description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2...
  4. Actual input tokens: 583
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 211 in-tok · score 0 · miss

Round 2: 372 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)
  1. Question: Who is the intended audience of this page?
  2. Planner: Planner mapped question `audience` on SCHEMA to minimal fields: description, name.
  3. Slice: description+name+headline+publisher+@type+block+dateModified+datePublished — SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026...
  4. Actual input tokens: 524
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 161 in-tok · score 0 · miss

Round 2: 363 in-tok · score 0 · miss

HTML

insufficient

UNKNOWN.

score 0 · 19,273 chars context · 583 in-tokens

HTML did not answer from 19273 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN.

score 0 · 13,674 chars context · 524 in-tokens

Schema did not answer from 13674 chars of context — additional or different layer context needed.

AIPM

sufficient

The intended audience of this page includes B2B, agency, SMBs, and businesses.

score 88 · 23,573 chars context · 140 in-tokens

AIPM answered using 23573 chars of layer context (minimum fed this run).

Q6 · Understanding · orientation

What is the purpose of this page?

Gold: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ahrefs Brand Radar, Peec AI, HubSpot AI Grader, Otterly AI, AthenaHQ, and more.

Gold source: html.page_summary · html_independent

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

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 160 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML meta_description+lead_paragraphs 210 api 1 medium yes
Schema description+name 160 api 1 medium yes
AIPM purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 695 api 2 low no
Execution chain · AIPM · 2 round(s)
  1. Question: What is the purpose of this page?
  2. Planner: Planner mapped question `purpose` on AIPM to minimal fields: purpose.
  3. Slice: purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.purpose: Help readers understand 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Sof...
  4. Actual input tokens: 695
  5. LLM answer: The purpose of this page is to help readers understand the 20 Best AI Visibility Tools Compared in 2026.
  6. Evidence: AIPM.purpose: Help readers understand 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide). AIPM.abstract: Compare th...
  7. Confidence: low · matched no

Round 1: 120 in-tok · score 30 · miss

Round 2: 575 in-tok · score 30 · miss

Execution chain · HTML · 1 round(s)
  1. Question: What is the purpose of this page?
  2. Planner: Planner mapped question `purpose` on HTML to minimal fields: meta_description, lead_paragraphs.
  3. Slice: meta_description+lead_paragraphs — HTML.meta_description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2...
  4. Actual input tokens: 210
  5. LLM answer: The purpose of this page is to compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026.
  6. Evidence: HTML.meta_description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ah...
  7. Confidence: medium · matched yes
Execution chain · SCHEMA · 1 round(s)
  1. Question: What is the purpose of this page?
  2. Planner: Planner mapped question `purpose` on SCHEMA to minimal fields: description, name.
  3. Slice: description+name — SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026...
  4. Actual input tokens: 160
  5. LLM answer: The purpose of this page is to compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026, including AIGeoRadar and others.
  6. Evidence: SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ahref...
  7. Confidence: medium · matched yes

Root cause · Layer miss

Improve orientation fields; do not paste full HTML into the sidecar.

HTML

sufficient

The purpose of this page is to compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026.

score 61 · 19,273 chars context · 210 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

The purpose of this page is to compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026, including AIGeoRadar and others.

score 61 · 13,674 chars context · 160 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

insufficient

The purpose of this page is to help readers understand the 20 Best AI Visibility Tools Compared in 2026.

score 30 · 23,573 chars context · 695 in-tokens

AIPM did not answer from 23573 chars of context — additional or different layer context needed.

Q7 · Understanding · orientation

Summarize this page in one sentence.

Gold: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ahrefs Brand Radar, Peec AI, HubSpot AI Grader, Otterly AI, AthenaHQ, and more.

