Sep 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
The ACI 318-25 Concrete Beam Checking Assistant is a reusable Claude AI Skill for checking reinforced concrete beam designs per ACI 318-25 and gravity loads per ASCE 7-22, using US customary (imperial) units exclusively. The skill performs 10 sequential code checks, cites the specific ACI 318-25 section governing every check, shows full step-by-step calculations, flags all assumptions explicitly, and ends every session with a mandatory disclaimer requiring review by a licensed Professional Engineer (PE). This is not a beam design tool. It is a checking assistant — all outputs require PE review before use in any engineering decision or construction project. Version 1.0: Original release - dual SI/imperial. ACI section reference corrections noted. Version 2.0: Imperial units only (US customary). Converted from dual SI/imperial to Imperial units exclusively. Version 3.0: Key corrections applied following use of Version 2.0: Ec = 57,000√f'c psi per §19.2.2.1(a); minimum cover references corrected to §20.5.1.2 through §20.5.1.4; concrete unit weight stated as 150 lb/ft³ per §19.2.1; Vc method updated to ACI 318-25 §22.5.5.1 Table 22.5.5.1; minimum shear reinforcement corrected to §9.6.3.4; max stirrup spacing corrected to include 24 in upper limit per §9.7.6.2.2. FILES INCLUDED:- ACI_Beam_Checker_v3_Skill.zip — install this in Claude (Customize → Skills → + → Upload)- ACI_Beam_Checker_v3_Imperial.docx — full instructions and all 10 checks explained- Example PDF — a real analysis run showing how to use the skill REQUIREMENTS: Claude Pro subscription ($20/month) at claude.ai Inspired by the EC7 geotechnical checking skill developed by Arabel Vilas Serín (2025). A companion academic paper introducing the AI Skill paradigm for structural engineering is currently under peer review at Discover Civil Engineering Journal.
The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.
Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson· EUROMICRO Conference on Soft...· 64 citations· ⚡6
The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.
Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al.· arXiv.org· 62 citations· ⚡3
The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.
Zheying Zhang, M. Rayhan, Tomas Herda et al.· International Conference on...· 48 citations· ⚡4
This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.
Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al.· arXiv.org· 44 citations· ⚡2
The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.
Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al.· arXiv.org· 41 citations
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.