7 papers · 1 filter
Commercial Intent in Human-AI Conversations: A Corpus Audit and Architecture for Website Sales Agents
Benjamin Tannenbaum
Conversational sales agents must distinguish questions about products from purchase commitments, preserve explicit requirements, and ground the next action in current business info…
From Prompt to Recommendation: A Fitted Stage Model of Brand Visibility in AI Search
Benjamin Tannenbaum
We analyze 34,960 unbranded prompt-engine observations from 75 anonymized Aiso projects, covering 2,854 distinct monitored prompts and repeated GPT and Gemini runs from June-Septem…
Scoring With the Engine: Retrieval Exposure, Cross-Engine Divergence, and the Limits of Engine-Agnostic GEO Scores
Benjamin Tannenbaum
Recent work asks whether generative-engine visibility can be approximated with deterministic, engine-free page scores. We separate two stages such scores can conflate: exposure to…
Purchase Advice and Observable Buyer Responses in Real AI Conversations
Benjamin Tannenbaum
How often does a generative assistant persuade someone to buy, or persuade them not to buy? Conversation logs contain recommendations, but they do not necessarily record subsequent…
Beyond the Final Prompt: Measuring the Effect of Within-Conversation Context on AI Answers
Benjamin Tannenbaum
An isolated final user message is often treated as the query in evaluations of AI systems. In a conversation, however, the actionable request may be distributed across preceding tu…
The Prompt Is Not the Query: How Request State Evolves Across Multi-Turn AI Conversations
Benjamin Tannenbaum
AI-search evaluation commonly treats a prompt as a stable query that can be counted, classified, and replayed in isolation. A conversation makes that unit of analysis questionable:…
Answer-Reconstruction Search Density: Measuring the Query and Source Work Compressed by Conversational Answers
Benjamin Tannenbaum
Conversational systems can collapse a visible sequence of web queries, result inspections, and source comparisons into a single synthesized answer. Existing retrieval metrics evalu…