Gold source: html.page_summary · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 161 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML meta_description+lead_paragraphs 211 api 1 medium yes
Schema description+name 161 api 1 medium yes
AIPM abstract+purpose 179 api 1 medium yes
Execution chain · AIPM · 1 round(s)
  1. Question: Summarize this page in one sentence.
  2. Planner: Planner mapped question `abstract` on AIPM to minimal fields: abstract, purpose.
  3. Slice: abstract+purpose — AIPM.abstract: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See...
  4. Actual input tokens: 179
  5. LLM answer: The page compares the best AI visibility tools, GEO platforms, and AI SEO software in 2026, focusing on AIGeoRadar and other notable tools.
  6. Evidence: AIPM.abstract: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ahrefs Bra...
  7. Confidence: medium · matched yes
Execution chain · HTML · 1 round(s)
  1. Question: Summarize this page in one sentence.
  2. Planner: Planner mapped question `abstract` on HTML to minimal fields: meta_description, lead_paragraphs.
  3. Slice: meta_description+lead_paragraphs — HTML.meta_description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2...
  4. Actual input tokens: 211
  5. LLM answer: The page compares various AI visibility tools, GEO platforms, and AI SEO software in 2026, highlighting AIGeoRadar alongside other tools like Ahrefs Brand Radar...
  6. Evidence: HTML.meta_description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ah...
  7. Confidence: medium · matched yes
Execution chain · SCHEMA · 1 round(s)
  1. Question: Summarize this page in one sentence.
  2. Planner: Planner mapped question `abstract` on SCHEMA to minimal fields: description, name.
  3. Slice: description+name — SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026...
  4. Actual input tokens: 161
  5. LLM answer: The page compares AIGeoRadar with various AI visibility tools, GEO platforms, and AI SEO software in 2026.
  6. Evidence: SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ahref...
  7. Confidence: medium · matched yes

HTML

sufficient

The page compares various AI visibility tools, GEO platforms, and AI SEO software in 2026, highlighting AIGeoRadar alongside other tools like Ahrefs Brand Radar and HubSpot AI Grader.

score 73 · 19,273 chars context · 211 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

The page compares AIGeoRadar with various AI visibility tools, GEO platforms, and AI SEO software in 2026.

score 61 · 13,674 chars context · 161 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

The page compares the best AI visibility tools, GEO platforms, and AI SEO software in 2026, focusing on AIGeoRadar and other notable tools.

score 61 · 23,573 chars context · 179 in-tokens

AIPM answered using 23573 chars of layer context (minimum fed this run).

Q8 · Understanding · orientation

What is the primary topic or headline of this page?

Gold: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)

Gold source: html.h1|title · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost HTML · 142 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML h1+title 142 api 1 high yes
Schema name+headline+description 184 api 1 high yes
AIPM primaryTopic+title+purpose 166 api 1 high yes
Execution chain · AIPM · 1 round(s)
  1. Question: What is the primary topic or headline of this page?
  2. Planner: Planner mapped question `primary_topic` on AIPM to minimal fields: primaryTopic, title, purpose.
  3. Slice: primaryTopic+title+purpose — AIPM.primaryTopic: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) AIPM....
  4. Actual input tokens: 166
  5. LLM answer: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)
  6. Evidence: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)
  7. Confidence: high · matched yes
Execution chain · HTML · 1 round(s)
  1. Question: What is the primary topic or headline of this page?
  2. Planner: Planner mapped question `primary_topic` on HTML to minimal fields: h1, title.
  3. Slice: h1+title — HTML.h1: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) HTML.title: 20...
  4. Actual input tokens: 142
  5. LLM answer: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)
  6. Evidence: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)
  7. Confidence: high · matched yes
Execution chain · SCHEMA · 1 round(s)
  1. Question: What is the primary topic or headline of this page?
  2. Planner: Planner mapped question `primary_topic` on SCHEMA to minimal fields: name, headline, description.
  3. Slice: name+headline+description — SCHEMA.name: AigeoRadar SCHEMA.headline: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO...
  4. Actual input tokens: 184
  5. LLM answer: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)
  6. Evidence: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)
  7. Confidence: high · matched yes

