Turn a prompt into an interactive system architecture
Describe a system and get an editable architecture diagram — components, data flows and subsystems you can drill into, explain, refine with AI and export. Every diagram is conceptual: based on publicly known patterns, with evidence labels, never a claim about a company’s real internal system.
How to generate a system design
From a one-line prompt to an editable diagram:
- Describe the system (e.g. “Design a scalable URL shortener”) or upload an architecture image.
- Generate with the built-in AI (Groq · Qwen), or start from a no-AI conceptual template.
- Explore the graph: drag nodes, open the inspector, read Explain, drill into subsystems.
- Edit directly or ask the AI to modify (“add a read replica”, “add Kafka for async events”).
- Export PNG, SVG, shareable JSON or a Markdown architecture document.
Why use it
- Honest by design. Evidence labels and a clear disclaimer — conceptual patterns, not fabricated internal services.
- Actually editable. A real graph model with validated operations, undo/redo, subsystems and versioning.
- AI that stays safe. The model returns structured JSON and graph operations — never code — validated before rendering.
- Key never in the browser. AI runs through our own secure server; the API key is server-side only, never in the client or your requests.
What is HLD (high-level design)?+
High-Level Design is the system view: the major components — clients, gateways, services, caches, queues, databases — and how requests flow between them. In this tool the HLD level shows the whole architecture and its boundaries; you can open any service from there to see its service-level and low-level design.
What is LLD (low-level design)?+
Low-Level Design is the implementation view of a single service — its internal steps, data model and dependencies. Select a service and open the LLD level to see how it works internally, derived from the same source-of-truth architecture graph (never a separate copy).
Is this a real company’s internal architecture?+
No. Every diagram is a conceptual architecture based on publicly known patterns and general information — not any organisation’s actual internal system. Components carry an evidence label (documented, common pattern, inferred, assumption) so you can see what is well-grounded and what is a reasonable guess.
How does generation work and is it private?+
You describe a system (e.g. “Design a scalable URL shortener”) or upload an architecture image, and the tool asks the AI (Groq · Qwen 3.6 27B) for a STRUCTURED architecture — JSON only, never code — which is validated before rendering. The AI runs through our own secure server: the API key is stored server-side and is never in your browser, the client bundle, or any request you send. Starter conceptual templates work with no AI at all.
Can I edit the diagram?+
Yes. Drag nodes, connect and delete edges, rename components, change categories and technologies, add nodes, auto-layout, undo/redo and snapshot versions. You can also ask the AI to modify the design (“add Redis caching between the API and the database”) — the AI returns graph operations that are validated before they touch the diagram.
What are subsystems?+
Any component can be expanded into its own sub-flow. “Explore subsystem” generates a more detailed graph for that component (e.g. a recommendation pipeline), and a breadcrumb lets you drill down and back without losing the parent architecture.
What can I export?+
PNG, SVG and a shareable JSON design file (which round-trips back into the editor), plus a Markdown architecture document covering components, data flow and assumptions. Nothing is uploaded and no API key is ever stored in exports.
Does it work for any system?+
Yes — it is a general prompt → architecture → interactive graph → explanation → drill-down → edit → export engine. Netflix, Uber, YouTube, a URL shortener, a chat app or a payment system are just examples that make it easy to understand.