AI · Systems Thinking

AI Chat Patterns

Designing the interaction framework for Dayforce's first agentic AI experience—establishing reusable patterns for how users communicate with intelligent systems

AI Chat Patterns
Click to enlarge
The Problem

No patterns for intelligent UI

When Dayforce launched AI capabilities, every product team interpreted "AI experience" differently. Some shipped chatbots. Some added magic buttons. Some built inline suggestions. The result: a fragmented, inconsistent AI layer with no shared mental model for how users should interact with agentic features.

The deeper problem: AI interactions don't follow the same rules as traditional UI. Users needed to understand what the AI can do, what it's doing right now, and when to trust its output—none of the existing design system components handled this.

Solution

A reusable AI interaction framework

01 Conversation Thread
Human + AI message patterns
Standardized message anatomy: user input, AI response, inline citations, confidence indicators. Consistent across every AI entry point in the product.
02 Agentic Action Cards
Surfacing what the AI can do
Structured card pattern for AI-suggested actions. Shows intent, scope, and consequence before the user commits—critical for trust in an enterprise context.
03 Processing States
Transparent AI thinking
Skeleton patterns, streaming text, and "thinking" indicators that make latency feel intentional rather than broken—adapted from the loading states system.
04 Prompt Scaffolding
Reducing blank canvas paralysis
Contextual suggested prompts scoped to the user's current workflow. Lowers the entry barrier and teaches users what's possible without documentation.
Systems Thinking

Built on the existing token foundation

Rather than building a parallel AI component library, I extended the Everest Design System token architecture to accommodate AI-specific states. New semantic tokens for AI contexts (ai.surface, ai.border.active, ai.text.streaming) slotted into the existing three-tier hierarchy—keeping the system coherent rather than forked.

Impact

A shared language for AI

1
Unified framework adopted across all AI features
32+
Product teams using shared AI interaction patterns
0
New component forks — AI patterns built on existing token system
Next Project
Data Tables →