HTML

sufficient

20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)

score 100 · 19,273 chars context · 142 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)

score 100 · 13,674 chars context · 184 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide)

score 100 · 23,573 chars context · 166 in-tokens

AIPM answered using 23573 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)
  1. Question: What language is this page written in?
  2. Planner: Planner mapped question `language` on AIPM to minimal fields: inLanguage.
  3. Slice: inLanguage — AIPM.inLanguage: en
  4. Actual input tokens: 102
  5. LLM answer: The page is written in English.
  6. Evidence: AIPM.inLanguage: en
  7. Confidence: high · matched yes
Execution chain · HTML · 1 round(s)
  1. Question: What language is this page written in?
  2. Planner: Planner mapped question `language` on HTML to minimal fields: lang.
  3. Slice: lang — HTML.lang: lang=en
  4. Actual input tokens: 100
  5. LLM answer: English
  6. Evidence: HTML.lang: lang=en
  7. Confidence: high · matched yes
Execution chain · SCHEMA · 1 round(s)
  1. Question: What language is this page written in?
  2. Planner: Planner mapped question `language` on SCHEMA to minimal fields: inLanguage.
  3. Slice: inLanguage — SCHEMA.inLanguage: en
  4. Actual input tokens: 101
  5. LLM answer: The page is written in English.
  6. Evidence: SCHEMA.inLanguage: en
  7. Confidence: high · matched yes

HTML

sufficient

English

score 100 · 19,273 chars context · 100 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

The page is written in English.

score 88 · 13,674 chars context · 101 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

The page is written in English.

score 88 · 23,573 chars context · 102 in-tokens

AIPM answered using 23573 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 HTML · 550 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML title+lead_paragraphs+h1+meta_description+prose_span+body_excerpt+time 550 api 2 low yes
Schema block+description+name+headline+publisher+@type+dateModified+datePublished 578 api 2 low yes
AIPM keyFacts+publisher+abstract+purpose+primaryTopic+title+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 799 api 2 low yes
Execution chain · AIPM · 2 round(s)
  1. Question: What phone number or contact detail is listed?
  2. Planner: Planner mapped question `contact_phone` on AIPM to minimal fields: keyFacts, publisher, abstract.
  3. Slice: keyFacts+publisher+abstract+purpose+primaryTopic+title+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: Which AI Visibility Platform Actually Helps AI Recommend Your Business? Instead of se...
  4. Actual input tokens: 799
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 223 in-tok · score 100 · match

Round 2: 576 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)
  1. Question: What phone number or contact detail is listed?
  2. Planner: Planner mapped question `contact_phone` on HTML to minimal fields: title, lead_paragraphs.
  3. Slice: title+lead_paragraphs+h1+meta_description+prose_span+body_excerpt+time — HTML.title: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Software Guide) — AigeoRadar...
  4. Actual input tokens: 550
  5. LLM answer: UNKNOWN
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 179 in-tok · score 100 · match

Round 2: 371 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: What phone number or contact detail is listed?
  2. Planner: Planner mapped question `contact_phone` on SCHEMA to minimal fields: telephone, block, description.
  3. Slice: block+description+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.block: { "@context": "https://schema.org", "@graph": [ { "@type":...
  4. Actual input tokens: 578
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 254 in-tok · score 100 · match

Round 2: 324 in-tok · score 100 · match

HTML

sufficient

UNKNOWN

score 100 · 19,273 chars context · 550 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 13,674 chars context · 578 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 23,573 chars context · 799 in-tokens

AIPM answered using 23573 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 · 324 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML prose_span+lead_paragraphs+title+h1+meta_description+body_excerpt+time 532 api 2 low yes
Schema name+headline+description+publisher+@type+block+dateModified+datePublished 324 api 2 low yes
AIPM purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 576 api 2 low yes
Execution chain · AIPM · 2 round(s)
  1. Question: What physical address is listed for this business?
  2. Planner: Planner mapped question `address` on AIPM to minimal fields: address, geo, areaServed.
  3. Slice: purpose+abstract+primaryTopic+title+publisher+keyFacts+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.purpose: Help readers understand 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Sof...
  4. Actual input tokens: 576
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 576 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)
  1. Question: What physical address is listed for this business?
  2. Planner: Planner mapped question `address` on HTML to minimal fields: prose_span, lead_paragraphs.
  3. Slice: prose_span+lead_paragraphs+title+h1+meta_description+body_excerpt+time — HTML.prose_span: UNKNOWN HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms,...
  4. Actual input tokens: 532
  5. LLM answer: UNKNOWN
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 161 in-tok · score 100 · match

