AI Generation Persistence

AI generations are expensive, non-reproducible assets. Never discard them.

Every call to an LLM costs real money and produces unique output that cannot be exactly reproduced. Treat generations like database records — assign an ID, persist immediately, and make them retrievable.

Core Rules

1. Generate an ID before the LLM call — use nanoid() or createId() from @paralleldrive/cuid2
2. Persist every generation — text and metadata to database, images and files to Vercel Blob
3. Make every generation addressable — URL pattern: /chat/[id], /generate/[id], /image/[id]
4. Track metadata — model name, token usage, estimated cost, timestamp, user ID
5. Never stream without saving — if the user refreshes, the generation must survive

Generate-Then-Redirect Pattern

The standard UX flow for AI features: create the resource first, then redirect to its page.