Here\u2019s what we\u2019ll cover:<\/h3>\n\n\n\n
What is experience architecture?<\/a> Experience architecture is the structural layer of product design. It provides an \u201cinvisible\u201d scaffolding that complex, generative AI systems use in real-time responses to create experiences that surface the right things at the right time and in the right places. Good UX design for these runtime experiences enables performant, human-centred interactions where people understand what the AI is doing, can trust its outputs, and feel confident engaging with it. Experience architecture makes that possible.\u00a0<\/p>\n\n\n\n To create systems that work well with human communication patterns, experience architects partner closely with conversation designers. Conversation design<\/a> defines the flow, tone, and recovery patterns that make interactions feel natural. Experience architecture provides the structural models and signals that keep those interactions coherent across contexts, modalities, and agents.<\/p>\n\n\n\n Experience architecture defines the rules of engagement for dynamically generated interactions, answering new types of experience questions:<\/p>\n\n\n\n The answers to these questions live in the underlying experience models and frameworks. By shaping how dynamic AI behaviours unfold, experience architecture ensures interactions are not only functional but also seamless and delightful for users.<\/p>\n\n\n\n Return to the top<\/a><\/p>\n\n\n\n An important distinction to recognise when building AI systems is the difference between design time<\/em> and runtime<\/em> experiences. Design time experiences shape the system\u2019s capabilities, while runtime experiences shape how someone perceives and experiences those capabilities. Both are fundamental, but runtime design ultimately defines whether an interaction feels coherent, human-centred, and reliable.\u00a0<\/p>\n\n\n\n Design time defines the models, workflows, ontologies<\/a>, guardrails, and prompts<\/a> that determine how the AI should operate. It focuses on prompt editors, training dashboards, orchestration tools, and such that prioritise usability for builders and admins who configure these systems.<\/p>\n\n\n\n Runtime is the moment of use, or when the system is actively working with real data, users, and contexts. The runtime experience centres on what end users encounter when they engage with the system: signals like status indicators, citations, agent hand-offs, memory, and guardrails that make the system\u2019s behaviour understandable, trustworthy, and smooth in real time.<\/p>\n\n\n\n Return to the top<\/a><\/p>\n\n\n\n To make this more tangible, let\u2019s look at a few examples of experience architecture that we use to make experiences on the Agentforce platform better for the people who use it.<\/p>\n\n\n\n Status indicators<\/strong> are ways that a system communicates to its users what\u2019s happening and what it has done. One of the hallmark heuristics \u2013 or cues \u2013 of good interaction design, these take on new forms for AI systems to keep people informed and give appropriate feedback. What do they do<\/strong>: Shows progress<\/em> (\u201cretrieving\u2026\u201d, \u201cgenerating\u2026\u201d, \u201cagent A is planning\u2026\u201d).<\/p>\n\n\n\n How do they help meet people\u2019s goals<\/strong>: Reduces uncertainty, provides reassurance that the system is active, and gives clear expectations for wait time.<\/p>\n\n\n\n There are four common types of status indicator in current AI systems:<\/p>\n\n\n\n Citations<\/strong> in traditional contexts are references that attribute information to external sources. They\u2019re used in research, journalism, legal writing, and beyond to signal important contributions to an author\u2019s work. Similarly, citations for generative AI systems provide people with an affordance, or clues, to understand what contributed to the system\u2019s output.<\/p>\n\n\n\n When do they show up<\/strong>: After the system produces an output.<\/p>\n\n\n\n What do they do<\/strong>: They show evidence of where information came from, which subsystems or agents contributed, what documents or APIs were used.<\/p>\n\n\n\n How do they help meet people\u2019s goals<\/strong>: Builds trust in the system and provides an opportunity for verification. Have a way to check the provenance of an answer or follow links for more context.<\/p>\n\n\n\n Agent handoff<\/strong>: This occurs when the AI system reaches a point where a person needs to step in, such as when a customer service agent is unable to fulfill the user\u2019s request. The agent needs to gracefully transfer that interaction to a human agent who can help the person accomplish their goal or clearly explain why the goal can\u2019t be met.<\/p>\n\n\n\n When does this show up<\/strong>: The AI system reaches a point where a person needs to step in, such as when the task requires judgment, empathy, or domain knowledge the system can\u2019t provide.<\/p>\n\n\n\n What does it do<\/strong>: Shifts control from the AI to a human, carrying forward context like conversation history, user intent, and relevant data so the human doesn\u2019t start from scratch. Agent handoff can also happen from human to agent, when the agent takes over from the human.