Round 2: 371 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: What physical address is listed for this business?
  2. Planner: Planner mapped question `address` on SCHEMA to minimal fields: address, addressLocality, areaServed.
  3. Slice: name+headline+description+publisher+@type+block+dateModified+datePublished — SCHEMA.name: AigeoRadar SCHEMA.headline: 20 Best AI Visibility Tools Compared in 2026 (Complete GEO...
  4. Actual input tokens: 324
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 0 in-tok · score 0 · miss

Round 2: 324 in-tok · score 100 · match

HTML

sufficient

UNKNOWN

score 100 · 19,273 chars context · 532 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 13,674 chars context · 324 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 23,573 chars context · 576 in-tokens

AIPM answered using 23573 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 · 576 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time 628 api 2 low yes
Schema block+description+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 813 api 2 low yes
Execution chain · AIPM · 2 round(s)
  1. Question: What are the opening hours or availability?
  2. Planner: Planner mapped question `hours` on AIPM to minimal fields: keyFacts, abstract, purpose.
  3. Slice: keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: Which AI Visibility Platform Actually Helps AI Recommend Your Business? Instead of se...
  4. Actual input tokens: 813
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 238 in-tok · score 100 · match

Round 2: 575 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)
  1. Question: What are the opening hours or availability?
  2. Planner: Planner mapped question `hours` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
  3. Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 20...
  4. Actual input tokens: 628
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 258 in-tok · score 100 · match

Round 2: 370 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: What are the opening hours or availability?
  2. Planner: Planner mapped question `hours` on SCHEMA to minimal fields: openingHours, block, description.
  3. Slice: block+description+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.block: { "@context": "https://schema.org", "@graph": [ { "@type":...
  4. Actual input tokens: 576
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 253 in-tok · score 100 · match

Round 2: 323 in-tok · score 100 · match

HTML

sufficient

UNKNOWN.

score 100 · 19,273 chars context · 628 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 13,674 chars context · 576 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 23,573 chars context · 813 in-tokens

AIPM answered using 23573 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: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 584 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time 636 api 2 low yes
Schema block+description+name+headline+publisher+@type+dateModified+datePublished 584 api 2 low yes
AIPM keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 795 api 2 low yes
Execution chain · AIPM · 2 round(s)
  1. Question: Is pricing or package information mentioned, and what is it?
  2. Planner: Planner mapped question `pricing` on AIPM to minimal fields: keyFacts, sections, abstract.
  3. Slice: keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: Which AI Visibility Platform Actually Helps AI Recommend Your Business? Instead of se...
  4. Actual input tokens: 795
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 216 in-tok · score 100 · match

Round 2: 579 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)
  1. Question: Is pricing or package information mentioned, and what is it?
  2. Planner: Planner mapped question `pricing` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
  3. Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 20...
  4. Actual input tokens: 636
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 262 in-tok · score 100 · match

Round 2: 374 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: Is pricing or package information mentioned, and what is it?
  2. Planner: Planner mapped question `pricing` on SCHEMA to minimal fields: offers, price, block, description.
  3. Slice: block+description+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.block: { "@context": "https://schema.org", "@graph": [ { "@type":...
  4. Actual input tokens: 584
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

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

Round 2: 327 in-tok · score 100 · match

HTML

sufficient

UNKNOWN.

score 100 · 19,273 chars context · 636 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 13,674 chars context · 584 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 23,573 chars context · 795 in-tokens

AIPM answered using 23573 chars of layer context (minimum fed this run).

Q14 · Retrieval · depth

What makes this offer different or stand out?

Gold: one-click

Gold source: html.prose|meta · html_independent

No layer provided a sufficient answer from its context alone.

