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

# Generation lifecycle

> Understand the stages, checkpoints, and failure boundaries of AI presentation generation.

Generation is a sequence of work, not a single AI response. Knowing the stages helps you decide whether to revise the input, wait for a task, or troubleshoot a dependency.

<img src="https://mintcdn.com/presenton-521d9e2f/a7GBkBOgfm-3ZeQM/images/general/generation-lifecycle-diagram.png?fit=max&auto=format&n=a7GBkBOgfm-3ZeQM&q=85&s=11cb04a5216f5d14ab9b4a61757a4aa3" alt="Diagram showing input ready, outline ready, generating, ready, editing, exported, and failed states" width="1759" height="812" data-path="images/general/generation-lifecycle-diagram.png" />

## Lifecycle stages

| Stage         | What happens                                             | What to check                                                    |
| ------------- | -------------------------------------------------------- | ---------------------------------------------------------------- |
| Input ready   | The brief, source files, and controls are collected      | Scope, file relevance, and must-keep facts                       |
| Outline ready | Presenton proposes the deck structure                    | Flow, coverage, repetition, and slide count                      |
| Generating    | Content, layouts, and visuals are assembled and rendered | Wait for completion; avoid duplicate submissions                 |
| Ready         | The presentation can be opened and reviewed              | Accuracy, design fit, and missing content                        |
| Editing       | You refine the generated result                          | Preserve verified facts while changing wording or layout         |
| Exported      | A PPTX or PDF is produced                                | Open the file and inspect fonts, charts, images, and page bounds |

## Synchronous and asynchronous API work

<Tabs>
  <Tab title="Synchronous">
    The request stays open while generation runs and returns after the operation completes or fails. Use it when the caller can safely wait for the full result.
  </Tab>

  <Tab title="Asynchronous">
    The request creates background work and returns a task identifier. Poll the deployment-specific status endpoint, or use a supported webhook workflow, until the task reaches a terminal state.
  </Tab>
</Tabs>

<Warning>
  Do not retry an asynchronous request only because generation is taking longer than expected. Check its task status first to avoid creating duplicate presentations.
</Warning>

## Where failures usually belong

* **Before outline creation:** inspect the input, upload, document processing, and provider configuration.
* **During generation:** inspect text, image, template, and rendering dependencies.
* **During export:** inspect fonts, assets, browser/export runtime, and storage.

<CardGroup cols={2}>
  <Card title="API workflow" icon="code" href="/api/workflow">
    Implement the lifecycle with the correct API surface.
  </Card>

  <Card title="Troubleshoot generation" icon="screwdriver-wrench" href="/archive/v0.9.2-beta/troubleshooting/generation">
    Diagnose a failed or incomplete generation.
  </Card>
</CardGroup>