# Interaction Readiness: A Framework for Building and Evaluating AI Agents in Human Roles

arXiv: https://arxiv.org/abs/2608.12358 · HTML: https://mlsanity.com/paper/2608.12358/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Builds on (most cited first, 6 of 6)

- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [Why human-AI relationships need socioaffective alignment](https://mlsanity.com/paper/2502.02528/) (2025)
- [Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trust](https://mlsanity.com/paper/2502.10844/) (2025)
- [Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation](https://mlsanity.com/paper/2602.07338/) (2026)
- [Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models](https://mlsanity.com/paper/2510.07642/) (2025)
- [Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs](https://mlsanity.com/paper/2604.19245/) (2026)

## Abstract (arXiv)

Product and engineering teams building role-bearing AI agents face an evaluation gap: an agent can produce accurate, safe, and fluent content while still failing the behavioral requirements of its assigned role. This paper introduces Interaction Readiness as a framework for specifying and evaluating that missing layer of performance. The framework separates content specifications, which govern what an agent knows and says, from interaction specifications, which define how an agent should conduct itself in a role-governed exchange. Interaction specifications require teams to define role purpose, authority boundaries, recurring situations, boundary cases, repair behaviors, and audit criteria before deployment. We operationalize interaction readiness through four agent operations: understanding purpose, calibrating authority, managing tone, and repairing breakdowns. Using StudyChat, a public dataset of student interactions with an AI tutoring agent, we show that content accuracy and interaction quality are independent dimensions: an agent may be factually correct while failing as a tutor, or interactionally sound while technically wrong. The most persistent failure is authority miscalibration: the agent often knows how to answer, but not whether, when, or how the tutor role permits it to answer. The paper translates these findings into a specification template and audit procedures that product and engineering teams can apply before and after deployment