Figma’s own Config 2026 recap makes its strategy clear: it shipped code layers that bring editable, inspectable code onto the canvas; Figma Motion with timelines, keyframes, exports, Dev Mode inspection, and MCP compatibility; shader fills and effects generated by the Figma agent; generative plugins that let teams create canvas-native tools by describing them; Weave tools for reusable generative workflows; and a broader Figma agent with skills, connectors, attachments, and shared chats. The through-line is not one more AI feature. It is Figma trying to make the canvas the place where code, motion, generative media, team-specific tools, and agent context all live together.

The old design-tool space was mostly canvas versus canvas: Sketch, Figma, XD, Framer, whichever product made design teams move faster. Darren Yeo, writing in UX Collective, is looking at a different fight: Figma against the possibility that the canvas becomes optional.

Figma’s enterprise strength has always depended on breadth. Designers used it first, then product managers, engineers, marketers, writers, and executives followed. The more people needed to review, comment, inspect, or reference design work, the more seats Figma could sell. The same applies for the product bench, with the rapid expansion of Slides, Buzz, Sites, and now Motion and Weave.

AI complicates that logic. If an engineer can generate or inspect UI directly inside a coding environment, or if a product team can translate structured design intent into working software without opening a shared canvas or applications, the need for passive, underutilised seats weakens. Config 2026 actually confirms this tension by bringing code layers and agent workflows closer to the main product, Figma Design. In other words, Figma is acknowledging that an increasing number of people want to participate in product and code creation without relying on traditional file-based design behaviour.

That does not kill Figma’s seat model overnight, but it does chip away at the assumption that every stakeholder must enter Figma to participate or experience design. Thus, the deeper issue goes beyond whether the team has seats at the table (canvas). The table of collaboration resides in a code-native environment and workflow, where the moment of truth shifts closer to implementation, and that reduces the number of times a team needs to return to a design file as the source of record.

The handoff-is-dead argument usually shows up as a claim about what designers can do now: move closer to implementation, write production-minded specs, and stay in the work longer. Yeo adds the business-model version of that argument. If collaboration moves into code-native environments, Figma is not just losing a handoff step. It is losing the shared room that made every reviewer, PM, engineer, and executive need a paid license.

Figma is not standing still. Even before Config 2026, the company pushed beyond static collaboration and into AI-connected workflows. Features like MCP, Code Connect, and Figma Make on local code point toward a future where design data can move more fluidly into development environments and AI tools.

That is a smarter response than pretending the canvas can win by becoming a slightly better canvas. Figma’s best path is to become the system that preserves design intent, component logic, and implementation alignment across tools. In that model, Figma is becoming an operating layer.

This is also why the company’s product strategy feels more important than its individual features. A single new AI button will not change the story. What matters is whether Figma can make design data more portable, more structured, and more useful outside the file itself. Config 2026 suggests that Figma understands this, but it also shows how hard the transition is: the company still has to make the canvas relevant in a world where many teams want to begin and finish elsewhere.

Yeo’s warning is blunt: “if teams can skip past the canvas by accelerating from intent to implementation with less translation, the value of designing to handoff vanishes.” The answer he points toward is less about file ownership and more about whether design intent can survive the trip across tools. For designers, that shifts the work from drawing the artifact to making the intent durable enough for other tools to read.

The future of design is likely to be built around reusable tokens, readable structures, and tool-agnostic metadata rather than locked files that only live well inside one platform. The winning systems will be the ones that can travel between editors, browsers, codebases, and AI agents without losing meaning.