> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tandemn.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Job lifecycle

> What happens after a user submits a Tandemn job.

A Tandemn job moves from user submission to server-side scheduling and execution.

<Steps>
  <Step title="Prepare input">
    The user prepares a JSONL prompt file and chooses a model that the deployment can run.
  </Step>

  <Step title="Submit">
    The user runs `tandemn deploy` from a machine that can reach the Tandemn server.
  </Step>

  <Step title="Validate">
    The server checks the request and determines whether the workload can be accepted.
  </Step>

  <Step title="Plan">
    Tandemn evaluates the available GPU pool and chooses where to place the workload.
  </Step>

  <Step title="Execute">
    The workload runs on the selected resources.
  </Step>

  <Step title="Review">
    The user checks the CLI output and any job artifacts exposed by the deployment.
  </Step>
</Steps>

## Practical advice

* Start with a small prompt file before submitting a large workload.
* Confirm the model is available in your deployment.
* Keep `TD_SERVER_URL` visible in your terminal when debugging.
* Ask your administrator for the supported SLO conventions in your environment.