> For the complete documentation index, see [llms.txt](https://docs.airops.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.airops.com/actions/workflow-concepts/workflow-steps/web-research/google-search.md).
# Google Search
Automate research with a Google Search
The "Google Search" Step allows you to automate a Google Search and pass the results as input into your Workflows.
## Configuring a "Google Search" Step
Configuring the step is straightforward with simple dropdown menus. No JSON payload required.
### Search Query
The "Search Query" input field is the exact phrase that will be Googled when the step runs, i.e. what do you want to search in Google?
{% hint style="info" %}
To search from a specific site, you can type **site:[www.example.com](http://www.example.com)** followed by your search phrase
{% endhint %}
### Search Parameters
Configure your search parameters using the dropdown menus:
* **Region**: Select the geographic region for your search results
* **Number of Results**: Choose how many results to return
* **Similar/Omitted Results**: Enable or disable filtering
{% hint style="info" %}
**Advanced Configuration:** For more complex use cases, you can still configure parameters based on the [SERP API documentation](https://serpapi.com/search-api) using JSON format.
{% endhint %}
To dynamically set variables as query or search parameters referencing an input (defined in the "Start" step) or output variable (generated by any step), you will need to use Liquid syntax:
{% @arcade/embed url="" flowId="ziYB9Ed9nh8CDuLHOHcX" %}
### Output Types
The following Output Types are currently supported by the "Google Search" Step:
**Links Only**: A list with links to the organic URL results.
```json
[
"https://www.zdnet.com/article/six-skills-you-need-to-become-an-ai-prompt-engineer/",
"https://en.wikipedia.org/wiki/Prompt_engineering",
"https://www.mckinsey.com/featured-insights/mckinsey-explainers/what-is-prompt-engineering",
"https://www.techtarget.com/searchenterpriseai/definition/AI-prompt-engineer",
"https://www.datacamp.com/blog/what-is-prompt-engineering-the-future-of-ai-communication",
"https://www.promptingguide.ai/",
"https://aws.amazon.com/what-is/prompt-engineering/",
"https://hbr.org/2023/06/ai-prompt-engineering-isnt-the-future",
"https://www.iit.edu/blog/unlock-career-opportunities-ai-how-become-ai-prompt-engineer",
"https://www.coursera.org/articles/how-to-become-a-prompt-engineer"
]
```
**Title, Snippet, Links (Markdown)**: Title, Snippet and Links for each organic result in Markdown format.
```markdown
**Six skills you need to become an AI prompt engineer**
Six skills you need to become an AI prompt engineer · 1. Understand AI, ML, and NLP · 2. Define problem statements clearly and specify detailed ...
https://www.zdnet.com/article/six-skills-you-need-to-become-an-ai-prompt-engineer/
**Prompt engineering**
Prompt engineering is the process of structuring text that can be interpreted and understood by a generative AI model. ... A prompt is natural language text ...
https://en.wikipedia.org/wiki/Prompt_engineering
**What is prompt engineering?**
Prompt engineering is the practice of designing inputs for generative AI tools that will produce optimal outputs.
https://www.mckinsey.com/featured-insights/mckinsey-explainers/what-is-prompt-engineering
...
```
**Organic Results (JSON)**: Organic results in JSON format.
```
[
{
"position": 1,
"title": "Six skills you need to become an AI prompt engineer",
"link": "https://www.zdnet.com/article/six-skills-you-need-to-become-an-ai-prompt-engineer/",
"displayed_link": "https://www.zdnet.com › ... › Artificial Intelligence",
"favicon": "https://serpapi.com/searches/65579a96e815af000b7dab68/images/a5422e713e6bc3f59a76b766eb80117740cc3058315f42d3df7f4337510ce3b6.png",
"date": "Oct 3, 2023",
"snippet": "Six skills you need to become an AI prompt engineer · 1. Understand AI, ML, and NLP · 2. Define problem statements clearly and specify detailed ...",
"snippet_highlighted_words": [
"prompt engineer"
],
"about_page_link": "https://www.google.com/search?q=About+https://www.zdnet.com/article/six-skills-you-need-to-become-an-ai-prompt-engineer/&tbm=ilp",
"about_page_serpapi_link": "https://serpapi.com/search.json?engine=google_about_this_result&google_domain=google.com&q=About+https%3A%2F%2Fwww.zdnet.com%2Farticle%2Fsix-skills-you-need-to-become-an-ai-prompt-engineer%2F",
"cached_page_link": "https://webcache.googleusercontent.com/search?q=cache:QnozTEs7HoMJ:https://www.zdnet.com/article/six-skills-you-need-to-become-an-ai-prompt-engineer/&hl=en&gl=us",
"source": "ZDNet"
},
...
]
```
**Raw**: Complete results from Serp API in JSON format.
```
{
"search_metadata": {
"id": "65ad949daf5af14fb1f744b3",
"status": "Success",
"json_endpoint": "https://serpapi.com/searches/c058cc17ce2a376c/65ad949daf5af14fb1f744b3.json",
"created_at": "2024-01-21 22:03:09 UTC",
"processed_at": "2024-01-21 22:03:09 UTC",
"google_url": "https://www.google.com/search?q=How+does+an+LLM+work%3F%0A%0A&oq=How+does+an+LLM+work%3F%0A%0A&num=1&sourceid=chrome&ie=UTF-8",
"raw_html_file": "https://serpapi.com/searches/c058cc17ce2a376c/65ad949daf5af14fb1f744b3.html",
"total_time_taken": 2.5
},
"search_parameters": {
"engine": "google",
"q": "How does an LLM work?\n\n",
"google_domain": "google.com",
"num": "1",
"device": "desktop"
},
...
```
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.airops.com/actions/workflow-concepts/workflow-steps/web-research/google-search.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
