Computer-use / browser agent template

Components in this architecture diagram

• Task: e.g. file expense report
• Take screenshot
• Vision-language model
• Next action
• Irreversible or sensitive?
• Ask user to confirm
• Approved?
• Stopped
• Execute in sandboxed browser
• Hand control to user
• Summary of what was done

How to use this architecture diagram template

1. Click Open in the editor. The architecture diagram opens on a new page in FlowDiagram — nothing is uploaded and there is no sign-up.
2. Rename, add or delete shapes and drag them where you want; connectors stay attached as things move.
3. Drop in vendor logos from the library — 1,160 of them, including every AWS, Azure and Google Cloud service icon — or restyle it with the colour and theme controls.
4. Prefer text? Edit the Mermaid source below and paste it in through ☰ → Import diagram (see the Mermaid editor); it imports as an editable diagram.
5. Export to PNG, SVG or PDF, or press Ctrl+L for a link that carries the whole diagram.

Mermaid source

The whole template is the text below. Paste it into FlowDiagram, keep it in Git next to the code it describes, or hand it to an AI assistant to extend.

flowchart TD
  G((Task: e.g. file expense report)) --> SS[Take screenshot]
  SS --> VLM[Vision-language model]
  VLM --> NEXT{Next action}
  NEXT -->|Click or type| RISK{Irreversible or sensitive?}
  RISK -->|Yes| CONFIRM[Ask user to confirm]
  CONFIRM --> OK{Approved?}
  OK -->|No| STOP((Stopped))
  OK -->|Yes| DO[Execute in sandboxed browser]
  RISK -->|No| DO
  DO --> SS
  NEXT -->|Blocked: login or captcha| HAND[Hand control to user]
  HAND --> SS
  NEXT -->|Done| REPORT((Summary of what was done))

Related: System architecture diagram tool · Mermaid editor · All agentic ai & multi-agent systems templates · All 521 templates