The Process
1
Select content
Pick individual assets or entire bundles
2
Choose schema
Select which schema to apply
3
Pick model
OpenAI, Anthropic, Google, or local via Ollama
4
Run
Each document gets processed, results stored as structured JSON
Choosing a Model
Different models have different strengths:| Provider | Best for | Notes |
|---|---|---|
| OpenAI | General extraction, high throughput | Reliable, fast, good default |
| Anthropic | Nuanced analysis, long documents | Better at complex reasoning |
| Large context windows | Good for lengthy documents | |
| Ollama | Privacy, local processing | No data leaves your machine |
Batch Processing
When analysing large collections
- Start small - Test on 2-3 documents first
- Check outputs - Do they match expectations?
- Refine instructions - Tighten schema if needed
- Scale up - Run on full collection
Monitoring Runs
Active analysis runs show progress in the UI:- Documents processed / total
- Current status (running, completed, failed)
- Error details if something goes wrong
Results
After analysis completes, results appear as annotations on your assets. Each annotation contains the structured data your schema extracted. View results:- On the asset - See all annotations for a specific document
- Fragments - If curated from a table, you can see the persistent fragments on the asset detail view
- In dashboards - Aggregate and visualise across the entire run
- Via export - Download as CSV or JSON for external analysis