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

# Parallel

> AI-powered web search, structured extraction, and long-running research tasks

# Parallel

Shanone's Parallel integration gives your agent 7 tools for [Parallel](https://parallel.ai)'s web search, structured find-and-extract, chat, and asynchronous research/monitoring APIs — built for agentic workloads that need grounded, real-time web data.

## Getting Started

<Steps>
  <Step title="Create a Parallel API key">
    Generate a key from the [Parallel platform](https://platform.parallel.ai/).
  </Step>

  <Step title="Add the key in Shanone">
    Go to **Integrations** in the Shanone dashboard, select Parallel, and paste in your API key.
  </Step>

  <Step title="Retry your request">
    Once saved, `shanone_execute_tool` calls for `parallel_*` tools will succeed.
  </Step>
</Steps>

## Available Tools

Shanone provides **7 tools** for Parallel, organized into these categories:

<AccordionGroup>
  <Accordion title="Search & extract">
    `parallel_search`, `parallel_extract` — run a web search optimized for LLM consumption, or extract structured content from specific URLs
  </Accordion>

  <Accordion title="Find-all">
    `parallel_findall` — discover entities matching a description across the web (e.g. "find companies that do X"), returning a structured list
  </Accordion>

  <Accordion title="Research & chat">
    `parallel_task`, `parallel_chat` — run a long-running research task with citations, or have a grounded conversation backed by live web search
  </Accordion>

  <Accordion title="Monitoring">
    `parallel_monitor_create`, `parallel_monitor_list`, `parallel_monitor_events`, `parallel_monitor_delete` — set up a standing web monitor for a topic and poll for new events
  </Accordion>
</AccordionGroup>

## Common Use Cases

<CardGroup cols={2}>
  <Card title="Grounded research reports" icon="file-search">
    Run `parallel_task` on a complex question and get a cited, structured answer back
  </Card>

  <Card title="Lead / entity discovery" icon="users">
    Use `parallel_findall` to build a list of companies or people matching specific criteria
  </Card>

  <Card title="Competitive monitoring" icon="radar">
    Create a monitor for a competitor or topic and check `parallel_monitor_events` on a schedule
  </Card>

  <Card title="Structured data extraction" icon="file-code">
    Pull specific fields out of a set of URLs with `parallel_extract` instead of scraping manually
  </Card>
</CardGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="parallel_task never seems to return a final answer">
    Research tasks run asynchronously and can take longer than a single request for complex queries — check the tool's response for a task/run ID and poll rather than expecting an immediate synchronous result.
  </Accordion>

  <Accordion title="parallel_monitor_events returns an empty list right after creating a monitor">
    Monitors need time to run their first scan cycle. Wait a few minutes after `parallel_monitor_create` before expecting events, then poll periodically.
  </Accordion>

  <Accordion title="parallel_extract returns partial or missing fields for a URL">
    Extraction quality depends on the page being accessible and reasonably structured; for JS-heavy or paywalled pages, results may be incomplete even with a valid API key.
  </Accordion>
</AccordionGroup>