InfuseOS
Getting Started

Your First Conversation

Learn how to use the InfuseOS chat interface, send messages, and understand AI responses.

Your First Conversation

The InfuseOS chat interface is where you'll spend most of your time. This guide walks you through the basics of chatting with the AI and understanding its responses.

Screenshot

[IMAGE PLACEHOLDER: Main chat interface with labeled components - input area, message list, sidebar]

The Chat Interface

When you log in, you'll see the main chat interface with these key areas:

Message Area

The central area where your conversation appears. You'll see:

  • Your messages on the right
  • AI responses on the left
  • Tool executions showing what the AI is doing

Input Area

At the bottom, you'll find:

  • Text input for typing your messages
  • Attachment button for uploading files
  • Web search toggle (globe icon)
  • Model selector for choosing the AI model
  • Send button

On the left, you can:

  • Start a new chat
  • View your chat history
  • Access settings

Sending Your First Message

Click in the text input at the bottom of the screen

Type your message. For example:

Hello! What can you help me with?

Press Enter or click the Send button

Watch as the AI responds in real-time

Tip: Use Shift + Enter to add a new line without sending the message.

Understanding AI Responses

The AI's responses may include several elements:

Text Responses

Regular conversational text answering your questions or providing information.

Reasoning (Thinking)

For complex questions, you may see a collapsible "Thinking" section that shows the AI's reasoning process. This helps you understand how it arrived at its answer.

Screenshot

[IMAGE PLACEHOLDER: AI response showing expanded reasoning/thinking section]

Tool Executions

When the AI performs actions (like searching the web or accessing your integrations), you'll see tool execution cards showing:

  • Tool name (e.g., "Web Search", "Gmail Search")
  • Status (running, completed, or failed)
  • Results summary

Screenshot

[IMAGE PLACEHOLDER: Tool execution card showing web search results]

Artifacts

The AI can create documents, code files, images, and spreadsheets called "artifacts." These appear as interactive cards you can click to view, edit, or download.

Choosing an AI Model

InfuseOS offers multiple AI models with different capabilities:

ModelBest ForReasoning Levels
GPT 5.1General tasks, fast responsesLow, Medium, High
GPT 5.2Complex reasoning, analysisLow, Medium, High
Gemini 3 ProLong context, detailed workNone, Low, High
Gemini 3 FlashQuick responses, simple tasksNone, Low, High

To change models:

  1. Click the model selector dropdown near the input
  2. Choose your preferred model
  3. Your selection is saved for future conversations

Free plan users can only access GPT 5.1. Upgrade to Pro or Max for all models.

Adjusting Reasoning Level

For complex problems, you can increase the AI's reasoning depth:

  • Low: Quick responses, minimal thinking
  • Medium: Balanced reasoning
  • High: Deep analysis, step-by-step thinking

Click the reasoning dropdown (next to model selector) to adjust.

Screenshot

[IMAGE PLACEHOLDER: Model selector and reasoning dropdown]

Attaching Files

You can share files with the AI for analysis:

Click the attachment button (paperclip icon)

Select a file from your computer, or drag and drop directly into the chat

The file will appear as an attachment to your message

Send your message with context about what you want to do with the file

Supported file types:

  • Images (PNG, JPG, GIF, WebP)
  • Documents (PDF, Word, Text)
  • Spreadsheets (CSV, Excel)

Tip: You can also paste images directly from your clipboard (Ctrl/Cmd + V).

Enable web search to get real-time information:

  1. Click the globe icon in the input area to toggle web search
  2. When enabled, the AI can search the internet for current information
  3. Sources are cited in the response

Screenshot

[IMAGE PLACEHOLDER: Web search toggle enabled, showing search results with citations]

Message Actions

Hover over any message to see available actions:

  • Copy: Copy the message text to clipboard
  • Edit: Edit and resend your message (creates a new branch)
  • Retry: Regenerate the AI's response
  • Branch navigation: Switch between different response versions

Tips for Better Conversations

  1. Be specific: "Summarize my emails from last week about the project" is better than "Check my emails"

  2. Provide context: Tell the AI what you're trying to accomplish

  3. Break down complex tasks: Ask for one thing at a time for best results

  4. Use follow-ups: The AI remembers the conversation, so you can build on previous messages

What's Next?

On this page