AI Search and Research

Many workflows and agents require the ability to dynamically Search Google or do broader AI-powered research on a topic. For example, you may want to do search for information about a company that fills out a prospect interest form. To achieve this, you have two basic options:

1) Search Google and analyze the results

2) Use an AI-model with built-in Search

Using Google Search

To initiate a Google Search in a workflow, you can use the 'Search Google' step, which is in both the AI and Web scraping menus:

The Search Google step

Once you've selected 'Search Google', you just need to specific your query and the number of results to return and / or scrape. Your query will typically be formulated from the ouptuts of previous steps (see Using Data Across Steps for more information).

Seetting up a "Search Google" step.

After your Search Google step, you'll typically need to use an AI Step to process the results and extract the information you want.

Using AI Search (Perplexity, ChatGPT, etc)

Alternatively, if you want to delegate more to AI, you can use an AI model with built-in search to do a prompt-based search. To do this, set up a standard 'Prompt any model' AI step and be sure to select a model with built-in search. This includes all of the Perplexity models, and a subset of the OpenAI and Google Gemini models.

An AI step with built-in search