> For the complete documentation index, see [llms.txt](https://docs.trendswap.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.trendswap.app/pricing/auto-refund-guarantee.md).

# auto refund guarantee

Generative AI pipelines operate on complex distributed GPU clusters. Network spikes, worker timeouts, or prompt edge-cases can occasionally cause an upstream rendering task to fail.

At TrendSwap, **you never pay for a failed generation**.

***

## How the Auto-Refund Engine Works

```
[ Job Initiated ] ---> [ Credits Debited (e.g. 50 CR) ]
                                |
                                v
                    [ GPU Neural Inference ]
                                |
              +-----------------+-----------------+
              |                                   |
              v                                   v
      [ Success (200 OK) ]               [ Failure Detected ]
              |                                   |
              v                                   v
      [ Video Ready ]               [ Instant Automatic Credit Refund ]
                                    [ Push Notification + Status Log  ]
```

{% stepper %}
{% step %}

## Instant Failure Detection

Our backend state machine continuously health-checks every active job. If an inference task:

* Exceeds the maximum 6-minute timeout threshold;
* Triggers an out-of-memory or worker crash; or
* Fails automated safety and content verification filters;

The system immediately flags the job as `FAILED`.
{% endstep %}

{% step %}

## Zero-Ticket Credit Restoration

The exact number of credits deducted at job creation is **instantly returned to your account balance**.

* No support emails required.
* No waiting for human review.
* The transaction is logged with type `REFUND` in your `/settings/credits` ledger.
  {% endstep %}

{% step %}

## Clear Remediation Guidance

When a failure occurs, the studio interface displays actionable guidance (e.g., *"Photo resolution too low"*, *"Face partially obscured"*, or *"Upstream cluster re-routed"*) so you can adjust your input and try again with zero penalty.
{% endstep %}
{% endstepper %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.trendswap.app/pricing/auto-refund-guarantee.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.