Understanding AI Responses
X21 uses Claude Sonnet 4, Anthropic’s advanced AI model, to understand your requests and interact with Excel. This guide explains how responses work and what to expect.The AI Model
Claude Sonnet 4
X21 is powered by Claude Sonnet 4 (claude-sonnet-4-20250514), which provides:- Advanced reasoning about spreadsheet operations
- Understanding of complex data relationships
- Natural language processing for Excel tasks
- Multi-step problem solving
Capabilities
- Context awareness: Understands your workbook structure, selected ranges, and sheet names
- Tool orchestration: Breaks down complex requests into appropriate Excel operations
- Explanation: Provides reasoning for its decisions
- Learning: Adapts responses based on your feedback
Response Streaming
Real-Time Updates
When you send a request, responses arrive in real-time:- Immediate start: Text begins appearing within seconds
- Token-by-token: Words stream as the AI generates them
- Live updates: No waiting for complete responses
- Cancellation: Stop generation anytime with the Cancel button
What You See
Thinking Blocks
What Are Thinking Blocks?
Thinking blocks show the AI’s reasoning process before it acts: Example:Why They’re Useful
- Transparency: See how the AI approaches your request
- Trust: Understand the logic behind actions
- Learning: Discover better ways to phrase requests
- Debugging: Identify when the AI misunderstands
Thinking Duration
- Complex requests: Longer thinking (5-10 seconds)
- Simple operations: Brief thinking (1-2 seconds)
- The AI has a 1,600 token “thinking budget” per request
Response Components
Text Blocks
Plain text explanations and answers:- Markdown formatting (bold, italic, lists)
- Syntax highlighting for code
- Excel range links (clickable)
Tool Use Blocks
When the AI proposes Excel operations:- Pending: Awaiting your approval
- Approved: Ready to execute
- Rejected: Declined by you
- Completed: Successfully executed
- Errored: Failed with error message
Code Blocks
Formula examples and references:Token Usage
What Are Tokens?
Tokens are units of text the AI processes:- ~4 characters = 1 token
- “Hello” = 1 token
- “spreadsheet” = 2 tokens
Token Counter
The status bar shows real-time token usage:Token Limits
- Conversation limit: 200,000 tokens total
- Output reserve: 32,000 tokens per response
- Thinking budget: 1,600 tokens for reasoning
What Counts Toward Tokens
- Your prompts
- AI responses
- Tool definitions (background)
- Previous conversation messages
- Attached files (estimated: 100KB per PDF page)
When Limits Are Reached
At 200,000 tokens, X21 automatically:- Compacts the conversation (summarizes old messages)
- Preserves recent context
- Continues without interruption
Reading AI Responses
Range References
The AI mentions Excel ranges as clickable links:B5 or A1:A4 to navigate directly to those cells.
Sheet References
Sheet names appear as interactive pills:Tool Results
After approval, the AI references tool outcomes:Response Patterns
Read-Then-Act
Common pattern for safety:- AI reads your selection first
- Analyzes the data
- Proposes specific changes
- Waits for approval
- Executes and confirms
Explanation-First
For complex operations:- AI explains its approach
- Breaks down steps
- Executes each part
- Summarizes results
Batch Operations
For efficiency:What the AI Knows
Automatic Context
Every request includes:- Active sheet name
- Selected range (if any)
- All sheet names in the workbook
- Used range (data boundaries)
- Workbook name
- Display language (for localization)
What It Doesn’t Know
- Data from other workbooks (unless you tell it)
- Your intent beyond the current prompt
- External systems or databases
- Previous conversations (unless in same session)
Error Messages
Common Errors
Rate Limit:Tool Errors
When operations fail:Best Practices
Clear Requests
Help the AI understand by being specific:Context Provision
Provide relevant details:Verify Complex Changes
For important data:- Use View to preview changes
- Review the modified cells
- Apply only if correct
- Use Revert if needed
Provide Feedback
Help improve responses:- 👍 Thumbs up for accurate results
- 👎 Thumbs down with comments for issues
- Specific feedback helps refine the system
Advanced Understanding
Model Limitations
Claude Sonnet 4 is powerful but:- May occasionally misinterpret ambiguous requests
- Works best with clear, structured data
- Requires approval for safety on writes
- Has token limits for very long conversations
Continuous Improvement
Your feedback trains the system:- Ratings influence future responses
- Comments help identify issues
- Usage patterns inform tool improvements
Next Steps
- Learn about Tool Management to control what the AI can do
- Explore Tool Permissions to understand approval workflows
- Read Best Practices for expert prompting tips

