These emerging topics represent the field's current frontier—understanding them helps designers anticipate near-future capabilities and constraints. Chain-of-Thought (CoT) Prompting Prompting LLMs to "think step by step," articulating intermediate reasoning before final answers. Dramatically improves math, logic, and multi-step reasoning. Evolved from manual prompting to being
Claude artefacts can reach out to live data sources and pull in real content every time you load them. This opens up new possibilities.
Skills have a 200-file limit which is limiting for design context. JSONL is how I got around it, and it's working better than I expected.
RAG architecture has become fundamental to AI products, enabling grounded, up-to-date, and domain-specific responses. RAG (Retrieval-Augmented Generation) Enhancing LLM responses by retrieving relevant external information before generating output. Addresses outdated training data, hallucinations, and domain-specific knowledge gaps. More cost-effective than fine-tuning; allows real-time knowledge updates. Reference: Lewis, P., Perez, E.
Understanding infrastructure helps designers appreciate performance constraints, cost considerations, and deployment options that affect product decisions. Hardware & Serving GPU (Graphics Processing Unit) Specialized processor for parallel calculations, dominant hardware for AI. GPUs excel at thousands of simultaneous calculations essential for neural networks. NVIDIA's H100 and A100 are
This is probably the most important part of the glossary for designers and these patterns and principles are directly relevant to product design practice. Understanding them enables the creation of AI experiences that are useful, usable, and appropriately trusted. Interaction Patterns Conversational UI Interface paradigm where interaction occurs through natural
These concepts are critical for responsible AI product development—understanding failure modes, safety measures, and evaluation approaches directly informs design decisions. Safety Concepts AI Safety The interdisciplinary field preventing accidents, misuse, or harmful AI consequences. Encompasses alignment research, risk monitoring, robustness, and developing norms for beneficial AI operation. Reference: Amodei,
Understanding how models are built and adapted helps designers recognize capability sources, appreciate customization options, and understand training-related behaviors and limitations. Pre-Training Concepts Pre-training The initial, computationally intensive phase of training on massive unlabeled text. During pre-training, models learn language patterns, grammar, factual knowledge, and reasoning capabilities by processing billions
Understanding how LLMs are built helps designers grasp capability limits, performance tradeoffs, and why certain behaviors emerge. This section covers the core concepts that explain how modern AI models work. Core Architecture Transformer Architecture The neural network design that revolutionized AI, introduced in 2017's "Attention Is All
Understanding the AI landscape helps designers navigate vendor decisions, cost considerations, and market dynamics. Here are a bunch of foundational concepts that we should all have some awareness of. No need to learn them by heart, but this is a good reference manual with references where possible. Foundation Models Large-scale
The agentic paradigm represents a fundamental shift from reactive chatbots to proactive AI systems that can plan and execute multi-step tasks. AI Agents / Agentic AI Systems autonomously planning, deciding, and acting to accomplish goals—moving beyond single-response chatbots to multi-step problem solvers. Combine LLMs (reasoning), tools (actions), and memory (context)
A few months of building Agent Skills in practice. Here are the small things I wish I'd known earlier - from packaging correctly to using skills as a lightweight knowledge base.