# Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration

DevFeed: [Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration](<https://devfeed.tech/articles/human-ai-interactions-as-first-class-data-a-formal-interaction-model-and-runtime-for-explainable-ai-collaboration-108254.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.40006>)

Author: Michela Taufer, Kin Ng, Ian Lumsden, Aashish Pandey, Rajasi Gore, Angelina Ju, Sukanya Moudgalya, Ewa Deelman, Sai Swaminathan

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [human computer interaction](<https://devfeed.tech/topics/human-computer-interaction.md>), [Human-AI evaluation](<https://devfeed.tech/topics/human-ai-evaluation.md>), [recording](<https://devfeed.tech/topics/recording.md>), [middleware](<https://devfeed.tech/topics/middleware.md>), [jupyterlab](<https://devfeed.tech/topics/jupyterlab.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [ai-collaboration](<https://devfeed.tech/tags/ai-collaboration.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [behavioral-analysis](<https://devfeed.tech/tags/behavioral-analysis.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [data](<https://devfeed.tech/tags/data.md>), [data-class](<https://devfeed.tech/tags/data-class.md>), [data-products](<https://devfeed.tech/tags/data-products.md>), [engagement](<https://devfeed.tech/tags/engagement.md>), [execution](<https://devfeed.tech/tags/execution.md>), [explainability](<https://devfeed.tech/tags/explainability.md>), [explainable-ai](<https://devfeed.tech/tags/explainable-ai.md>), [formal](<https://devfeed.tech/tags/formal.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [model](<https://devfeed.tech/tags/model.md>), [runtime](<https://devfeed.tech/tags/runtime.md>)

## AI overview

HAIDL represents human-AI interactions as structured data, recording computational context, requests and prompt payloads, responses, feedback, provenance, problem context, and model metadata. Its JupyterLab middleware, HAIDL-X, captures user-bot state, builds contextualized prompts, connects to AI providers, collects feedback, and stores interactions in a repository. A learning layer combines these records with notebook execution traces to derive reproducible measures such as engagement, performance, help-seeking, error-oriented use, and learning personas. The abstract presents this as a foundation for querying, replaying, and analyzing collaboration; it does not report evaluation results or compare providers.

## Source excerpt

arXiv:2610.40006v1 Announce Type: new Abstract: AI assistants are increasingly embedded in computational notebooks, scientific workflows, software engineering tools, and learning systems, yet human-AI interactions are often treated as transient prompt-response exchanges rather than durable data products, hindering reproducibility, explainability, replay, behavioral analysis, and adaptive AI support. We argue that these interactions form a new data class requiring formal representation and introduce the Human-AI Interaction Description Language (HAIDL), a formal interaction model with a Backus-Naur Form-inspired concrete syntax. HAIDL encodes each interaction as a structured object capturing computational context, user request, prompt payload, AI response, feedback, problem context, provenance, and model metadata. We integrate this vision into HAIDL-X, a middleware for JupyterLab that instantiates HAIDL by capturing user-bot state, building contextualized prompts, interfacing with AI providers, collecting feedback, and storing interactions in a repository. We add a learning layer over HAIDL that maps interaction objects and notebook execution traces into reproducible measures of user behavior, including engagement, performance, help-seeking, error-oriented use, and learning personas. HAIDL-X provides a foundation for treating human-AI collaboration as structured, queryable, replayable, analyzable data.