Measured retrieval cost (API tokens) · lowest cost HTML · 632 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time 632 api 2 low no
Schema description+block+name+headline+publisher+@type+dateModified+datePublished 665 api 2 low no
AIPM keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 815 api 2 low no
Execution chain · AIPM · 2 round(s)
  1. Question: What makes this offer different or stand out?
  2. Planner: Planner mapped question `differentiator` on AIPM to minimal fields: keyFacts, abstract, purpose.
  3. Slice: keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: Which AI Visibility Platform Actually Helps AI Recommend Your Business? Instead of se...
  4. Actual input tokens: 815
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 239 in-tok · score 0 · miss

Round 2: 576 in-tok · score 0 · miss

Execution chain · HTML · 2 round(s)
  1. Question: What makes this offer different or stand out?
  2. Planner: Planner mapped question `differentiator` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
  3. Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 20...
  4. Actual input tokens: 632
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 260 in-tok · score 0 · miss

Round 2: 372 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)
  1. Question: What makes this offer different or stand out?
  2. Planner: Planner mapped question `differentiator` on SCHEMA to minimal fields: description, block, name.
  3. Slice: description+block+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026...
  4. Actual input tokens: 665
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 302 in-tok · score 0 · miss

Round 2: 363 in-tok · score 0 · miss

Root cause · Depth gap (expected)

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

HTML

insufficient

UNKNOWN.

score 0 · 19,273 chars context · 632 in-tokens

HTML did not answer from 19273 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN.

score 0 · 13,674 chars context · 665 in-tokens

Schema did not answer from 13674 chars of context — additional or different layer context needed.

AIPM

insufficient

UNKNOWN.

score 0 · 23,573 chars context · 815 in-tokens

AIPM did not answer from 23573 chars of context — additional or different layer context needed.

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 · 601 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time 644 api 2 low yes
Schema description+block+name+headline+publisher+@type+dateModified+datePublished 601 api 2 low yes
AIPM keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 829 api 2 low yes
Execution chain · AIPM · 2 round(s)
  1. Question: What trust signals are present (reviews, certificates, guarantees, years of experience)?
  2. Planner: Planner mapped question `trust` on AIPM to minimal fields: keyFacts, abstract, purpose.
  3. Slice: keyFacts+abstract+purpose+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.keyFacts: Which AI Visibility Platform Actually Helps AI Recommend Your Business? Instead of se...
  4. Actual input tokens: 829
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 246 in-tok · score 100 · match

Round 2: 583 in-tok · score 100 · match

Execution chain · HTML · 2 round(s)
  1. Question: What trust signals are present (reviews, certificates, guarantees, years of experience)?
  2. Planner: Planner mapped question `trust` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
  3. Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 20...
  4. Actual input tokens: 644
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

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

Round 2: 378 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: What trust signals are present (reviews, certificates, guarantees, years of experience)?
  2. Planner: Planner mapped question `trust` on SCHEMA to minimal fields: description, block, name.
  3. Slice: description+block+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026...
  4. Actual input tokens: 601
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched yes

Round 1: 270 in-tok · score 100 · match

Round 2: 331 in-tok · score 100 · match

HTML

sufficient

UNKNOWN.

score 100 · 19,273 chars context · 644 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

UNKNOWN.

score 100 · 13,674 chars context · 601 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

UNKNOWN.

score 100 · 23,573 chars context · 829 in-tokens

AIPM answered using 23573 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 SCHEMA · 658 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time 714 api 2 medium yes
Schema block+description+name+headline+publisher+@type+dateModified+datePublished 658 api 2 low no
AIPM faqEntity+keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate 741 api 2 low no
Execution chain · AIPM · 2 round(s)
  1. Question: What frequently asked questions or FAQ topics are covered?
  2. Planner: Planner mapped question `faq` on AIPM to minimal fields: faqEntity, keyFacts.
  3. Slice: faqEntity+keyFacts+purpose+abstract+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate — AIPM.faqEntity: [] AIPM.keyFacts: Which AI Visibility Platform Actually Helps AI Recommend Your Bus...
  4. Actual input tokens: 741
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 164 in-tok · score 0 · miss

Round 2: 577 in-tok · score 0 · miss

Execution chain · HTML · 2 round(s)
  1. Question: What frequently asked questions or FAQ topics are covered?
  2. Planner: Planner mapped question `faq` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
  3. Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 20...
  4. Actual input tokens: 714
  5. LLM answer: The frequently asked questions covered include monitoring GEO score, common mistakes with AigeoRadar, and plan limits for AigeoRadar.
  6. Evidence: HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ahr...
  7. Confidence: medium · matched yes

