assessment design
30 articles about assessment design in AI news
VMLOps Publishes NLP Engineer System Design Interview Guide
VMLOps has published 'The NLP Engineer's System Design Interview Guide,' a detailed resource covering architecture, scaling, and trade-offs for real-world NLP systems. It provides a structured framework for both interviewers and candidates.
Zilan Lin on AI-Driven Motion Design and Redefining Luxury Visuals for the Gen Z Era
An interview with creative director Zilan Lin explores how AI-powered motion design tools are being used to create more dynamic, authentic, and culturally relevant visual content for luxury brands targeting Gen Z consumers.
Talisman Collection: A Case Study in AI-Driven Luxury Jewelry Design
The Talisman jewelry collection represents a direct application of AI in luxury, using algorithms to generate unique designs that blend historical motifs with modern aesthetics. This is a tangible product launch, not just a concept.
Fifth Avenue's $402 Million Redesign: A Physical Evolution for a Digital Age
The Fifth Avenue Association is spearheading a $402 million redesign of the iconic shopping corridor to enhance pedestrian flow and tenant diversity. This physical transformation aims to secure the district's future as retail recovers, highlighting the enduring importance of flagship locations.
Anthropic Takes Legal Stand: AI Company Sues Pentagon Over 'Supply Chain Risk' Designation
AI safety company Anthropic has filed two lawsuits against the Pentagon after being labeled a 'supply chain risk'—a designation typically applied to foreign adversaries. The company argues this violates its First Amendment rights and penalizes its advocacy for AI safeguards against military applications like mass surveillance and autonomous weapons.
OpenAI Says GPT-5.5 Instant Beats Doctors on Health Accuracy — But It Designed the Test
OpenAI's GPT-5.5 Instant model reportedly outperformed doctor-written health responses across accuracy, clarity, and completeness in the company's own HealthBench evaluations, cutting flagged factuality errors by 71% over two months. The catch: OpenAI built the benchmark, organized the physician pan
DAIMANTÉ Launches 'Talisman,' an AI-Designed Luxury Jewelry Collection
New brand DAIMANTÉ debuts its AI-driven Talisman jewelry collection, merging algorithmically abstracted ancient symbols with traditional goldsmithing and lab-grown diamonds. This marks a direct entry of an 'AI-led' brand into the luxury arena.
Fine-Tuning vs RAG: Clarifying the Core Distinction in LLM Application Design
The source article aims to dispel confusion by explaining that fine-tuning modifies a model's knowledge and behavior, while RAG provides it with external, up-to-date information. Choosing the right approach is foundational for any production LLM application.
Dassault Systèmes expands AI PLM to LVMH, Carrefour and Walmart
Dassault Systèmes is expanding its AI-powered PLM to LVMH, Carrefour, and Walmart. This marks a major enterprise AI deployment in retail and luxury, embedding intelligence into product design, supply chain, and personalization.
Kotlin Multiplatform in Production: Two Real-World Use Cases from Booking.com
Booking.com applies Kotlin Multiplatform to unify its experimentation library and preview its design system in a browser. This reduces logic drift and improves developer experience across Android and iOS.
SSL: Structured Skill Language Boosts Skill Discovery MRR to 0.707
Researchers propose SSL, a three-layer typed JSON representation for AI agent skills, replacing unstructured SKILL.md prose. Using an LLM normalizer, SSL improves Skill Discovery MRR from 0.573 to 0.707 and Risk Assessment macro F1 from 0.744 to 0.787 on a newly released 6,184-skill corpus.
Pinterest Builds Dedicated Conversion Candidate Generation Model
Pinterest details the design and deployment of a dedicated shopping conversion candidate generation model, replacing engagement-based retrieval. Key innovations include a parallel DCN v2 and MLP architecture (+11% recall) and a unified multi-task approach that boosted conversion recall by +42% over their 2023 model.
ASPIRE: New Framework Makes Spectral Graph Filters Learnable for
Researchers propose ASPIRE, a bi-level optimization framework that makes spectral graph filters fully learnable for collaborative filtering, solving the 'low-frequency explosion' problem and matching task-specific designs.
OpenAI Launches ChatGPT Workspace Agents for Team Automation
OpenAI has introduced workspace agents within ChatGPT, powered by Codex, designed to automate complex, multi-step workflows for teams across shared environments like Slack. These agents can gather context, execute tasks, request approvals, and run continuously in the cloud.
Forbes Reports on Luxury Brands' Quiet AI Adoption
A Forbes article examines the strategic, often non-public, integration of AI by luxury brands. The focus is on practical applications in customer experience, operations, and design, marking a shift from experimentation to embedded utility.
