ai-design-skills

Classifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency.

Tracking AI product quality over time — drift, degradation, and improvement.

Designing for informed user consent, opt-out, and human override.

A/B testing, side-by-side comparison, and preference ranking for AI outputs.

Reading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages.

Managing prompt iterations, testing changes, and tracking what works.

Designing what information goes into the context window and in what order.

Designing smooth transitions between agents and between AI and humans.

Adapting AI behavior for different cultural contexts, languages, and norms.

Showing users what the AI knows, doesn't know, and how confident it is.

Adapting AI behavior for different cultural contexts, languages, and norms.

Designing reasoning chains that produce better outputs.

Interpreting implicit and explicit feedback — edits, regenerations, abandonment.

How the AI responds to user frustration, confusion, delight, and distress.

Turn-taking, repair sequences, grounding, and dialogue structure for human-AI interaction.

Making multi-agent workflows visible and debuggable for designers and developers.

Defining what each agent does, knows, and owns in a multi-agent system.

Creating reusable, parameterised prompt templates for consistent outputs.

Designing around token limits, memory, and conversation persistence.

Defining behavioral boundaries — what the AI should and shouldn't do.

Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.

Breaking complex user goals into subtasks that agents can handle.

Translating organisational values and user expectations into system constraints.

Tailoring AI behavior for specific professional domains.

Defining behavioral boundaries — what the AI should and shouldn't do.