Web Search
Web Search
Section titled “Web Search”Run a web search and return the results as structured data.
What it does
Section titled “What it does”Searches the web on a chosen engine and returns the results as a list of { title, url, snippet } objects. It works entirely in your browser through the extension: it opens the engine’s results page in a background tab, reads the results from the page, and closes the tab again.
When to use it
Section titled “When to use it”Use this node to feed live web results into a workflow — for example to gather sources for an AI agent, monitor mentions, or collect links for further processing.
Inputs and settings
Section titled “Inputs and settings”| Setting | Notes |
|---|---|
| Query | The search query. |
| Engine | Which search engine to use: DuckDuckGo (default, most reliable), Bing, or Brave. |
| Max results | Optional cap on how many results to return. Leave empty (or 0) to return all results found on the first page. |
Outputs
Section titled “Outputs”Returns an array of result objects, each shaped like:
[ { "title": "Example result", "url": "https://example.com", "snippet": "A short description of the result." }]Dependencies and credentials
Section titled “Dependencies and credentials”- No credential is required.
- Requires the awflow browser extension to be installed — the search runs inside the browser.
Example workflow
Section titled “Example workflow”Add Web Search with Engine = DuckDuckGo and a query, then pass its output into an AI Agent or an Edit Fields node to summarise or filter the results.
Troubleshooting
Section titled “Troubleshooting”- This node runs in the extension. If it returns nothing, confirm the extension is installed and active.
- Search engines change their page markup over time, which can affect scraping. If one engine returns no results, try another — DuckDuckGo is the most stable, while Brave is the most likely to need updates.
- Google is intentionally not offered, because it blocks automated searches.