Tested Qoder this week. Dropped a docs link into the task screen. Asked it to generate an architecture diagram. The agent read the docs, planned the structure, and built the diagram without me touching a single tool.

Here's what happened: Opened Qoder's task screen. Selected Coding task. Pointed it to a workspace folder. Prompt: "Read these docs and create an architecture diagram." Picked Qwen 3.8 Flash (running at 0.0x Credits through September 30). Hit send.

Qoder started planning immediately. It parsed the documentation, identified the key components, mapped dependencies, and outlined the diagram structure. No back-and-forth. No manual steps. Just straight execution.

The agent opened files, extracted technical details, and started building. Every step was visible in the interface. I could pause or adjust if needed, but didn't have to. It finished and saved the diagram to the workspace.

Final result: Clean architecture diagram that accurately reflected the docs. No prompt engineering. No tool-switching. Just described the outcome and let the agent handle the workflow.

Why this matters: Qoder treats AI work as tasks, not chat. You describe what you need. The agent plans, executes, and verifies. Browser Use for signed-in web tasks. Computer Use for desktop apps. /goal for measurable outcomes. Real agent workflow in a desktop app.