# Troubleshooting

AIsuru provides several indicators and solutions to help you deal with issues that may arise with generative AI providers. This guide will help you quickly identify and resolve the most common problems.

### Temporary provider issues

It's normal for providers like OpenAI or Anthropic to occasionally experience temporary outages. These issues usually resolve within 30 minutes, but in some cases the fix may take several hours. Problems can be limited to a specific model or may affect all of the provider's models.

No action is required on your part: the service will resume automatically.

{% hint style="info" %} <mark style="color:blue;">**AIsuru cannot resolve issues with individual providers**</mark><mark style="color:blue;">, but it does provide the tools to detect disruptions and quickly implement a solution.</mark>
{% endhint %}

#### Provider issue indicator

When you interact with an Agent that uses a provider that is experiencing problems, you'll see an empty icon with red borders ⚠️ signaling a potential issue.

This indicator appears automatically when the selected provider is having difficulties.

#### How to switch providers when there's a problem

AIsuru can't fix a provider's outage, but it does let you avoid service disruptions for your users. You just need to [**select a different provider and model**](/en/generative-ai/activate-generative-ai-and-change-model.md#how-to-change-your-agents-model) **to keep your Agent available to users**.

### Response processing time

Another common issue is response processing time. **Each generative AI request has a maximum of 180 seconds** (90 seconds for LLM models without reasoning) to complete processing. If the model can't produce a response within that time:

1. The request is automatically interrupted;
2. The Agent shows the generic error message: "I'm sorry, my responses are limited. You need to ask me the right questions";
3. A descriptive error in red will appear in the chat area communicating the problem. (Example: <mark style="color:$warning;">Error: Anthropic Message call failed with status code: RequestEntityTooLarge - Request Entity Too Large, content:)</mark>

This time limit is a safety measure to prevent the Agent from getting stuck in excessively long processing cycles, ensuring a better overall user experience.


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aisuru.com/en/generative-ai/advanced/troubleshooting.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.