Empirical Evidence, Live Telemetry & Architectural Record
This page demonstrates how Taghi Molavi and InTen engineer search discoverability and answer-engine presence across Google, ChatGPT, and AI systems. Direct Search Console telemetry, open-source benchmarks, and international scientific registries are documented below.
Understand three things: the core problem, the system built, and what can be verified independently. Client identities and domain names remain redacted under non-disclosure agreements, but console ownership and comparative telemetry are preserved.
Direct Google Search Console Telemetry
Direct telemetry from Search Console. Client domain names are masked under NDAs, while verified console ownership and comparative growth curves remain visible.
Clicks (3m)
4.3M
↑ vs 1.42M prev
Impressions
53.5M
↑ vs 16.9M prev
3x organic surge via automated NewsArticle Schema graphs, author disambiguation, and Knowledge Graph grounding.
🔒 Client domain redacted under NDA
AI Impressions
153K
↑ vs 0 prev
Period
6 Mos
Consistent
Sustained presence and citation grounding in Google AI Overviews using systematic GEO entity disambiguation.
🔒 Client domain redacted under NDA
Avg Position
1.5
Multimodal
Impressions (28d)
81.7K
1.11K Clicks
Top-tier visibility in Google Multimodal / Lens retrieval via structured media-entity graph modeling.
🔒 Client domain redacted under NDA
Reproducible AI Visibility Metrics
Empirical, reproducible observations across four major AI providers (ChatGPT, Perplexity, Gemini, Claude) with 118 verified observations and stored SHA-256 checksums.
| Target Brand | Mention Rate | Top-1 Recommendation | Citation Recorded | Sample (n) |
|---|---|---|---|---|
| HubSpot | 73.7% | 26.3% | 79.7% | n = 118 |
| Salesforce | 62.7% | 46.6% | 61.0% | n = 118 |
| Zoho CRM | 64.4% | 17.8% | 30.5% | n = 118 |
| Pipedrive | 61.0% | 9.3% | 33.9% | n = 118 |
💡 Technical note: Mention rate, top-1 recommendation, and citation recorded are distinct metrics that must be measured and optimized independently.
View Live Dataset & SHA-256 Checksums on GitHub ↗Problem → Build → Evidence
Specific client identities remain confidential under NDA; the problem pattern, system build, and qualitative evidence are detailed below.
High-frequency editorial publication with hundreds of daily articles and distributed syndication channels.
Rapid publishing cadence outpaced structured metadata hygiene, causing fragmented entity signals in Google News and near-zero source attribution in generative answer engines.
Architected automated JSON-LD NewsArticle and Author entity graphs, established canonical author disambiguation via Wikidata/sameAs references, and built pre-publication schema validation pipelines.
Qualitative outcome: Achieved consistent Knowledge Graph entity attribution and validated Rich Results across all primary editorial sections. Verified schema compliance with zero syntax errors on Search Console indexation queues.
🔒 Client identity and internal proprietary CMS configurations remain confidential under non-disclosure agreements.
Specialized machinery and industrial manufacturing firm serving domestic and export markets.
Extensive product catalogs lacked hierarchical topical clustering. Generative search engines hallucinated technical specifications or attributed product capabilities to competitors.
Engineered multi-layered Product and Service schema models, rebuilt semantic specification tables for machine extraction, and aligned reciprocal multilingual hreflang clusters across regional markets.
Qualitative outcome: Established unambiguous entity boundaries in Google Knowledge Panels and eliminated model hallucinations across standard commercial evaluation prompts.
🔒 Commercial contract values and specific corporate entities are strictly protected under confidentiality agreements.
Cross-border consultancy handling international client inquiries across three regional languages.
High volume of unqualified, unstructured leads created operational bottlenecks while primary service pages lacked semantic depth for AI retrieval.
Constructed an integrated Digital Twin intake workflow with interactive screening criteria, connected validated brand knowledge bases, and structured localized service landing pages.
Qualitative outcome: Disqualified mismatched inquiries before human consultant intake, established validated service schema across all locales, and achieved reliable retrieval in targeted answer engine queries.
🔒 Customer inquiry logs and proprietary diagnostic protocols remain confidential.
Inspecting the Engineering
Three public repositories on GitHub that make the measurement methodology, evaluation logic, and agent skill frameworks inspectable.
Problem: There was no repeatable way to compare how an entity appeared in answer engines.
Built: A reproducible Python benchmark framework for recording prompts, model answers, citations, and retrieval differences.
Example: Execute identical prompts across multiple answer engines to inspect where the brand and source citations appear.
Verifiable result: A reproducible report and benchmark methodology in Python, rather than an unverified visibility claim.
Problem: AI coding agents had scattered, untested instructions and lacked consistent skill definitions.
Built: A curated collection of Markdown skill definitions with YAML frontmatter and Model Context Protocol (MCP) server configurations.
Example: Before executing a task, an agent loads verified domain instructions and connects scoped tools without broad permissions.
Verifiable result: Agent skills and tool configurations become discoverable, versioned, and reviewable in public repositories.
Problem: n8n workflow automations functioned in prototypes but lacked structured validation and runtime observability.
Built: Production workflow patterns, agent skill recipes, and MCP routing with pre- and post-execution validation checkpoints.
Example: Validate entity schemas, links, and API payloads before publication or agent task completion.
Verifiable result: Observable, deterministic workflow execution with explicit error recovery instead of unmonitored runs.
Scientific Integrity & Verification
International researcher identifiers, peer-accessible publications in Zenodo and OpenAIRE, and public developer profiles.
0009-0009-6253-5354
International Researcher ID
orcid.org ↗Zenodo / CERN DOI10.5281/zenodo.23234349
OpenAIRE & CERN Archival DOI
zenodo.org ↗Hugging Facetaqimolavi
Live Spaces & AI Benchmarks
huggingface.co ↗PyPI Distributiontaghi-molavi88
Official geo-scope Python package
pypi.org ↗Wikidata Knowledge GraphQ141270530
Canonical Knowledge Graph Node
wikidata.org ↗OpenAIRE European PortalPublication Index
European Research Registry
openaire.eu ↗Academia.eduERP AI Architecture
Enterprise ERP Governance Paper
academia.edu ↗GitHub Organizationtmolavi
Canonical Git Organization
github.com/tmolavi ↗Open source and direct console telemetry ensure that work is not supported by marketing claims alone. Engineers and search evaluators can inspect real Search Console graphs, benchmark methodologies, and source repositories while client confidentiality remains strictly protected.