Skip to main content

Just want working code?

Skip to the Websets coding agent reference — a self-contained page your agent can read to integrate Websets.

​
What Are Websets?

Websets finds exactly what you need on the web — even when it’s complex. Give it a query like “agtech companies in the US that raised Series A” and it will search, verify each result against your criteria, and enrich every match with additional data you specify. Results arrive as structured, verified items you can export or pipe into your workflow. You can also build websets visually in the Dashboard — no code required.

​
How It Works

  1. You define a search — a natural language query, how many results you want, and optionally criteria to verify against and enrichments to extract.
  2. Websets searches and verifies — it uses Exa’s search engine to find candidates, then verifies each one against your criteria. Only matching results become items.
  3. Enrichments run automatically — for each verified item, Websets searches the web to find the additional data you requested (CEO name, funding amount, contact info, etc.).
  4. Results arrive over time — Websets is asynchronous. Poll for status, use webhooks for real-time updates, or just check the dashboard.

​
Key Capabilities

FeatureWhat It Does
Criteria verificationEach result is checked against rules you define, so you only get relevant matches
EnrichmentsExtract specific data points (text, numbers, dates, booleans) for every result
MonitorsSchedule recurring searches to keep your webset updated automatically
WebhooksGet real-time HTTP callbacks as items are added or enriched
ImportsBring your own URLs and run enrichments on them

​
Human Quickstart

Get your API key from the Exa Dashboard. 
pip install exa-py

from exa_py import Exa
from exa_py.websets.types import CreateWebsetParameters, CreateEnrichmentParameters
import os

exa = Exa(os.getenv("EXA_API_KEY"))

webset = exa.websets.create(
    params=CreateWebsetParameters(
        search={
            "query": "Top AI research labs focusing on large language models",
            "count": 5
        },
        enrichments=[
            CreateEnrichmentParameters(
                description="LinkedIn profile of VP of Engineering or related role",
                format="text",
            ),
        ],
    )
)

print(f"Webset created with ID: {webset.id}")
print(f"View your Webset at: {webset.dashboard_url}")

# Wait until Webset completes processing
webset = exa.websets.wait_until_idle(webset.id)

# Retrieve Webset Items
items = exa.websets.items.list(webset_id=webset.id)
for item in items.data:
    print(f"Item: {item.model_dump_json(indent=2)}")

​
Next