Architecture overview

Choose the right AI request pattern

Every AI application is different. Choose the request pattern that best fits your use case, then explore how it works with interactive diagrams and side-by-side comparisons.

Recommended

Backend pipeline

Live progress updates, background AI workflows, and backend processing. Best for interactive AI applications.

Learn more

Async (Dual-Delivery)

Submit once, then automatically deliver results to both your backend and your users. Best for reliable asynchronous processing.

Learn more

Sync

Wait for AI to finish before returning the result. Best for quick AI requests and straightforward integrations.

Learn more

Detailed Comparison

A side-by-side break down of scaling properties and best use cases for each method.

Capability	Backend Pipeline	Async (Dual-Delivery)	Sync
Best for	Customer-facing AI apps with live progress	Reliable background processing	Quick AI requests
User experience	Live progress updates	Wait, then receive final result	Wait until AI finishes
Backend processing	Continues after the response	Runs until completion	Ends with the HTTP request
Difficulty	Medium	Medium	Easy
Scalability	Excellent	Excellent	Limited by HTTP connections
Reliability	Automatic retries & failover	Automatic retries	Depends on request timeout
Response delivery	WebSocket + Webhook	WebSocket + Webhook	HTTP response
Typical examples	AI chat, CRM assistant, customer support	Reports, document processing, batch jobs	Classification, moderation, autocomplete