This study presents a modular, multi-agent system for the automated review of highly structured enterprise business documents using AI agents. Unlike prior solutions focused on unstructured texts or limited compliance checks, this framework leverages modern orchestration tools such as LangChain, CrewAI, TruLens, and Guidance to enable section-by-section evaluation of documents for accuracy, consistency, completeness, and clarity. Specialized agents, each responsible for discrete review criteria such as template compliance or factual correctness, operate in parallel or sequence as required. Evaluation outputs are enforced to a standardized, machine-readable schema, supporting downstream analytics and auditability. Continuous monitoring and a feedback loop with human reviewers allow for iterative system improvement and bias mitigation. Quantitative evaluation demonstrates that the AI Agent-as-Judge system approaches or exceeds human performance in key areas: achieving 99% information consistency (vs. 92% for humans), halving error and bias rates, and reducing average review time from 30 to 2.5 minutes per document, with a 95% agreement rate between AI and expert human judgment. While promising for a wide range of industries, the study also discusses current limitations, including the need for human oversight in highly specialized domains and the operational cost of large-scale LLM usage. The proposed system serves as a flexible, auditable, and scalable foundation for AI-driven document quality assurance in the enterprise context.

The workforce will need to continually upskill in order to meet the evolving demands of industry, especially working with robotic and autonomous systems. Current training methods are not scalable and do not adapt to the skills that learners already possess. In this work, we develop a system that automatically assesses learner skill in a quadrotor teleoperation task using temporal logic task specifications. This assessment is used to generate multimodal feedback based on the principles of effective formative feedback. Participants perceived the feedback positively. Those receiving formative feedback viewed the feedback as more actionable compared to receiving summary statistics. Participants in the multimodal feedback condition were more likely to achieve a safe landing and increased their safe landings more over the experiment compared to other feedback conditions. Finally, we identify themes to improve adaptive feedback and discuss and how training for complex psychomotor tasks can be integrated with learning theories.

Classroom observation protocols standardize the assessment of teaching effectiveness and facilitate comprehension of classroom interactions. Whereas these protocols offer teachers specific feedback on their teaching practices, the manual coding by human raters is resource-intensive and often unreliable. This has sparked interest in developing AI-driven, cost-effective methods for automating such holistic coding. Our work explores a multimodal approach to automatically estimating encouragement and warmth in classrooms, a key component of the Global Teaching Insights (GTI) study's observation protocol. To this end, we employed facial and speech emotion recognition with sentiment analysis to extract interpretable features from video, audio, and transcript data. The prediction task involved both classification and regression methods. Additionally, in light of recent large language models' remarkable text annotation capabilities, we evaluated ChatGPT's zero-shot performance on this scoring task based on transcripts. We demonstrated our approach on the GTI dataset, comprising 367 16-minute video segments from 92 authentic lesson recordings. The inferences of GPT-4 and the best-trained model yielded correlations of r = .341 and r = .441 with human ratings, respectively. Combining estimates from both models through averaging, an ensemble approach achieved a correlation of r = .513, comparable to human inter-rater reliability. Our model explanation analysis indicated that text sentiment features were the primary contributors to the trained model's decisions. Moreover, GPT-4 could deliver logical and concrete reasoning as potential teacher guidelines. Our findings provide insights into using advanced, multimodal techniques for automated classroom observation, aiming to foster teacher training through frequent and valuable feedback.

Rigorous and interactive class discussions that support students to engage in high-level thinking and reasoning are essential to learning and are a central component of most teaching interventions. However, formally assessing discussion quality 'at scale' is expensive and infeasible for most researchers. In this work, we experimented with various modern natural language processing (NLP) techniques to automatically generate rubric scores for individual dimensions of classroom text discussion quality. Specifically, we worked on a dataset of 90 classroom discussion transcripts consisting of over 18000 turns annotated with fine-grained Analyzing Teaching Moves (ATM) codes and focused on four Instructional Quality Assessment (IQA) rubrics. Despite the limited amount of data, our work shows encouraging results in some of the rubrics while suggesting that there is room for improvement in the others. We also found that certain NLP approaches work better for certain rubrics.