Guides
191 guides to help you use methods properly
Showing 29 of 191 guides
Artificial Intelligence
Retrieval-Augmented Generation (RAG)
What retrieval-augmented generation is, how it improves AI accuracy, and what designers and product teams need to know when working with it.
Read guideArtificial Intelligence
Human-in-the-Loop (HITL)
What human-in-the-loop design is, how it reduces risk in AI systems, and what product and UX teams need to consider when deciding where humans belong.
Read guideArtificial Intelligence
Large Language Models (LLMs)
What LLMs are, how they generate responses, and what designers and product people need to understand to work effectively with AI-powered features.
Read guideArtificial Intelligence
Hallucinations
What AI hallucinations are, why they happen, how to spot them, and how to design AI products that account for them.
Read guideArtificial Intelligence
Fine-tuning
What fine-tuning does to an AI model, when it is worth doing, and what product and design teams need to know before commissioning it.
Read guideArtificial Intelligence
System Prompts
What system prompts do, how they define an AI's role and constraints, and what product and design teams need to know when working with them.
Read guideArtificial Intelligence
Context Windows
What a context window is, how it affects AI behaviour across a conversation, and what product and design teams need to account for when building AI features.
Read guideArtificial Intelligence
Tokens and Tokenisation
What tokens are, how tokenisation affects AI behaviour and cost, and what designers and product teams need to know when building AI features.
Read guideArtificial Intelligence
Embeddings
What embeddings do, how they let AI understand meaning rather than match words, and what product teams need to know when working with semantic search or RAG.
Read guideArtificial Intelligence
AI Agents
What AI agents are, how they work, and what product and design teams need to understand when building or evaluating agentic AI features.
Read guideArtificial Intelligence
Prompt Engineering
What prompt engineering involves, how it shapes AI output quality, and what product and design teams need to know to do it well.
Read guideArtificial Intelligence
AI Bias
What AI bias is, where it comes from, how it affects real users, and what designers and product teams should do about it.
Read guideArtificial Intelligence
Foundation Models
What foundation models are, how they differ from traditional software, and what product and design teams need to know when building on top of them.
Read guideArtificial Intelligence
AI Guardrails
What guardrails are, how they stop AI behaving in harmful or off-brand ways, and what product and design teams need to consider when defining them.
Read guideArtificial Intelligence
Multimodal AI
What multimodal AI can process and generate beyond text, how it expands what is possible in product design, and what teams need to consider when using it.
Read guideArtificial Intelligence
Temperature
What temperature controls in AI models, how it affects the range and consistency of responses, and when to adjust it for different product use cases.
Read guideArtificial Intelligence
Training Data
What training data is, how it shapes what an AI model knows and assumes, and what product and design teams need to understand about its role in quality.
Read guideArtificial Intelligence
Reinforcement Learning from Human Feedback (RLHF)
What reinforcement learning from human feedback is, how it makes AI more helpful and appropriate, and what product teams need to know about its role.
Read guideArtificial Intelligence
Vector Databases
What vector databases do, how they enable semantic search and RAG, and what product and design teams need to know when working with AI systems that use them.
Read guideArtificial Intelligence
Inference
What inference is, how it differs from training, and what product and design teams need to understand about its implications for speed, cost, and reliability.
Read guideArtificial Intelligence
Synthetic Data
What synthetic data is, how it is generated, and what product and design teams need to know about its role in training, testing, and evaluation.
Read guideArtificial Intelligence
AI Transparency
What transparency in AI products involves, why users need to know when they are using AI, and how to design honest, clear communication about AI use.
Read guideArtificial Intelligence
Prompt Injection
What prompt injection attacks are, how they work, and what product and design teams need to understand to protect AI features against them.
Read guideArtificial Intelligence
Zero-shot and Few-shot Learning
What zero-shot and few-shot learning are, how they affect AI output quality, and how product teams can use them to improve results without deep technical work.
Read guideArtificial Intelligence
Model Evaluation
What model evaluation involves, how to assess whether an AI model works for your use case, and what product teams need to contribute effectively.
Read guideArtificial Intelligence
AI Latency
What latency means in AI systems, how it affects user experience, and what product and design teams can do to manage it effectively.
Read guideArtificial Intelligence
AI Safety and Alignment
What AI safety and alignment involve, why they are not just researcher concerns, and what product and design teams need to know to build responsibly with AI.
Read guideArtificial Intelligence
Neural Networks
What neural networks are, how they relate to modern AI, and what product and design teams need to know without needing to understand the mathematics.
Read guideArtificial Intelligence
Chain-of-Thought Prompting
What chain-of-thought prompting does, when it helps, and how product and design teams can use it to get more reliable outputs from AI on complex tasks.
Read guide
LET'S WORK TOGETHER
Ready to improve your product?
UX, research and product leadership for teams tackling complex digital services.
Previous feedback
I had a fantastic experience working with Andy. One of his most impressive achievements during our time at NHS HEE was masterminding a deeply complex information architecture for a new platform that brought together a large number of legacy websites.
Will Parkhouse
Senior Content Designer