AI is Your New Intern, and the Prompt is Your Brief

In a significant shift in how design professionals approach artificial intelligence, the industry is moving away from the fear of AI replacing designers towards a more collaborative and empowering perspective. This evolution, highlighted in the second part of the "UX & AI" series, reframes AI not as a competitor, but as a powerful new assistant. The core of this new paradigm lies in understanding the "prompt" – the instructions given to AI – not as a technical hurdle, but as a sophisticated form of communication that designers are already adept at.

The foundational myth that AI is poised to replace designers has been replaced by a more accurate and actionable understanding: AI is a fast, tireless, and well-read intern, entirely dependent on human direction, judgment, and accountability. This perspective shifts the focus from a battle for relevance to an opportunity for enhanced productivity and creativity. The second installment of the series delves deeper, positing that the mastery of AI prompting is not a nascent technical skill, but an extension of a competency designers have honed over years: the art of crafting effective briefs.

The Unrecognized Skill: Brief-Writing as Prompt Design

The article argues that designers and researchers already possess the fundamental skills required for effective AI prompting. The ability to articulate a clear understanding of a task for another party to execute, defining goals, audience, constraints, tone, and providing essential context, is a cornerstone of professional design practice. Whether it’s a design brief, a research brief, a creative direction document, or a UX researcher’s discussion guide, these professional activities are direct precursors to crafting AI prompts.

"Every designer who has ever written a design brief, a research brief, a creative direction document, or a content strategy brief has done exactly this," the article states. "Every UX researcher who has written a discussion guide has done this. Every design lead who has briefed a copywriter, an illustrator, or a junior designer has done this." This recontextualization suggests that the much-hyped term "prompt engineering," borrowed from software development and emphasizing technical capability, overlooks the deeply ingrained communication and design skills designers already wield.

The implications of this insight are profound. Designers and researchers who have invested in the craft of clear, specific, and contextually rich communication are inherently better prepared for AI integration than those approaching it as a purely technical challenge. This positions them for a significant advantage in the evolving landscape of digital product development.

Parallels Between Briefs and Prompts

The structural similarities between effective design briefs and effective AI prompts are striking and instructive. A strong design brief, much like a well-crafted prompt, is characterized by several key elements:

• Clear Goals: A brief specifies the desired outcome, not merely the task. For instance, instead of "homepage redesign," a strong brief defines a goal like: "We need a homepage that converts first-time visitors from paid search into newsletter subscribers for a financial planning product targeting working professionals aged 28 to 40." Similarly, an effective AI prompt moves beyond generic requests like "Write me some onboarding copy" to specific instructions such as: "Write three variations of a welcome message for a financial planning app. The user is a working professional in their early thirties who has just connected their first bank account. The tone should be encouraging but not patronizing. Maximum 40 words per variation." The specificity of the goal directly correlates to the usefulness of the output.

• Audience Specificity: A good brief provides enough detail about the target audience to inform decision-making. Moving beyond vague descriptors like "urban professionals," a more effective brief might detail: "first-generation professionals in Tier 2 Indian cities, primarily mobile-first, with moderate financial literacy and a high degree of trust skepticism toward financial institutions." Likewise, when prompting an AI, detailing the user’s background, context, knowledge level, and specific situation significantly enhances the relevance of the generated output. The AI, unlike a human team member, has no pre-existing knowledge of the user base unless explicitly provided.

• Defined Constraints: Constraints such as budget, timeline, technical limitations, brand guidelines, and regulatory requirements are crucial for effective briefs. These are not seen as obstacles but as necessary conditions for creativity to yield practical results. An unconstrained brief often leads to unconstrained, and therefore useless, output. In the context of AI prompting, specifying format, length, and tone constraints, along with defining what the output must not do, helps the AI perform significantly better by understanding the boundaries of the solution space.

• Rich Context: A design brief provides essential background information, including the project’s origin, previous attempts, organizational context, and challenged assumptions. This context empowers the recipient to make intelligent decisions when explicit guidance is absent. Similarly, AI prompts benefit from rich context. Since AI has no inherent memory of a project, organization, users, or past decisions, each prompt represents a fresh start. Treating a prompt as a context-setting document, rather than a mere command, leads to consistently superior results compared to treating it as a simple search query.

