← Back to Home

Figma AI Team Training & Consultancy

AI UXDesignOpsPrompt Engineering
Industry
DesignOps, AI for Designers
Year
2025
Role
AI Design Facilitator
Timeline
48h
Team
10 designers

Adopted as internal standard; requested as AI consultant by multiple teams post-session

Overview

Most designers treat AI as a random generator. They type in a guess and hope for something useful. That creates a cycle of trial and error that wastes time and makes it hard to use AI for real product work. I wanted to move the team from exploring to executing by giving them a repeatable way to talk to the AI.

I presented to the whole design org to make that shift official, with an actual workflow for Figma AI. Instead of treating AI as a random visual generator, I showed how it works as a fast validation tool when you approach it the right way. I introduced the TC-EBC framework (Task, Context, Elements, Behavior, Constraints) so every prompt was complete and tied to our product goals, replacing trial and error with something repeatable.

The Process

01

Chatbot configuration

Configured our internal chatbot as a prompt translator, turning messy design notes into complete TC-EBC frameworks automatically.

02

Structured Prompt Engineering

Shifted focus from "perfect writing" to core functional questions, producing a copy-paste-ready Figma Make prompt every time.

03

Flow Validation with Figma Make

Used the initial AI output to validate the workflow's logic first, before touching visual iteration.

04

Visual Iteration

Established a "3-Iteration Rule" to move from a validated flow to a stakeholder-ready prototype in three focused cycles.

Chatbot Prompt

System PromptReusable

For any Figma Make prompt or design workflow request I share, always do the following:

  1. 1.Analyze my text (regardless of structure) and detect which information fits Task, Context, Elements, Behavior, and Constraints. Example pattern: Task: [What the screen should do] Context: [Where it fits in the product] Elements: [Literal components present] Behavior: [Key interactions only] Constraints: [Device, layout rules, visual limits]
  2. 2.Classify and rewrite my input into a copy-paste-ready TC-EBC Figma Make prompt.
  3. 3.If it's unclear which section something belongs to, make a best guess or ask me for clarification.
  4. 4.If any required section (especially Constraints) is missing or ambiguous, prompt me for specifics before giving the output.
  5. 5.Do not add extra commentary or explanation, just provide the final TC-EBC-structured prompt as your response.

Image from the session

Presentation slide 'Using Figma Make as a flow validation tool' showing the Figma Make Prompt Formatter and a Figma Make project screen

Impact

I presented this live to the whole design org. A structured prompt plus a disciplined iteration process gets a team to alignment much faster than the usual trial and error.

It changed how the team approaches AI: less random experimentation, more repeatable process. The TC-EBC framework became the internal standard for Figma AI work, and Figma Make went from a random visual generator to a validation tool people actually trust.

A few product teams reached out on their own afterward to bring the methodology into their process. Turns out structured prompt engineering is really a design systems problem, and it works a lot better once you treat it like one.