Prompting Agents

Direct Agent with text prompts in the chat input. You can attach context, images, and voice, and switch models at any point.

@ Mentions

Type @ in the chat input to attach specific context to your prompt. Start typing after @ and Vyre shows matching suggestions. Use @ mentions when you know which files are relevant. If you're not sure which files matter, skip it — Agent finds relevant files through its own search.

Rich Inputs

Image Input

Attach images to your prompt to provide visual context for UI work, debugging, and design implementation.

  • Drag and drop an image file into the chat input
  • Paste from clipboard with Cmd+V or Ctrl+V, including screenshots

This is useful for implementing design mockups, debugging visual issues, and referencing error messages or stack traces without manual transcription.

Voice Input

Click the microphone icon in the chat input to dictate your prompt instead of typing. Speak naturally, include technical details like file and function names, and review the transcription before sending.

Context Usage

Every chat shares a fixed context window with the model. As you add files, run tools, and exchange messages, those tokens fill up. When the window gets close to full, Vyre compresses older parts of the conversation into a summary to leave more room for new conversation.

The context ring next to your prompt input shows how full the window is at a glance. Click the ring to open the breakdown tray, which shows the total tokens used split by category:

  • System prompt: Vyre's built-in instructions for the model
  • Tools: definitions of every tool available to the agent
  • Rules & Skills: project rules and skill descriptions injected into context
  • MCP & Subagents: connected server catalogs and subagent documentation
  • Conversation: your messages, the agent's replies, and tool results

Changing Models

Use the model picker dropdown at the top of the chat input to switch models, or press Cmd / to cycle through models. The change applies to the current conversation going forward.

  • Faster models work well for quick edits and routine tasks.
  • More capable models are better for complex reasoning and multi-file refactoring.

You can switch models mid-conversation, for example when a faster model handled exploration but you need deeper reasoning for implementation.