The Anatomy of an Effective Prompt

Drawing on over 25 years of experience, the article outlines a framework for prompt design that directly applies brief-writing principles. This structure, while not a rigid formula, serves as a guide for articulating what the AI needs to know, mirroring the thinking process behind effective brief-writing. This approach has been observed to yield better outputs across various AI applications, including research synthesis, microcopy generation, user flow mapping, and competitive analysis.

The article suggests that the most valuable skill for a UX professional is the ability to communicate design intent with precision, specificity, and contextual richness. AI amplifies the importance of this skill, making its impact immediate and visible.

Designers’ Existing Strengths in AI Prompting

The design community’s tendency to approach AI prompting with intimidation is seen as unwarranted, given their inherent capabilities. Designers are uniquely equipped with several critical skills that translate directly to AI interaction:

• Ambiguity Management: Design practice inherently involves making decisions with incomplete information. Designers are skilled at understanding problems well enough to progress without resolving every uncertainty. This is precisely the challenge of prompting. Judgments about the most important context, binding constraints, and likely failure modes are constantly exercised.

• Iteration: Design is fundamentally iterative. Producing, evaluating against criteria, identifying shortcomings, and revising is a standard process. Prompting mirrors this iterative nature. The first prompt rarely yields the optimal output. Practitioners who treat the initial output as a starting point, critically evaluate its shortcomings, and refine the prompt accordingly, achieve superior results.

• Audience Empathy: The core of UX is understanding the end-user—their mental models, contexts, and needs. Applied to prompting, this means understanding the AI as a system with specific capabilities and limitations, and designing prompts to leverage these capabilities while mitigating limitations. Approaching AI with curiosity about its information processing, akin to user research, accelerates prompting fluency.

• Specification: The ability to precisely describe intended outputs—whether UI, interaction, or content specifications—for others to execute correctly is a hallmark of design. Prompting is a form of specification applied to AI. The more precisely a designer can specify requirements and anticipate potential AI misinterpretations, the better the outputs will be.

Common Failure Modes in Prompting

Understanding why prompts fail is as crucial as understanding why they succeed. The article notes that the failure modes of prompting closely align with those of design briefs, giving designers a head start in diagnosing and rectifying issues. These include:

• Vague Objectives: Lack of clear, measurable goals leads to generic or irrelevant outputs.
• Undefined Audience: Without a clear understanding of who the output is for, the AI cannot tailor its response effectively.
• Missing Context: Insufficient background information prevents the AI from making informed decisions.
• Unrealistic Constraints: Overly restrictive or contradictory constraints can lead to unworkable outputs.
• Ambiguous Language: Unclear phrasing or jargon can result in misinterpretations by the AI.

Shifting the Conversation: Design’s Role in AI Integration

The insight that prompting is essentially brief-writing has significant practical implications for how organizations approach AI integration. The prevailing assumption, fueled by the "prompt engineering" framing, is that AI fluency is primarily a technical capability, best suited for engineers, data scientists, and technical product managers. This perspective is identified as flawed within the UX context and is leading to suboptimal AI adoption decisions that underutilize design teams.

In most product organizations, designers and researchers are best positioned to craft effective prompts for design and research tasks. They possess a deep understanding of the user, the design problem, and what constitutes a valuable output. Their years of developing brief-writing skills directly translate to effective prompting. Designers who remain on the periphery of AI adoption conversations, waiting to be instructed, are ceding ground that rightfully belongs to them.

The World Economic Forum’s Future of Jobs Report 2025 projects AI and big data fluency as the fastest-growing skills demanded by employers through 2030, with a significant shift in core skills expected. Designers who recognize their brief-writing competence as a direct pathway to AI prompting fluency are strategically positioned to thrive in this evolving landscape.

Applying LucyUX to Prompt Design

The LucyUX framework—Listen, Understand, Conceptualize, Yield—is presented as a robust model for prompt design, applicable with the same rigor as any other design challenge.