Round 1: 301 in-tok · score 59 · match

Round 2: 413 in-tok · score 70 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: What frequently asked questions or FAQ topics are covered?
  2. Planner: Planner mapped question `faq` on SCHEMA to minimal fields: block, description.
  3. Slice: block+description+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.block: { "@context": "https://schema.org", "@graph": [ { "@type":...
  4. Actual input tokens: 658
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 294 in-tok · score 0 · miss

Round 2: 364 in-tok · score 0 · miss

Root cause · Depth gap (expected)

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

HTML

sufficient

The frequently asked questions covered include monitoring GEO score, common mistakes with AigeoRadar, and plan limits for AigeoRadar.

score 70 · 19,273 chars context · 714 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

insufficient

UNKNOWN.

score 0 · 13,674 chars context · 658 in-tokens

Schema did not answer from 13674 chars of context — additional or different layer context needed.

AIPM

insufficient

UNKNOWN.

score 0 · 23,573 chars context · 741 in-tokens

AIPM did not answer from 23573 chars of context — additional or different layer context needed.

Q17 · Retrieval · depth

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

Gold: get started

Gold source: html.cta|prose · html_independent

No layer provided a sufficient answer from its context alone.

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 599 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time 644 api 2 low no
Schema description+block+name+headline+publisher+@type+dateModified+datePublished 599 api 2 low no
AIPM purpose+abstract+keyFacts+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity 827 api 2 low no
Execution chain · AIPM · 2 round(s)
  1. Question: What action should the visitor take (call, buy, contact, book)?
  2. Planner: Planner mapped question `cta` on AIPM to minimal fields: purpose, abstract, keyFacts.
  3. Slice: purpose+abstract+keyFacts+primaryTopic+title+publisher+audience+contentIntent+relatedPages+dateModified+datePublished+reviewDate+faqEntity — AIPM.purpose: Help readers understand 20 Best AI Visibility Tools Compared in 2026 (Complete GEO Sof...
  4. Actual input tokens: 827
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 245 in-tok · score 0 · miss

Round 2: 582 in-tok · score 0 · miss

Execution chain · HTML · 2 round(s)
  1. Question: What action should the visitor take (call, buy, contact, book)?
  2. Planner: Planner mapped question `cta` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
  3. Slice: lead_paragraphs+body_excerpt+prose_span+title+h1+meta_description+time — HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 20...
  4. Actual input tokens: 644
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 266 in-tok · score 0 · miss

Round 2: 378 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)
  1. Question: What action should the visitor take (call, buy, contact, book)?
  2. Planner: Planner mapped question `cta` on SCHEMA to minimal fields: description, block, name.
  3. Slice: description+block+name+headline+publisher+@type+dateModified+datePublished — SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026...
  4. Actual input tokens: 599
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 269 in-tok · score 0 · miss

Round 2: 330 in-tok · score 0 · miss

Root cause · Depth gap (expected)

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

HTML

insufficient

UNKNOWN.

score 0 · 19,273 chars context · 644 in-tokens

HTML did not answer from 19273 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN.

score 0 · 13,674 chars context · 599 in-tokens

Schema did not answer from 13674 chars of context — additional or different layer context needed.

AIPM

insufficient

UNKNOWN.

score 0 · 23,573 chars context · 827 in-tokens

AIPM did not answer from 23573 chars of context — additional or different layer context needed.

Q18 · Retrieval · depth

What related products, services, or pages are mentioned?

