Web Search Agent

Ask the web a question. Get every matching event.

50,000+ pages scanned per job and over 2 million events indexed daily.

Try API for free
Documentation

how it works

From query to dataset

Step 01

Query planning

Query rewritten into multiple retrieval prompts covering different phrasings and event types.

Step 02

Retrieval

50,000+ pages scanned per job at ~10,000 pages/min.

Step 03

Clustering

Related pages grouped into single event records using the Leiden algorithm.

Step 04

Validation

Each cluster scored by LLM validators against your query. Irrelevant clusters dropped.

Step 05

Structured output

One JSON object per event, with source citations and dynamic schema.

Output

Structured records, not ranked links

Each result is a validated, deduplicated event, with citations, schema, and no token billing.

US biotech startups that raised a venture round in the last 7 days
{ "candidate_records": 32566, "valid_records": 34,1 "all_records": [{ "record_title": "Ambros Therapeutics Secures $150M…",
"enrichment": {2 "funding_amount": 150000000, "lead_investor": "RA Capital Management, Janus…", "headquarters_location": "San Diego, California", "therapeutic_focus": "Complex Regional Pain Syndrome…" },
"citations": [3 { "title": "Werewolf and Ambros to tie the knot…", "link": "biospace.com" }, "… +16 more" ] }, "… +33 more"] }
no cap on results returned
enrichment fields are LLM-generated,
vary by query
source references included

  1. no cap on results returned

  2. enrichment fields are LLM-generated, vary by query

  3. source references included

Dynamic schema adapts to your query. No fixed fields to map around.

Web Search Agent vs. Competitors

The Web Search Agent finds 1.6× more verified events than Exa Websets, the next-best provider.

The Web Search Agent finds 1.6× more verified events than Exa Websets, the next-best provider.

Metric Web Search Agent Exa Websets Manus 1.6 Parallel AI OpenAI GPT-5
F1 Score 0.605★ 0.4960.3620.2640.139
Precision 0.5570.6140.8250.853 0.864★
Recall 0.663★ 0.4160.2320.1560.075
Uniqueness % 95.4%★ 21.7%68.5%89.2%70.5%
Query Wins 10/15★ 4/151/150/150/15

★ Best in category · Observable universe: 1,261 unique verified events across 15 queries · September 2026

Web Search Agent
0.605
Exa Websets
0.496
Manus 1.6
0.362
Parallel AI Core
0.264
OpenAI GPT-5 Search
0.139
0 0.25 0.50 0.75 1.0
F1 score: harmonic mean of precision & recall (0–1 scale)
Web Search Agent
66.3%836
Exa Websets
41.6%525
Manus 1.6
23.2%292
Parallel AI Core
15.6%197
OpenAI GPT-5 Search
7.5%95
0% 25% 50% 75% 100%
Coverage of the 1,261-event observable universe (%)

Read the full benchmark →

Integration

In production in under an hour

REST API with SDKs for Python, Node, and Java.

from newscatcher_catchall import CatchAllApi

client = CatchAllApi(api_key="YOUR_API_KEY")

job = client.jobs.create_job(
    query="EU AI Act enforcement actions",
    context="Focus on regulator, subject, and regulation cited",
    start_date="2026-09-08T00:00:00Z",
    end_date="2026-10-08T00:00:00Z",
    limit=50
)

job_id = job.job_id
import { CatchAllApiClient } from 'newscatcher-catchall-sdk'

const client = new CatchAllApiClient({ apiKey: 'YOUR_API_KEY' })

const job = await client.jobs.createJob({
  query: 'EU AI Act enforcement actions',
  context: 'Focus on regulator, subject, and regulation cited',
  start_date: '2026-09-08T00:00:00Z',
  end_date: '2026-10-08T00:00:00Z',
  limit: 50
})

const jobId = job.job_id
curl -X POST "https://catchall.newscatcherapi.com/catchAll/submit" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "EU AI Act enforcement actions",
    "context": "Focus on regulator, subject, and regulation cited",
    "start_date": "2026-09-08T00:00:00Z",
    "end_date": "2026-10-08T00:00:00Z",
    "limit": 50
  }'

Full reference in the Web Search Agent docs →

Real-time monitors

Best search is no search: enterprises don’t want a query box, they want notifications about predefined real‑world events that matter.

Use cases

What teams build with it

Prediction markets
Prediction Markets
From breaking event to tradable signal.
Explore →
Compliance and regulatory monitoring
Compliance & Regulatory Monitoring
From regulatory noise to structured compliance events.
Explore →
Sales intelligence
Sales Intelligence
Every funding round, exec hire, and expansion.
Explore →
Supply chain intelligence
Supply Chain Intelligence
From scattered supply-chain events to structured signals.
Explore →
Market intelligence
Market Intelligence
Market-moving events, the instant they surface.
Explore →
Third-party and vendor risk
Third-Party & Vendor Risk
Every breach, sanction, and enforcement action.
Explore →

FAQ

Agent
Monitors
Watchlist
Is the Web Search Agent the same as the News API?

No. These are two separate products with separate endpoints, under one API key and one credit balance. The Web Search Agent is a web search API focused on real-world events. News API is a general news search API.

Is the Web Search Agent free to use?

Yes, to start. Every account gets 10,000 free credits every 30 days, and no credit card is needed to sign up. After that, top-ups start at $25.

How does billing work?

Per search, in credits. A Fast search is 1,000 credits and returns up to 50 rows. Standard is 3,000 and Max 6,000 for the first 50 rows, plus 1,500 or 3,000 for each 50 more. Searches that fail or find nothing are free.

How long does a search take?

Lite mode returns results in seconds. Base mode typically takes around 15 minutes. Jobs show as "pending" while processing.

How do I write a good query?

Use the formula: event type + time window + optional scope. Example: "Series A funding announcements in Europe over the past 30 days." More specific queries return better results.

Does the Web Search Agent support non-English sources?

Yes. The Web Search Agent indexes international sources and may return results in multiple languages. Add language filters in the context field for English-only results.

Monitors is a feature of the Web Search Agent: it reruns your search automatically on a schedule.

How is this different from running a cron job myself?

A Monitor handles the date windowing, deduplication, and delivery. You get a clean feed of new records — no infrastructure to maintain.

What's the minimum schedule interval?

Hourly.

Can I attach a Watchlist to a Monitor?

Yes. Attach a dataset with your entity list to scope results to specific companies. Watchlist scoring applies to every run.

Can I pause a monitor without deleting it?

Yes. Disable pauses execution without removing configuration or history. Re-enable to resume on the same schedule.

Watchlist is a feature of the Web Search Agent: it scopes your search to a list of companies you choose.

Is this a news alert tool?

No. Alerts send links. Watchlist returns deduplicated event records, filtered to your companies and scored for relevance.

What counts as a "mention"?

Any page where a tracked entity is confirmed relevant by the validator. Entity resolution, not keyword matching.

How is relevance scored?

LLM validator scores each result 1–10 against your entity list. 7+ is typically high relevance.

Can I use the same Watchlist across multiple searches?

Yes. One list across all jobs and monitors. Update once.

Does it support non-English companies?

Yes. Name variants, aliases, and non-English spellings handled by default.

Start for free

10,000 free credits every 30 days. No credit card required.

Try API for free
Talk to us
|
GDPR compliant
|