• Listen: This involves understanding the user’s needs and the problem space. In prompt design, it translates to thoroughly grasping the AI’s capabilities and limitations, and the specific problem the prompt aims to solve.
• Understand: This stage focuses on deeply comprehending the problem and the context. For prompts, it means dissecting the requirements, identifying potential ambiguities, and defining the desired outcome with precision.
• Conceptualize: This is where creative solutions are generated. In prompt design, it involves brainstorming different ways to articulate the request, considering various phrasing, and structuring the prompt for maximum clarity and effectiveness.
• Yield: This final stage is about delivering the solution. For prompts, it means generating the output, evaluating it against the initial goals, and iterating based on the results.

The Peril of "Prompt Engineering" as a Technical Skill

A significant risk emerges when AI prompting is exclusively framed as "prompt engineering," a technical skill. This framing positions it as the domain of technical roles, with engineers defining system prompts and product managers orchestrating AI workflows. Designers, in this scenario, are relegated to a "creative" role, tasked with making AI-generated outputs aesthetically pleasing rather than being involved in defining their purpose and utility.

This division risks perpetuating a persistent problem in product development: the separation of technical execution from user understanding. AI systems designed without UX involvement at the prompting and workflow level are more likely to optimize for technical feasibility rather than genuine human utility.

The role of UX professionals in AI product development extends beyond merely refining AI outputs. It involves shaping the AI’s behavior from its inception—through system prompts that define its presentation, workflow design that dictates its tasks, and evaluation frameworks that ensure its outputs genuinely serve users. These are all fundamentally brief-writing and UX challenges, and they rightly belong to UX professionals.

Research by the Nielsen Norman Group on AI in design workflows supports this view. The designers adding the most value in AI-integrated teams are not necessarily those most fluent with AI tools, but those who apply UX thinking to how AI should behave, what it should produce, and how users should experience it. Tool fluency is a baseline requirement; shaping the tool’s function is the strategic opportunity.

Actionable Steps for Designers This Week

To bridge the gap between existing skills and AI proficiency, designers are encouraged to undertake a practical exercise:

1. Select a Recent Piece of Work: Choose a document produced in the past week that required communicating design direction to a collaborator or client. This could be a research discussion guide, microcopy, a user flow, or a competitive analysis.
2. Identify the Implicit Brief: Analyze the chosen work and articulate the underlying brief. What was the goal? Who was the audience? What were the constraints? What did success look like?
3. Write the Explicit Brief: Formulate this brief as if presenting it to a junior designer joining the team who has no prior project knowledge.
4. Use the Brief as a Prompt: Input this explicit brief into an AI tool of choice.
5. Compare and Analyze: Evaluate the AI’s output against the original work. Assess where the AI’s output matches the quality of the designer’s work, where it falls short, and what this reveals about the designer’s unique knowledge and judgment. Crucially, note any surprising directions or variations the AI might suggest.

This comparison is designed to be instructive, highlighting the AI’s potential to free up time by handling certain tasks, revealing what unique contributions designers make that AI cannot replicate, and uncovering unforeseen creative avenues. These outcomes are most likely to occur when prompts are well-defined and specific.

A Believer’s Perspective: The Strategic Opportunity

The design community faces a dual risk: excessive intimidation and insufficient strategic ambition regarding AI. The intimidation stems from the technical framing of prompting, which masks the fact that designers have been building these communication skills throughout their careers. The lack of strategic ambition is evident in the current focus on individual tool usage, overlooking the more critical question of how UX professionals can shape the AI systems that will define future digital products.

The article posits that "brief-writing is the prompt. Prompt design is UX. The interface between human intent and AI output is a design challenge—and it belongs to designers." Practitioners who internalize this principle, shifting from viewing AI prompting as a technical skill to be learned from engineers, and instead embracing it as an extension of their existing communication discipline, will experience accelerated AI fluency. This growth will not be due to technical tricks, but from recognizing and leveraging an already developed competence. The recipient of their briefs has changed, but the fundamental skill remains the same.

The ongoing "UX & AI" series continues with "Part 3: Stop Calling It Empathy: AI Does Not Feel Anything," which aims to address the tendency within the design industry to anthropomorphize AI. This imprecise and potentially dangerous language shapes design decisions in ways that can disadvantage the very human beings design is intended to serve. The series underscores the critical need for clear, objective language and a grounded understanding of AI’s capabilities and limitations.