Gold: Features, What is AigeoRadar?, Pricing

Gold source: html.nav|prose · html_independent

Sufficient: HTML, Schema, AIPM

Measured retrieval cost (API tokens) · lowest cost SCHEMA · 265 input tokens

Layer Planner fields Input tokens Rounds Confidence OK?
HTML lead_paragraphs+body_excerpt+prose_span 270 api 1 high yes
Schema description+block+name 265 api 1 high yes
AIPM relatedPages+keyFacts 366 api 1 high yes
Execution chain · AIPM · 1 round(s)
  1. Question: What related products, services, or pages are mentioned?
  2. Planner: Planner mapped question `related` on AIPM to minimal fields: relatedPages, sections, keyFacts.
  3. Slice: relatedPages+keyFacts — AIPM.relatedPages: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026 — https://aigeor...
  4. Actual input tokens: 366
  5. LLM answer: The related pages mentioned are guides and tools for WordPress and AI, including a free AI bot checker and an LLMS.txt generator.
  6. Evidence: AIPM.relatedPages: WordPress GEO: llms.txt, llms-full.txt, and AI discovery in 2026 — https://aigeoradar.com/blog/wordpress-geo-llms-txt-gui...
  7. Confidence: high · matched yes
Execution chain · HTML · 1 round(s)
  1. Question: What related products, services, or pages are mentioned?
  2. Planner: Planner mapped question `related` on HTML to minimal fields: lead_paragraphs, body_excerpt, prose_span.
  3. Slice: lead_paragraphs+body_excerpt+prose_span — HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 20...
  4. Actual input tokens: 270
  5. LLM answer: Ahrefs Brand Radar, Peec AI, HubSpot AI.
  6. Evidence: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ahrefs Brand Radar, Peec...
  7. Confidence: high · matched yes
Execution chain · SCHEMA · 1 round(s)
  1. Question: What related products, services, or pages are mentioned?
  2. Planner: Planner mapped question `related` on SCHEMA to minimal fields: description, block, name.
  3. Slice: description+block+name — SCHEMA.description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026...
  4. Actual input tokens: 265
  5. LLM answer: Ahrefs Brand Radar, Peec AI, HubSpot AI Grader, Otterly AI, AthenaHQ.
  6. Evidence: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2026. See how AIGeoRadar compares with Ahrefs Brand Radar, Peec...
  7. Confidence: high · matched yes

HTML

sufficient

Ahrefs Brand Radar, Peec AI, HubSpot AI.

score 82 · 19,273 chars context · 270 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

sufficient

Ahrefs Brand Radar, Peec AI, HubSpot AI Grader, Otterly AI, AthenaHQ.

score 82 · 13,674 chars context · 265 in-tokens

Schema answered using 13674 chars of layer context (minimum fed this run).

AIPM

sufficient

The related pages mentioned are guides and tools for WordPress and AI, including a free AI bot checker and an LLMS.txt generator.

score 82 · 23,573 chars context · 366 in-tokens

AIPM answered using 23573 chars of layer context (minimum fed this run).

Q19 · Metadata · orientation

When was this page published or last updated?

Gold: 2026-06-25

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

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

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+title+h1+meta_description+prose_span 638 api 2 high yes
Schema dateModified+datePublished+block+name+headline+description+publisher+@type 623 api 2 low no
AIPM dateModified+datePublished+reviewDate 134 api 1 high yes
Execution chain · AIPM · 1 round(s)
  1. Question: When was this page published or last updated?
  2. Planner: Planner mapped question `freshness` on AIPM to minimal fields: dateModified, datePublished, reviewDate.
  3. Slice: dateModified+datePublished+reviewDate — AIPM.dateModified: 2026-07-25 AIPM.datePublished: 2026-06-25 AIPM.reviewDate: 2026-07-25
  4. Actual input tokens: 134
  5. LLM answer: The page was published on 2026-06-25 and last updated on 2026-07-25.
  6. Evidence: AIPM.dateModified: 2026-07-25 AIPM.datePublished: 2026-06-25 AIPM.reviewDate: 2026-07-25
  7. Confidence: high · matched yes
Execution chain · HTML · 2 round(s)
  1. Question: When was this page published or last updated?
  2. Planner: Planner mapped question `freshness` on HTML to minimal fields: time, lead_paragraphs, body_excerpt.
  3. Slice: time+lead_paragraphs+body_excerpt+title+h1+meta_description+prose_span — HTML.time: 2026-06-25 HTML.lead_paragraphs: Compare the best AI Visibility tools, GEO platforms, an...
  4. Actual input tokens: 638
  5. LLM answer: 2026-06-25
  6. Evidence: 2026-06-25
  7. Confidence: high · matched yes

