Measuring the friction in AI use that standard evaluations miss<\/p>\n\n\n\n
AI platforms can see what people ask. They cannot see what happens between the person and the model while they work together.<\/p>\n\n\n\n
Evaluations score the model\u2019s output. Aggregate analysis counts patterns across millions of conversations. Surveys ask users afterwards. None of them follows the individual exchange as it unfolds, and that is where friction lives.<\/p>\n\n\n\n
I measure the relational form of human\u2013AI exchanges: how roles, expectations and interaction patterns shift across turns, on both sides of the conversation. When the AI starts to carry the decision instead of supporting it, I call that role drift. It needs no technical failure. It happens in the exchange itself.<\/p>\n\n\n\n
Zenn is a live instrument that observes this layer. Real conversations, contributed with consent, are scored turn by turn against a codebook of friction codes, human turns and AI turns alike. Every finding is traceable to the exact turn it comes from.<\/p>\n\n\n\n
Human judgment anchors the scoring. A classifier scores every turn; a human judge decides borderline cases and samples, and each judgment recalibrates the classifier. Agreement between judges is measured, not assumed.<\/p>\n\n\n\n
Zenn is model-independent. The current cases come from ChatGPT, Claude and Gemini users.<\/p>\n\n\n\n
See it work: a three-minute walkthrough<\/a>.<\/strong><\/em><\/p>\n\n\n\n For those who build and evaluate AI, it adds a view their own evaluations cannot produce: human judgment on real exchanges, followed over time, on both sides of the conversation, with every finding checkable against its source.<\/p>\n\n\n\n It does not assess content. Factual accuracy, safety and policy compliance remain the domain of existing evaluations. The two layers do not compete; one measures what the other cannot see.<\/p>\n\n\n\n Zenn: A Live Instrument for Observing Relational and Cognitive Friction in Human\u2013AI Interaction<\/a><\/strong> Before the Recommendation: A Conceptual Framework for Clinical AI Attribution, Attention, and Influence<\/a><\/strong> Relational Perception in AI Use: Theoretical Framework<\/a><\/strong> If you work on how people actually use AI (evaluation, societal impact, human oversight), I\u2019d like to compare notes.<\/p>\n\n\n\n Henri Hommersom Relational Perception, Utrecht, Netherlands. Registered Dutch CoC number 42033246. VAT number NL005444927B33<\/p>\n\n\n\n I work independently as a Relational AI Analyst, with no vendor relationships. My background is in psychiatric nursing, where reading what happens between people was the daily work.<\/p>\n\n\n\n LinkedIn<\/a> \u00b7 X<\/a> \u00b7 Privacy<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Measuring the friction in AI use that standard evaluations miss THE GAP AI platforms can see what people ask. They cannot see what happens between the person and the model while they work together. Evaluations score the model\u2019s output. Aggregate analysis counts patterns across millions of conversations. Surveys ask users afterwards. None of them follows […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-8","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/relationalperception.org\/index.php\/wp-json\/wp\/v2\/pages\/8","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/relationalperception.org\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/relationalperception.org\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/relationalperception.org\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/relationalperception.org\/index.php\/wp-json\/wp\/v2\/comments?post=8"}],"version-history":[{"count":203,"href":"https:\/\/relationalperception.org\/index.php\/wp-json\/wp\/v2\/pages\/8\/revisions"}],"predecessor-version":[{"id":315,"href":"https:\/\/relationalperception.org\/index.php\/wp-json\/wp\/v2\/pages\/8\/revisions\/315"}],"wp:attachment":[{"href":"https:\/\/relationalperception.org\/index.php\/wp-json\/wp\/v2\/media?parent=8"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n\n\n\nWHAT IT YIELDS<\/strong><\/h2>\n\n\n\n
\n\n\n\nGO DEEPER<\/strong><\/h2>\n\n\n\n
Provenance deposit \u00b7 Zenodo \u00b7 August 2026, latest version October 2026 \u00b7 record public, files restricted \u00b7 DOI 10.5281\/zenodo.21995957<\/p>\n\n\n\n
With Emma Paraschiva, Mujahid M. Altamimi & Sarah E. Curtright \u00b7 Preprint, SSRN \u00b7 July 2026 \u00b7 DOI 10.2139\/ssrn.6996320<\/p>\n\n\n\n
Preprint, Zenodo \u00b7 April 2026 \u00b7 CC BY 4.0 \u00b7 DOI 10.5281\/zenodo.19844178<\/p>\n\n\n\n
\n\n\n\nIF YOU RECOGNIZE THIS<\/strong><\/h2>\n\n\n\n
Relational AI Analyst
info@relationalperception.org<\/a><\/p>\n\n\n\n
\n\n\n\nABOUT<\/strong><\/h2>\n\n\n\n