Observed Signal · Apr 6, 2026 · Best Practice / Technical Guidance · Source: UX Collective · Impact: 2/5 · Sentiment: Positive
Data models: the shared language AI and teams need
This article by Alexandra Vasquez argues that product teams must build explicit data models before prompting AI tools. Using a food-delivery example, the author explains how to name entities (User, Restaurant, Menu item, Order, Driver, Delivery, Payment, Review), cluster them into domains, and make relationships explicit (produce, reference, influence). The piece shows how a shared data model aligns designers, PMs, engineers and LLMs, improves prompt precision, and enables agentic behaviours. Vasquez demonstrates a short prompt → Figma Make prototype workflow and frames the data model as a low-cost, high-leverage step in Meet → Map → Prompt. The article connects the approach to agentic UX and previews a follow-up on turning data models into task diagrams for testing before tickets are written.
Provides practical, cross-functional guidance for aligning product teams and LLMs via explicit data models; useful for improving AI-driven product outputs and prompt engineering but not an industry-shifting announcement.
Track Figma Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Author Alexandra Vasquez published the article on UXDesign/Medium on 2026-04-06.
- The article presents a food-delivery example with eight entities: User, Restaurant, Menu item, Order, Driver, Delivery, Payment, Review.
- It recommends three relationship questions for connectors: what does it produce, what does it reference, and what does it influence.
- The author demonstrates using a data model as the basis for a short prompt to generate a focused Figma Make prototype.
- The article positions the data model as a foundational step (Meet → Map → Prompt) for reliable AI-driven product design and agentic UX.
Connected Companies & Entities
2 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Agentic AI Meets Figma: Practical Design Systems Guide
This practical guide explains how agentic AI agents are beginning to use well-structured Figma design systems as machine-readable instructions to assemble UI components. The author recounts a Storybook demo where an agent composed a customer-review component by reading components, tokens and props, and highlights technical building blocks designers must adopt: semantic tokens, exact prop and component naming, complete state coverage, auto layout, slots (Figma feature), and Code Connect mappings to code. The piece defines MCP (Model Context Protocol) as the connector agents use to read tools, notes Uber’s recent write-up using an open-source Figma Console MCP, and raises open questions about governance, visual review workflows, and who owns quality as agents accelerate component generation. The article frames agentic workflows as enabling but requiring disciplined file and process changes.
Designers Becoming AI-Native: From Files to Running Demos
A designer describes how AI tools (Claude Code, Figma Make, ChatGPT and other LLMs) have transformed product design workflows since 2024. Rather than producing static deliverables, designers can now generate working prototypes, connect design systems to code, and run research and synthesis inside LLM projects. The author introduces a practical 3C framework (Context, Components, Criteria) for transmitting tacit design knowledge to AI, argues for hands-on end-to-end prototyping to build judgment, and shows how designers can build bespoke scaffolding (e.g., an icon library built with Figma Make) to remove repetitive friction. The piece highlights shifts in where design expertise applies and how demos create persuasive momentum for shipping features.
Data, Not Models, Is the Marketing Differentiator
The article argues that in the era of large language models (LLMs) the model itself is increasingly commoditized, while proprietary enterprise data remains the primary source of competitive advantage. Prompt engineering and clear context improve model outputs, but models have limited context windows and can "forget" prior instructions; storing documents helps but does not eliminate limits. Granting governed, secure access to enterprise marketing and business data (historical performance, customer cohorts, pricing, inventory signals, sentiment) enables foundation models to produce outputs that reflect a company’s reality and accelerates the transition from dashboards to operational ML workflows. The author shares an anecdote about using an AI coding assistant plus enterprise data to compress a month’s work into a week, and recommends bringing models to governed data rather than moving data into external models to protect competitive value.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.