Web data
Give your agents full access to Apify.
Agents run Apify actors to collect structured data from the web at scale, then analyze the results in their own sandbox. Pair it with built-in web search and scraping for research that goes wide and deep.
5,000 free credits to start.
Agent reach
Apify API v2
The full surface, searched at run time.
Connect with
- API key
Event triggers
Not yet
Manual, schedule, and signed webhook are available.
What the agent can do
What agents do with Apify
Helios searches the Apify API v2 at run time. The agent finds the endpoint the task needs and calls it.
- Search Apify's entire API surface at run time and call any endpoint your token allows.
- Start actor runs with custom input and wait for them to finish.
- Read datasets, key-value stores, and run logs from completed runs.
- Analyze scraped datasets as code in the agent's sandbox.
- Combine actor output with built-in web search and page scraping.
- Write results into a sheet, a database, or a document.
Examples
Tasks you can hand to a Apify agent
Track competitor pricing
A weekly agent scrapes competitor pricing pages, diffs them against last week, and reports only what changed.
Weekly, scrape competitor pricing pages and report what changed.
- apify·run the web scraper on 9 pricing pages
- apify·read the resulting dataset
- code·diff against last week's snapshot
- slack·post changes to #competitive
2 pricing changes detected
- Competitor A raised its team tier to $29/seat
- Competitor B added a usage-based plan
- 7 pages unchanged
Collect a dataset for research
Point the agent at a source. It runs the right actor, cleans the output, and writes a dataset you can actually use.
Collect job postings for platform engineers at Series B devtools companies.
- apify·run the job board actor across 3 sources
- code·dedupe and normalize 1,240 postings
- google-sheets·write `Hiring Signals`
1,240 postings collected
- 418 remain after dedupe and filtering
- 64 companies hiring for the target role
- Sorted by posting recency
Monitor a page for changes
The agent watches the pages you care about - docs, changelogs, status pages - and tells you the moment something moves.
Daily, check competitor changelogs and summarize anything new.
- apify·scrape 5 changelog pages
- code·diff against yesterday's snapshot
- notion·append new entries to `Competitive Intel`
3 new entries
- Competitor A shipped SAML SSO
- Competitor C deprecated its v1 API
Enrich a list with public web data
Take a list of companies and let the agent read each site, pull what you asked for, and write it back in a column.
For each company in the sheet, read its site and classify its category.
- google-sheets·read 300 company URLs
- apify·scrape homepages and about pages
- code·classify by category and stage
- google-sheets·write the classification columns
300 companies classified
- 287 classified with high confidence
- 13 flagged for a human to check
Triggers
How a Apify workflow starts
Apify does not emit event triggers yet. Workflows that use it start by hand, on a schedule, or from a signed webhook.
Manual
Run it from the app with an optional JSON payload. Every workflow supports this.
Schedule
A cron expression or a plain sentence such as every weekday at 9am. Times are UTC.
Signed webhook
A public URL per workflow. Requests are signed with HMAC-SHA256 and expire after five minutes.
Works with
Apify works with the rest of your stack
One agent, one run, several services. It reads from one tool and writes to the next in the same sandbox.
Templates
Ready-to-run Apify workflows
Copy the prompt, connect your tools, and start a run.
FAQ
Questions, answered
Put an agent on Apify.
Connect it once and describe the task in chat. Then reuse the prompt as a workflow on a schedule or a webhook.