Readable task states
Follow a task from queued to running, waiting, and completed without piecing together application logs.
A dependable next step Private preview
A task queue designed for AI workflows: visible handoffs, deliberate retries, and a clear place to resume when a run needs another try.
01 / The product
Three capabilities planned for the first release of Relaymoss.
Follow a task from queued to running, waiting, and completed without piecing together application logs.
Keep the inputs and last known state beside each retry, so your team can understand what happens next.
Define where a task goes next, whether that is another agent, a scheduled step, or a person.
02 / The workflow
Explore the intended workflow, from the first input to a useful result. This is an interactive concept preview.
Follow a task from queued to running, waiting, and completed without piecing together application logs.
Keep the inputs and last known state beside each retry, so your team can understand what happens next.
Define where a task goes next, whether that is another agent, a scheduled step, or a person.
03 / Good to know
Relaymoss is a product in development. This page shows the intended direction and illustrative sample data. Email us to discuss the private preview.
The concept is a coordination layer around existing agent workflows. Framework support and the first integrations are still being scoped.
Small engineering teams that need to see where multi-step agent tasks are waiting, failing, or handing work to someone else.
Help shape what comes next
Tell us about your workflow and what you need from Relaymoss. We’re opening conversations with potential early users.