Pre-Built Models
Out-of-box: text classification, sentiment, entity extraction, document processing (forms, invoices, receipts), object detection. Zero training needed for many use cases.
Custom Models
Train on your own data: custom document types, custom classification. Requires labeled training data; 50–200 samples per class to get decent accuracy.
Capacity
AI Builder consumption is metered in credits. Monitor usage per maker. Forecast before broad rollout or you’ll hit limits mid-month.
Integration
AI Builder actions plug into Power Automate and Power Apps. No glue code needed. Action input → model → structured output → downstream logic.
When It Fits
Invoice processing, contract analysis, feedback sentiment, simple vision. When the job is ‘classify or extract from a document’, AI Builder is usually faster than rolling custom.