A single Sonnet-class agent answers everything. Many queries are simple lookups a Haiku-class model handles for a fraction of the cost. The expensive model spends most of its budget on questions it never needed to see.
Apps with a wide query distribution where many requests are simple and a few are complex. Customer support, knowledge base assistants, internal helpdesks.
Apps where every query touches the same tool surface and the cost of misrouting (a small model failing) is high.
Describe this pattern to the builder assistant and it wires it up for you, brains, tools and triggers. It's vibe coding for agents, no config to write.
Walking through the pattern one piece at a time so the design is clear, not memorised.
The router runs Haiku-class. Its only job is one-word classification of incoming messages, almost free per call.
Three specialists: Haiku for trivial lookups, Sonnet for research, Opus for hard reasoning. Each only sees the queries that need it.
Returning the specialist's output as-is keeps the response identical to what a single big model would have produced. No double summarisation.
Most workloads skew heavily toward simple queries. With a large cost ratio between the cheapest and most expensive model, the average query cost drops sharply.
The pattern above is not the only answer. Here is when something else is the right call.
Simpler config, predictable quality. You pay the expert price on every query.
Replace the LLM router with a local embedding classifier trained on past queries. Near-zero cost, lower flexibility.
Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.