> ## Documentation Index
> Fetch the complete documentation index at: https://notte-experiment-visibility-md-links.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Fallback

> Gracefully handle script execution failures with Web Agents

# Overview

Agent Fallback are mechanisms that allow you to gracefully handle script execution failures without any additional code:

{/* @sniptest testers/agents/fallback.py */}

```python agent_fallback.py highlight={11-18} theme={null}
from notte_sdk import NotteClient

client = NotteClient()
url = "https://www.linkedin.com/feed/"
company_name = "nottelabs"

# scrape all new posts (post url, date, title, content) from the company page on LinkedIn
with client.Session() as session:
    session.execute(type="goto", url=url)
    # spin up agent fallback if the search for the company name fails
    with client.AgentFallback(
        session=session, task=f"Open the company page for {company_name}. Fail if user is not logged in."
    ) as agent:
        # search for the company name
        session.execute(type="fill", selector='internal:role=combobox[name="Search"i]', value=company_name)
        # press enter to search
        session.execute(type="press_key", key="Enter")
        # click on the company link
        session.execute(type="click", selector=f'internal:role=link[name="{company_name}"s] >> nth=0')
    # open the post tab on the company page
    session.execute(type="click", selector='internal:role=link[name="Posts"i]', raise_on_failure=False)
    data = session.scrape(instructions="scrape all new posts (post url, date, title, content)")
    print(f"Scraped data: {data}")
```

They ensure your scripts always terminate successfully even if the website changes or something unexpected happens.

## Parameters

<ParamField path="session" type="RemoteSession" required />

<ParamField path="task" type="str" required />

<ParamField path="response_format" type="UnionType[type[BaseModel], None]" default="None" />

<ParamField path="reasoning_model" type="notte_core.common.config.LlmModel | str">
  The language model to use for agent reasoning.
</ParamField>

<ParamField path="use_vision" type="bool">
  Whether to enable vision capabilities for the agent.
</ParamField>

<ParamField path="max_steps" type="int">
  Maximum number of steps the agent can take.
</ParamField>

<ParamField path="vault_id" type="str | None">
  Optional ID of the vault to use.
</ParamField>

<ParamField path="persona_id" type="str | None" />

<ParamField path="notifier_config" type="dict[str, typing.Any] | None">
  Config used for the notifier.
</ParamField>