
ResearchOriginal research
An AI books a hotel but cannot confirm it worked. A 32-run booking experiment shows why agents need affordances, authorization and verifiable results.
- Affordance
- Agent Experience
- AI agents
- Web accessibility
Read research ↗
ResearchOriginal research
Asked to void an invoice, an AI prepares to call a payment tool. The cause may be how the tool describes its capabilities, not the AI itself.
- #TCC
- #TSO
- #ToolMetadata
- #AIAgent
Read research ↗
ResearchOriginal research
The tool is listed and the API works, yet the AI never calls your service. The problem may lie not in the tool but in how the model understands it.
- TSO
- Tool selection
- Tool retrieval
- MCP
Read research ↗
Guides
Compare UX, DX and AX, and see where AI agents run into interface, authorization and error-handling problems on websites.
- AX
- Agent Experience
- AI agents
- MCP
- GEO
Read article ↗
Guides
Why are semantically similar articles not always cited by AI? Embeddings, cosine similarity, DPR, reranking, the KDD 2024 GEO paper and citation verification.
- GEO
- Semantic retrieval
- Embedding
- RAG
- AI citations
Read article ↗
Guides
How AI agents retrieve, select and call tools, from Toolformer to ToolScope, and what providers can adjust with TSO, how to validate it and its limits.
- TSO
- AI agents
- Tool retrieval
- MCP
- Tool Search
Read article ↗
News
Turkey’s competition authority is investigating Google’s AI Overviews and AI Mode, and is requiring a publisher opt-out choice and fair content-use terms.
- Google
- AI search
- Antitrust
- GEO
Read article ↗
Guides
What UTM parameters are, why ChatGPT links carry utm_source=chatgpt.com, how to find ChatGPT traffic in GA4, and the October 2026 tagging failure.
- UTM
- ChatGPT
- GA4
- AI traffic
- Attribution
Read article ↗
Guides
Design an AI visibility report with a fixed question set, explicit denominators and separate mention, citation, factual and action measures.
- AI visibility
- Citation rate
- MCAC
Read article ↗
ResearchResearch review
A research review of Synthetic Sources?: its 712-query audit, the detector-based 16% finding and its limits, plus circular reporting and citation trust.
- Synthetic sources
- Research review
- Citation reliability
Read research ↗
Guides
What October 2026 observations of ranking and vendor-claim warnings show, what they do not prove, and how to audit the way AI answers describe a brand.
- AI citations
- Comparison content
- GEO measurement
Read article ↗
News
Exa’s October 19, 2026 release explained: Lite versus Auto, Dynamic Highlights, product and place data, vendor benchmarks, API examples and crawler controls.
Read article ↗
Guides
A practical guide to feeds, Product and Offer markup, purchase conditions and measurement, with dated Shopify, ChatGPT and Google examples and regional limits.
- Agentic commerce
- Ecommerce SEO
- Product data
Read article ↗
News
An October 2026 analysis of AI agent restrictions at banks and retailers, Yelp’s licensed data model, and data access versus transaction authority.
- AI agents
- Platform access
- Data licensing
Read article ↗
Guides
Nine public ChatGPT Ads case reports with currencies, CPC, CPM, sample periods and attribution limits, plus Synter’s five-market USD breakdown.
- ChatGPT Ads
- CPC and CPM
- Attribution
Read article ↗
News
A dated analysis of Meta’s proposed October 30 commercial terms, the off-site content rights dispute, robots.txt and access controls for publishers.
- Meta
- AI crawlers
- Content licensing
Read article ↗
News
What Anthropic’s October 8 policy announcement says about fabricated sources, undisclosed sponsorship and GEO, ahead of its November 12 effective date.
- Anthropic
- GEO
- Source integrity
Read article ↗
News
OpenSEO’s Fall 2026 YC entry, DataForSEO dependency, pricing and customer story: where it adds value and where the API-wrapper critique holds.
- OpenSEO
- SEO tools
- MCP
- Y Combinator
Read article ↗
Guides
Find AI Assistant sessions, sources, landing pages and key events in GA4, separate human referrals from crawlers, and check missing attribution.
Read article ↗
Guides
Compare training, search and user-triggered AI bots, including Google-Extended and OpenAI exceptions, with 26 dated publisher snapshots and limits.
- robots.txt
- AI crawlers
- Publisher policy
Read article ↗
News
A Taiwan launch archive: the September 2026 rollout, advertiser evidence, local budget context and how ChatGPT ads differ from Sponsored Agents.
- ChatGPT Ads
- Taiwan
- Advertising
Read article ↗
News
OpenAI’s September 16, 2026 Sponsored Agents test explained: the user flow, Amazon Ads integration, availability limits and implications for SEO and paid media.
- Sponsored Agents
- ChatGPT Ads
- Agentic commerce
Read article ↗
News
A September 2026 account of Meta Muse’s launch, Amazon’s access dispute, early market reaction and the implications for shopping, search and marketing.
- Meta Muse
- AI agents
- Agentic commerce
Read article ↗
News
Jev’s structured decisions, Choice/Score/Noul types, release-era pricing and SEO demonstrations explained, with clear limits on benchmark and accuracy claims.
- Jev
- TypeSafe AI
- SEO automation
Read article ↗
ResearchOriginal research
A six-restaurant Taipei case study with 21 Sonar observations, separating mentions, citations, reference agreement and actionable information.
- Original research
- MCAC
- Local business
- AI search
Read research ↗