Blog
Engineering notes, creator economics, and product announcements from the team building ToRun.
How ToRun picks the right model for every message
The problem with "just use GPT-4" Most AI platforms make a quiet choice on your behalf: they pick a model they like, wire everything to it, and move on. That works until it doesn't — until the model is down, until a comp…
Designing for multi-tenant SaaS — the ToRun approach
Tenants, hosts, and the dataset filter ToRun is built on ABP Framework's multi-tenancy model. A row marked IsMultiTenant has a TenantId column that the framework filters automatically; queries from inside a tenant contex…
Understanding multimodal AI pricing — tokens, images, and seconds
One BillingRecord per call, full snapshot Every AI call on ToRun produces exactly one BillingRecord that captures the price at the moment of execution. Provider rates change every few weeks; storing the rate inline means…