Round 1: 262 in-tok · score 40 · miss

Round 2: 376 in-tok · score 100 · match

Execution chain · SCHEMA · 2 round(s)
  1. Question: When was this page published or last updated?
  2. Planner: Planner mapped question `freshness` on SCHEMA to minimal fields: dateModified, datePublished, block.
  3. Slice: dateModified+datePublished+block+name+headline+description+publisher+@type — SCHEMA.dateModified: 2026-07-25 SCHEMA.datePublished: 2026-06-25 SCHEMA.block: { "@context": "...
  4. Actual input tokens: 623
  5. LLM answer: The page was published on June 25, 2026, and last updated on July 25, 2026.
  6. Evidence: SCHEMA.dateModified: 2026-07-25 SCHEMA.datePublished: 2026-06-25 SCHEMA.block: { "@context": "https://schema.org", "@graph": [...
  7. Confidence: low · matched no

Round 1: 260 in-tok · score 36 · miss

Round 2: 363 in-tok · score 36 · miss

HTML

sufficient

2026-06-25

score 100 · 19,273 chars context · 638 in-tokens

HTML answered using 19273 chars of layer context (minimum fed this run).

Schema

insufficient

The page was published on June 25, 2026, and last updated on July 25, 2026.

score 36 · 13,674 chars context · 623 in-tokens

Schema did not answer from 13674 chars of context — additional or different layer context needed.

AIPM

sufficient

The page was published on 2026-06-25 and last updated on 2026-07-25.

score 88 · 23,573 chars context · 134 in-tokens

AIPM answered using 23573 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 606 api 2 low no
Schema @type+name+headline+description+publisher+block+dateModified+datePublished 489 api 2 low no
AIPM contentIntent+pageType 124 api 1 high yes
Execution chain · AIPM · 1 round(s)
  1. Question: What kind of page is this (article, product, local service, company page, FAQ, other)?
  2. Planner: Planner mapped question `page_kind` on AIPM to minimal fields: contentIntent, pageType.
  3. Slice: contentIntent+pageType — AIPM.contentIntent: informational AIPM.pageType: blog
  4. Actual input tokens: 124
  5. LLM answer: blog
  6. Evidence: blog
  7. Confidence: high · matched yes
Execution chain · HTML · 2 round(s)
  1. Question: What kind of page is this (article, product, local service, company page, FAQ, other)?
  2. Planner: Planner mapped question `page_kind` on HTML to minimal fields: meta_description, lead_paragraphs.
  3. Slice: meta_description+lead_paragraphs+title+h1+prose_span+body_excerpt+time — HTML.meta_description: Compare the best AI Visibility tools, GEO platforms, and AI SEO software in 2...
  4. Actual input tokens: 606
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 223 in-tok · score 0 · miss

Round 2: 383 in-tok · score 0 · miss

Execution chain · SCHEMA · 2 round(s)
  1. Question: What kind of page is this (article, product, local service, company page, FAQ, other)?
  2. Planner: Planner mapped question `page_kind` on SCHEMA to minimal fields: @type.
  3. Slice: @type+name+headline+description+publisher+block+dateModified+datePublished — SCHEMA.@type: Organization SCHEMA.name: AigeoRadar SCHEMA.headline: 20 Best AI Visibility Tools Co...
  4. Actual input tokens: 489
  5. LLM answer: UNKNOWN.
  6. Evidence: —
  7. Confidence: low · matched no

Round 1: 114 in-tok · score 0 · miss

Round 2: 375 in-tok · score 0 · miss

HTML

insufficient

UNKNOWN.

score 0 · 19,273 chars context · 606 in-tokens

HTML did not answer from 19273 chars of context — additional or different layer context needed.

Schema

insufficient

UNKNOWN.

score 0 · 13,674 chars context · 489 in-tokens

Schema did not answer from 13674 chars of context — additional or different layer context needed.

AIPM

sufficient

blog

score 100 · 23,573 chars context · 124 in-tokens

AIPM answered using 23573 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 · Fri, Aug 7, 2026 11:14 PM · aipm_benchmark_score_v10

Share

Per-question context chain across layers.

Post on X LinkedIn WhatsApp
About the lab →