tldraw

tldraw (tldraw.com) is a very good free whiteboard that has grown into one of the most influential AI-native canvas products of the last two years. The free hosted app gives anyone an infinite canvas with shapes, arrows, sticky notes, freehand drawing, and multiplayer collaboration. What sets tldraw apart is its 'computer' feature: an AI mode where you can sketch a rough wireframe or write a prompt in a frame and tldraw generates working HTML/React/SVG output inside the same canvas, which you can then edit, iterate on, and connect to other frames as a live app. Beyond the app, tldraw is best known as a developer SDK: the tldraw React library powers whiteboarding, canvas UI, and node-and-edge editors inside dozens of AI products (agent builder canvases, workflow tools, mind maps), and includes hooks for embedding LLM-driven behaviors directly onto shapes. The company offers a permissive license for personal and prototyping use, a paid Business License for embedding in commercial products, and a hosted Sync backend for real-time collaboration. tldraw has become a de facto standard for anyone building a spatial UI, an agent 'thinking canvas', or a diagram tool with AI.

Practical evaluation and buying guide

Evaluate tldraw against one bounded production task, not a broad automation promise. Build a test set of at least 20 representative jobs, including malformed inputs and difficult edge cases. Record median completion time, correction rate, failure rate, and cost per successful output. A useful pilot identifies both time savings and the exact points where a person must inspect or approve results.

Test these capabilities first: Infinite-canvas whiteboard with real-time multiplayer; AI 'computer' mode — sketch to working UI/HTML in the same canvas; React SDK for embedding a canvas in your own app; Powers agent builders, workflow tools, and diagram tools across the AI ecosystem; Hosted Sync backend for collaboration. Verify every capability with your own data and permissions. Inspect exports, logs, errors, and recovery behavior rather than judging a polished demo. Reliability and predictable output usually matter more than the best single result.

Pricing evidence currently recorded is: Free App: Free; SDK (personal/prototype): Free; Business License: Contact sales. Direct vendor homepage and pricing requests returned no response in this scheduled environment, so confirm plan names, billing units, included usage, overages, concurrency limits, support, and cancellation terms with the vendor. Never interpret a missing price as “free.” Include model calls, third-party APIs, compute, implementation, monitoring, and human review when calculating total cost.

Reported advantages include Excellent infinite-canvas interaction model for spatial applications; React SDK provides a serious foundation instead of a closed whiteboard; Real-time multiplayer and hosted Sync reduce collaboration engineering. Main cautions include Commercial embedding requires a Business License with unverified custom pricing; A canvas SDK still requires substantial product and interaction design work; AI-generated UI needs accessibility, security, and browser testing. Convert each claim into a measurement: compare median task time for speed, use blind review for quality, and ask a second teammate to repeat setup from written instructions. Run the pilot long enough to expose rate limits, intermittent failures, and workload variation.

Before production, confirm authentication, role-based access, audit logs, encryption, deletion controls, retention, data residency, subprocessors, and whether customer data trains models. Technical teams should test API versioning, retries, idempotency, observability, and export paths. Simulate expired credentials, upstream outages, timeouts, invalid responses, and partial completion. Document who owns each alert and how users fall back to the old process.

The verdict is conditional: tldraw deserves a pilot when its specific workflow matches a measurable bottleneck and the team can supervise exceptions. It is a weaker fit when the organization requires fully predictable costs, offline operation, strict procurement evidence, or zero-touch accuracy. Keep source data, make the pilot reversible, and expand only when measured results beat the current workflow.