Source: VentureBeat

Figma Make: From Prototyping Sandbox to Live Visual Code Editor

Cloud design software company Figma is officially transforming its AI design assistant, Figma Make, from a prototyping sandbox into a live, visual software editor that connects natively to production codebases.

Announced today, the update allows product managers, designers, and non‑technical builders to:

1. Import an existing Git repository directly into the Figma desktop app.
2. Visually edit the application’s underlying code via the canvas.
3. Push those changes back to engineering through standard GitHub pull requests.

Engineering Governance & Licensing

• Enterprise‑grade guardrails – The integration does not bypass established engineering controls.
• Standard version‑control workflow – Figma Make operates entirely within a typical Git flow:
  • Design changes accumulate as local commits.
  • When ready to ship, the designer generates a branch and opens a pull request (PR) directly from Figma Make.
• Governance impact – Visual AI edits are subject to the same CI pipelines, security checks, and code reviews as any traditional engineering commit.
• Licensing – Figma Make remains a proprietary commercial service available to Full seats on Figma’s paid plans:
  • Professional – $16 / month per seat
  • Enterprise – $90 / month per seat
• The service interfaces cleanly with both open‑source and proprietary Git repositories without imposing new licensing restrictions on the generated code.

Breaking the One‑Way Barrier

• Original launch (May 2025) – Figma Make bridged static wireframes and interactive prototypes but was isolated from the real‑world software lifecycle.
  • Operated on a rigid, one‑way push: users could export an AI‑generated project to a new GitHub repository, but could not receive upstream changes or sync with an existing codebase.
• Today’s update – Enables a two‑way connection to any Git provider, eliminating parallel, out‑of‑sync environments.
  • Teams can connect a production or sandbox repository, highlight UI elements, and use natural language or contextual annotations to prompt Figma’s multi‑model AI.
  • The AI toggles between Anthropic’s Claude 3.7 Sonnet, Claude Opus, and Google’s Gemini models to write the underlying code.
  • The agent dynamically reads surrounding code architecture, applies visual edits, and anchors generated code to the team’s existing design‑system guidelines.

Competitive Landscape: Figma Make vs. Lovable vs. Claude Design

Navigating the “Vibe Coding” Era

The emergence of two‑way repo synchronization crystallizes the enterprise reality of the “vibe coding” era: the primary bottleneck in product development is shifting from raw engineering bandwidth to architectural governance and design intent.

Key takeaways for technical leaders:

• Figma Make is not a general‑purpose, standalone app builder; it is a highly specialized frontend optimization tool for mid‑to‑large, cross‑functional product teams.
• Ideal fit – Designers who already have access rights to their company’s existing corporate codebase.
• Enterprise adoption – Consider Figma Make if you have:
  • A mature engineering organization with a well‑defined design system.
  • Rigid repository guardrails (CI/CD, security reviews, etc.).
  • A desire to unlock faster iteration cycles while preserving governance.
• It directly addresses the technical friction felt by the 45 % of designers and 59 % of (text truncated in source).

All information reflects the announcement and documentation available as of 28 May 2026.

Product‑Manager & Developer Use‑Cases

Visual‑first product managers – those who already contribute code but prefer a visual canvas over a command‑line terminal – can treat the canvas as a local development environment. This lets non‑technical builders:

• Execute visual layouts, typography tweaks, and color changes independently.
• Offload tedious front‑end implementation to core engineers.

Zero‑to‑one / skunk‑works teams – organizations launching brand‑new projects or solo developers building lightweight SaaS products from scratch – gain the most from a code‑first, full‑stack platform like Lovable.

• Lovable natively orchestrates backend logic and database integrations (e.g., Supabase).
• It spins up functional applications rapidly without needing a pre‑existing vector infrastructure or legacy codebase.

Rapid UI wireframing – individual product managers or software engineers who want text‑prompt‑driven UI sketches without rigid design‑system constraints – are best served by the immediacy of Claude Design.

Enterprise‑grade adoption – leaders wary of over‑committing capital or locking custom builds into proprietary AI back‑ends should consider compartmentalization:

• Figma Make relies on standard Git workflows (local commits, isolated branches, mandatory engineering PR reviews).
• This enforces the same security and code‑quality standards required for enterprise stability.
• Use Figma Make as a targeted front‑end bridge for existing systems, and platforms like Lovable for external, greenfield prototyping.

By selecting the right tool for each context, leaders can adopt productive new AI tooling without risking core architectural integrity.

Why Figma Needs to Keep Innovating

• IPO recap – Figma went public on July 31 2025 at $33 per share. Immense institutional demand oversubscribed the deal by 40×, sending the stock 250 % higher to an intraday high of $115.50 on day one.
• Post‑IPO correction – By May 2026, the stock (NYSE: FIG) had fallen 81 % from its peak, trading around $21–$22, well below the IPO price, shrinking market cap to roughly $11.3 B.

Analysts cite:

1. Structural IPO pricing mechanics.
2. Low float.
3. The broader “software apocalypse” – capital rotating from traditional SaaS to AI‑native workflows.

Existential Stakes

Enterprises are shifting spend toward generative‑AI models and localized coding agents such as Claude Design, Claude Code, and OpenAI Codex. Traditional “vanilla” cloud design tools risk becoming commoditized.

Figma Make is the company’s critical counter‑offensive in the era of “vibe coding.” To restore a premium valuation, Figma must demonstrate that its platform is more than a static vector canvas—it must be an indispensable live orchestration layer where:

• Human intent,
• Enterprise design systems, and
• AI‑generated production code

seamlessly integrate.

With the new two‑way GitHub integration and governance introduced in Figma Make, the company appears well positioned to prove a viable path forward in the AI‑powered “vibe coding” development era.