Hey Coda community! Just dropped a new pack that brings Claude AI’s vision powers directly into your docs
What it does:
- Analyze any image with Claude’s AI vision
- Auto-optimizes images before sending (faster + cheaper)
- Extract text, analyze charts, describe photos, process documents
- Simple formula: AskClaude(apiKey, message, [images])
Why you’ll like it:
- 4 Claude models to choose from (Sonnet 4 is
)
- Handles multiple images at once
- Built-in cost optimization
- Works with any Coda-hosted image
Perfect for:
- Processing receipts/invoices
- Analyzing charts and graphs
- Quality control with photos
- Converting handwritten notes
Getting started:
- Get API key + credits at https://console.anthropic.com ($5 minimum)
- Install the pack
- Use Help() for English guide or Help(“br”) for Portuguese
Beta Notice: This pack is in beta - expect updates and potential changes as I improve it based on your feedback!
The pack automatically optimizes your images so you get better results while using fewer tokens. Pretty neat, right?
Anyone using Claude for image analysis in their workflows? Would love to hear your use cases and suggestions!