An AI that confidently provides wrong answers erodes user trust more than one that admits uncertainty. Designing for "humility" by showing confidence indicators, citing sources, or even refusing to answer is a superior strategy for building long-term user confidence and managing hallucinations.

People struggle with AI prompts because the model lacks background on their goals and progress. The solution is 'Context Engineering': creating an environment where the AI continuously accumulates user-specific information, materials, and intent, reducing the need for constant prompt tweaking.

To build trust, users need Awareness (know when AI is active), Agency (have control over it), and Assurance (confidence in its outputs). This framework, from a former Google DeepMind PM, provides a clear model for designing trustworthy AI experiences by mimicking human trust signals.

To trust an agentic AI, users need to see its work, just as a manager would with a new intern. Design patterns like "stream of thought" (showing the AI reasoning) or "planning mode" (presenting an action plan before executing) make the AI's logic legible and give users a chance to intervene, building crucial trust.

Building features like custom commands and sub-agents can look like reliable, deterministic workflows. However, because they are built on non-deterministic LLMs, they fail unpredictably. This misleads users into trusting a fragile abstraction and ultimately results in a poor experience.

As AI models are used for critical decisions in finance and law, black-box empirical testing will become insufficient. Mechanistic interpretability, which analyzes model weights to understand reasoning, is a bet that society and regulators will require explainable AI, making it a crucial future technology.

AI's unpredictability requires more than just better models. Product teams must work with researchers on training data and specific evaluations for sensitive content. Simultaneously, the UI must clearly differentiate between original and AI-generated content to facilitate effective human oversight.

The New York Times is so consistent in labeling AI-assisted content that users trust that any unlabeled content is human-generated. This strategy demonstrates how the "presence of disclosure makes the absence of disclosure comforting," creating a powerful implicit signal of trustworthiness across an entire platform.

Unlike many AI tools that hide the model's reasoning, Spiral displays it by default. This intentional design choice frames the AI as a "writing partner," helping users understand its perspective, spot misunderstandings, and collaborate more effectively, which builds trust in the process.