Bulk classification architecture
High-volume, low-cost classification over a queue, with the cheap model doing the work and a cap on the bill.
Every resource, and what it costs.
Projections from August 2026 list prices for always-on resources. Connect an account and these become the figures your provider actually bills.
| Node | Type | What it is | Projected |
|---|---|---|---|
| Input bucket | Storage | 100 GB standard | $3.00/mo |
| Classification queue | Messaging | 5M requests | $2.00/mo |
| Labels store | Database | on-demand · ~5M writes, 20M reads | from $15/mo |
| Batch enqueued | Trigger | Queue message | — |
| Classify | Agent step | Single-label, schema-enforced | billed per token |
| Budget cap | Guardrail | Halts runs over $600/mo | enforced at runtime |
| ArcFoundry runtime | Runtime | — | — |
Agent steps are priced from provider-reported token usage once the agent runs, not estimated. Guardrails cost nothing and are the reason a runaway agent cannot. One row shows from because those services bill by usage, so the total is a scenario at the stated volumes, not a quote.
Similar templates.
Support agent on live systems
A support agent that reads the orders database and writes back through an approval gate. Agent steps and the systems they touch on one graph.
Agent with enforced write control
The pattern for letting an agent touch production: every write passes an approval gate, every action lands in a hash-chained evidence log.
Retrieval service (RAG)
An answer endpoint over your own documents: vector store, retrieval step, generation step, cached responses.
Open Bulk classification on the canvas.
It loads as an editable graph. Connect an account or instrument an agent and the projected figures above become measured ones.