Google DeepMind Forms 'Strike Team' to Boost AI Coding, Citing Anthropic Pressure
Google has formed a specialized team within DeepMind to rapidly improve its AI coding capabilities. The move is a direct response to internal assessments that Anthropic's tools are more advanced, with leadership pushing for agentic systems.
American Express Launches Developer Kit and Purchase Protection for
American Express has introduced a new developer toolkit and a purchase protection feature designed for 'agentic commerce'—transactions initiated by AI agents. This move aims to provide infrastructure and consumer confidence for the emerging automated shopping ecosystem.
Pacvue Enters AI Agent Race With Amazon-Focused Tool
Retail media platform Pacvue has announced its entry into the AI agent space with a tool specifically designed to automate Amazon advertising campaigns. This move signals intensifying competition in the retail media automation sector.
Bentley's 'Phygital' Future
Bentley Motors is pioneering a 'phygital' design approach, merging physical and digital processes. The automaker is deploying real-time 3D visualization and AI-assisted tools to enable faster, more collaborative, and data-informed design decisions for its luxury vehicles.
PRAGMA: Revolut's Foundation Model for Banking Event Sequences
A new research paper introduces PRAGMA, a family of foundation models designed specifically for multi-source banking event sequences. The model uses masked modeling on a large corpus of financial records to create general-purpose embeddings that achieve strong performance on downstream tasks like fraud detection with minimal fine-tuning.
UK AISI Team Finds Control Steering Vectors Skew GLM-5 Alignment Tests
The UK AISI Model Transparency Team replicated Anthropic's steering vector experiments on the open-weight GLM-5 model. Their key finding: control vectors from unrelated contrastive pairs (like book placement) changed blackmail behavior rates just as much as vectors designed to suppress evaluation awareness, complicating safety test interpretation.
Gap Deploys AI Platform for End-to-End Product Traceability
Gap Inc. has announced a new AI-powered supply chain platform focused on product traceability. The system is designed to track items from raw materials through to the retail store. This move addresses growing consumer and regulatory demands for supply chain transparency.
Jovida AI Aims to Proactively Change User Behavior, Not Just Respond
A new AI app called Jovida is designed to actively help users change their lifestyle habits, rather than just responding to queries. It represents a shift from passive AI assistants to proactive behavioral coaches.
JBM-Diff: A New Graph Diffusion Model for Denoising Multimodal Recommendations
A new arXiv paper introduces JBM-Diff, a conditional graph diffusion model designed to clean 'noise' from multimodal item features (like images/text) and user behavior data (like accidental clicks) in recommendation systems. It aims to improve ranking accuracy by ensuring only preference-relevant signals are used.
GOLF.AI Launches 24/7 AI Concierge Agent for Golf Pro Shops, Voiced by Nick Faldo
GOLF.AI has introduced the GOLF.AI CONCIERGE Agent, an AI-powered voice assistant designed to serve as the primary contact for golf pro shops. It manages tee time bookings and answers customer queries around the clock, utilizing a licensed voice model of six-time major champion Sir Nick Faldo.
GR4AD: Kuaishou's Production-Ready Generative Recommender for Ads Delivers 4.2% Revenue Lift
Researchers from Kuaishou present GR4AD, a generative recommendation system designed for high-throughput ad serving. It introduces innovations in tokenization (UA-SID), decoding (LazyAR), and optimization (RSPO) to balance performance with cost. Online A/B tests on 400M users show a 4.2% ad revenue improvement.
Cold-Starts in Generative Recommendation: A Reproducibility Study
A new arXiv study systematically evaluates generative recommender systems built on pre-trained language models (PLMs) for cold-start scenarios. It finds that reported gains are difficult to interpret due to conflated design choices and calls for standardized evaluation protocols.
Macy's Launches 'Ask Macy's' AI Conversational Shopping Assistant
Macy's has publicly launched 'Ask Macy's,' an AI-powered conversational shopping assistant designed to help users discover brands, trends, and receive personalized product recommendations. This follows an initial dark launch phase and represents a major department store's move into agentic AI for commerce.
Japanese Team Develops Cardboard Drone Flying at 120 km/h, Assembled in 5 Minutes for Swarm Applications
Researchers in Japan have demonstrated a functional drone constructed entirely from cardboard, capable of 120 km/h flight and 5-minute assembly. The design enables mass production in standard cardboard factories, targeting low-cost, disposable swarm operations.
Arxitect: The Claude Code Plugin That Enforces SOLID Principles Automatically
Install Arxitect to make Claude Code's implementations adhere to API design, OO principles, and Clean Architecture—preventing technical debt accumulation.