<\/p>\n\n\n\n How does this help meet people\u2019s goals<\/strong>: Provides a smooth, transparent transition that preserves trust, minimises user frustration, and empowers the human to continue seamlessly.<\/p>\n\n\n\n Return to the top<\/a><\/p>\n\n\n\n While many aspects of designing for AI experiences are just good UX design, there are a few key pillars that make an experience architecture practice more successful.<\/p>\n\n\n\n To design the experience architecture for AI-driven interactions, work with product managers, engineers, and software architects to understand existing capabilities and the systems that drive them. <\/p>\n\n\n\n It\u2019s critical to understand the software architecture and how AI systems are generating interactions: what are the inputs, what happens with those inputs, and what the system outputs in response. These are the building blocks for your experience architecture. <\/p>\n\n\n\n For example, on the Agentforce platform, the reasoning engine is the heart and soul of generating dynamic interactions. Understanding how that works helps designers create interaction patterns that are aligned with how the system actually performs and accurately reflect it in runtime experiences. <\/p>\n\n\n\n Mapping the experience architectures, frameworks, experience models, and principals is essential. Make a map of where dynamic experiences are happening in the UI, what\u2019s happening, and when it\u2019s happening. Define how and where that happens across a user\u2019s journey and assess how well the current capabilities are meeting users\u2019 goals. <\/p>\n\n\n\n Look for examples of how this is done elsewhere and draw on analogous patterns for ideas and inspiration. <\/p>\n\n\n\n When <\/strong>using your system, what do people want to achieve and how should people feel when interacting with your product or service?<\/p>\n\n\n\n From hand-drawn sketches to AI-generated interactive prototypes, make your ideas tangible. Do it in ways that let others fluidly collaborate with you. Although a common tendency is to start UX with designing for design time experiences, it’s far more effective to begin with working out the desired runtime experience. When you\u2019re clear on what you want the system to generate, it\u2019s much faster to craft a usable and efficient design time experience.<\/p>\n\n\n\n Return to the top<\/a><\/p>\n\n\n\n Experience architecture is critical to your AI design practice. It\u2019s the structural layer of product design that keeps dynamically generated experiences coherent, consistent, and aligned with intended outcomes. It serves as the foundation that allows AI systems to deliver clarity and reliability at runtime. <\/p>\n\n\n\n Beyond being part of the product itself, it defines the outcomes that matter most for people<\/a> and the holistic journeys that help them accomplish those outcomes across every touchpoint.\u00a0<\/p>\n\n\n\n
A good runtime experience relies on good architecture<\/a>
Three examples of how experience architecture shows up<\/a>
Get to know the building blocks of success<\/a>
Architect your AI design practice<\/a><\/p>\n\n\n\nWhat is experience architecture?<\/h2>\n\n\n\n
\n
A good runtime experience relies on good architecture<\/h2>\n\n\n\n
\n\t\t\t\tTake a Deeper Dive\t<\/h2>\n<\/div>\n\n\n\n
![\"Illustration](\"https:\/\/www.salesforce.com\/ap\/blog\/wp-content\/uploads\/sites\/8\/2025\/07\/KH_Adobe_Pattarin.png?w=300\")
<\/span>\t\t\t<\/figure>\n\t\t\t\t\n\t\t\tDesign Jobs Are Getting an AI Makeover\t\t<\/h4>\n\t<\/a>\n<\/div>\n\n<\/div>\n\n\n\n
![\"Colorful,](\"https:\/\/www.salesforce.com\/ap\/blog\/wp-content\/uploads\/sites\/8\/2025\/07\/CxD_Adobe_Tida.png?w=300\")
<\/span>\t\t\t<\/figure>\n\t\t\t\t\n\t\t\tWhat is Conversation Design and How Does It Shape AI\u2019s Behaviour?\t\t<\/h4>\n\t<\/a>\n<\/div>\n\n\n\n
![\"On](\"https:\/\/www.salesforce.com\/ap\/blog\/wp-content\/uploads\/sites\/8\/2025\/07\/jtbd_adobe_Visual_Generation.png?w=300\")
<\/span>\t\t\t<\/figure>\n\t\t\t\t\n\t\t\tHere Are Ways AI Helps Designers Rethink Skills and Jobs To Be Done\t\t<\/h4>\n\t<\/a>\n<\/div>\n\n\n\n
![\"Illustration](\"https:\/\/www.salesforce.com\/ap\/blog\/wp-content\/uploads\/sites\/8\/2025\/04\/what-is-ontology.png?w=300\")
<\/span>\t\t\t<\/figure>\n\t\t\t\t\n\t\t\tWhat is Ontology and Its Role in Agentic Experience Design?\t\t<\/h4>\n\t<\/a>\n<\/div>\n\n<\/div>\n<\/div>\n\n\t<\/div>\n<\/div>\n\n\n\n
Three examples of how experience architecture shows up <\/h2>\n\n\n\n
1. Making system status visible<\/h3>\n\n\n\n
When do they show up<\/strong>: While the system is working.<\/p>\n\n\n\n\n
2. Attributing sources and evidence<\/h3>\n\n\n\n
3. Handing off to humans<\/h3>\n\n\n\n
Get to know the building blocks of success<\/h2>\n\n\n\n
Cross functional collaboration<\/strong> <\/h3>\n\n\n\n
Understanding your AI <\/strong><\/h3>\n\n\n\n
Experience modeling<\/strong><\/h3>\n\n\n\n
Market awareness<\/strong><\/h3>\n\n\n\n
Understanding the outcomes that matter most to the people <\/strong><\/h3>\n\n\n\n
Sketch the possibilities<\/strong><\/h3>\n\n\n\n
Architect your AI design practice<\/h2>\n\n\n\n