Glossary · Cost engine

Cross-tenant skill corpus

A shared, sanitized library of compiled skills that lets a skill compiled once be safely reused across tenants, compounding the cache savings.

What is cross-tenant skill corpus?

The cross-tenant skill corpus is a pooled set of compiled skills, sanitized of tenant-specific data, that any tenant’s dispatch can match against. A common workflow compiled by one account can satisfy a semantically similar request from another, so the network’s collective experience raises everyone’s cache-hit rate.

Why it matters

A single-tenant cache only learns from your own traffic. A cross-tenant corpus means the system gets cheaper the more the whole network runs, not just you — a compounding advantage that per-browser-hour competitors structurally cannot offer.

See it in context: read how Twin compiles and replays a run, follow the cost-cutting guide, or browse use cases and comparisons.

Run your first skill

Give an LLM agent a real browser, compile the workflow once, and watch the marginal cost fall as the cache takes over.