Sushidata Research Swarm Actor

Deploy parallel AI research swarms via Sushidata on the Apify platform. This Actor launches multiple AI agents that work in parallel to deeply research any topic, then aggregates and verifies their findings.

What does Sushidata Research Swarm do?

This Actor connects to your Sushidata dataspace and deploys a configurable swarm of AI research agents. Each agent tackles a different angle of your research query simultaneously, providing comprehensive multi-perspective analysis. Results are verified for source quality and pushed to an Apify dataset for easy access via API, scheduling, and integrations.

Why use this Actor?

• Deep research at scale — Deploy 2-20 parallel AI agents that each explore a different facet of your question
• Verified sources — Evidence links are automatically verified; bad/blocked sources are filtered out
• Automated & scheduled — Run on a schedule via Apify platform, access results via API
• Context persistence — Results are saved to your Sushidata context lake for future reference
• Partial results — If the timeout is reached, you still get results from completed workers

How to use Sushidata Research Swarm

1. Create a free account at Sushidata and get your Resource ID
2. Open this Actor on Apify Console and click "Start"
3. Enter your Resource ID and research query
4. Choose a swarm size (default: 5 agents)
5. Run the Actor and check the dataset for results

Input

Field	Type	Required	Default	Description
resourceId	string	Yes	—	Your Sushidata dataspace resource ID
query	string	Yes	—	Research task for the swarm
swarmSize	integer	No	5	Number of parallel agents (2-20)
pollIntervalSeconds	integer	No	60	Polling interval in seconds
timeoutMinutes	integer	No	5	Max wait time before fetching partial results

Swarm size guide

Size	Use case
3–5	Focused, specific tasks
5–10	Broad research topics
10–20	Exhaustive, multi-angle analysis

Output

The Actor pushes two types of records to the dataset:

1. Deployment record (type: "swarm_deployed") — confirms the swarm was launched with the plan and worker details.

2. Result record (type: "swarm_result") — the final aggregated research summary.

{
    "type": "swarm_result",
    "query": "Analyze the current state of AI agents in production",
    "summary": "Based on research from multiple angles...",
    "completed": 5,
    "total": 5,
    "pending": 0,
    "isPartial": false,
    "verification": { "good": 4, "bad": 1, "blocked": 0 },
    "goodSources": ["https://verified-source-1.com", "https://verified-source-2.com"],
    "timestamp": "2026-05-15T12:00:00.000Z"
}

You can download the dataset in various formats such as JSON, HTML, CSV, or Excel.

Data fields

Field	Description
type	Record type: swarm_deployed or swarm_result
query	The original research query
summary	Aggregated research summary from all workers
completed	Number of workers that finished
total	Total number of workers deployed
isPartial	Whether the result is based on incomplete data
goodSources	Verified evidence links
timestamp	ISO timestamp of the result

Pricing / Cost estimation

This Actor itself uses minimal Apify compute (no browser, just HTTP calls). The main cost factor is your Sushidata plan token usage, which depends on swarm size and query complexity. A typical run with 5 agents completes in under 5 minutes of Apify compute time.

Tips

• Start with a swarm size of 3-5 for focused questions to save Sushidata tokens
• Use specific, well-defined queries — "Analyze pros and cons of React Server Components for e-commerce" is better than "React"
• Increase timeoutMinutes for larger swarms (10+ agents may need 10-15 minutes)
• Results are saved to your Sushidata context lake, so future queries can build on past research

FAQ and support

Is this affiliated with Sushidata? No, this is a community Actor that integrates with the Sushidata API.

What if I hit token limits? The Actor will report the error and suggest upgrading your Sushidata plan.

Where do I get a Resource ID? Sign up at dashboard.sushidata.ai and create a dataspace. The resource ID is in your dataspace URL.

For issues or feature requests, use the Issues tab. For custom solutions, reach out via the Apify community.