- Use Cases
- What can you build with Ironflow?
What can you build with Ironflow?
Start with the work your application needs to finish. Ironflow is a durable runtime for AI agents and event-driven systems. It preserves completed step results, waits for external input, and supports state derived from events.
The use cases below connect those capabilities to concrete applications. Each explains a job, its difficult moment, an illustrative implementation flow, and the pieces your application supplies. The starting guides demonstrate specific runtime behaviors; some use cases combine them into an application you would build.
Agents and AI applications
Section titled “Agents and AI applications”- Agents over A2A: expose a specialist agent so other agents can discover it, delegate tasks, and follow progress.
- Agent harnesses with MCP: expose application capabilities to AI clients and connect them to durable work.
- Document processing: extract, classify, and publish documents through worker interruptions, with an optional review step you add.
- Support resolution agents: investigate a case, obtain approval, and wait for a customer reply.
- Reconciliation: match routine transactions and resolve exceptions through agent triage, approval, and outside responses.
Business workflows
Section titled “Business workflows”- Customer onboarding: provision an account across services and track delayed verification.
- Orders and returns: coordinate stock, payments, fulfillment, and a related return lifecycle.
- Bookings and reservations: reserve scarce resources and release completed holds after a terminal failure.
Data and operations
Section titled “Data and operations”- Data imports and synchronization: process incoming records, recover failed batches, and update derived views.
Choose by the difficult moment
Section titled “Choose by the difficult moment”An application is a useful fit when completed work must survive an interruption, the next input might arrive tomorrow, or several services must converge on one visible result. Look for the use case with the closest failure or wait to yours. Ordinary reads and writes can continue to use your application database.
For a first runnable introduction, follow Getting started. For an agent, Survive a crash demonstrates recovery after a worker is killed during a document-processing task.