An AI Variable is a reusable prompt-and-settings bundle that tells Enginy how to research and return a specific piece of information for a Contact or Company. Think of it as a smart column: instead of manually researching, the AI reads the attributes you provide (name, domain, job title, LinkedIn, etc.), optionally searches external sources, and returns the answer in the format you specify.

AI Variables are used to generate additional information columns in your lists. You can use ready-made templates or build your own, then run them in bulk and store results as columns on your table.

Example use cases:

You can start from default Templates to be able to configure the new AI variable even faster:

Select the Output type to define how the AI returns results:

Example: An AI Variable with the instruction "Tell me if the company is either a B2B, B2C, or B2C with B2B products" and the output type set to One of will only return one of those three values. This ensures consistency, makes results easier to filter and analyze, and prevents unexpected or vague answers.

You can activate the Provide explanation option when creating or editing a variable. When enabled, the AI returns both the result and a short reasoning behind it, giving your team more context about why the AI chose that answer.

The Prompt field is the main instruction. Use the following recommended structure:

You can reference contact and company fields inside your prompt using the {field_name} syntax. Type { in the prompt editor to see the full list of available variables.

Examples of effective prompts:

Avoid vague prompts like: "Tell me everything about this company." — Too broad, no structure.

Below the prompt editor, the Enhance button lets the AI automatically polish your prompt — improving its structure, wording, and references to Enginy attributes. Write a first draft, click Enhance, then review and accept or adjust the improved version.

Use the Add attributes option to select which row fields the variable can use as context. Reference them inside your prompt with the {field_name} syntax.

Common Contact attributes:

{firstname}, {lastname}, {job_title}, {geo_region}, {last_linkedin_post}, {job_change}, {previous_positions}, {mentioned_in_news}

Common Company attributes:

{company_name}, {description}, {industry}, {iq_company_news}, {yearly_headcount_growth}, {website}

Enable the Deep Research toggle to let the AI browse the web and find information beyond what is already available in your lists. It covers web pages, news, company websites, and other public sources in one unified search.

The technology behind Deep Research uses Firecrawl, a specialized web-scraping tool designed to extract content from websites and convert it into a format the AI can understand.

Deep Research uses more credits than standard AI Variables because web searches and page scraping incur additional costs per execution, and multiple iterations may be needed.

When creating or editing an AI Variable, you can choose the AI model to use. Each model has different strengths — see the Available AI Models article for a full comparison.

Each AI model has an associated cost. Beyond the model, cost can also increase based on:

Before running a variable across your entire list, test it on a single contact or company to validate the output quality and prompt accuracy. Click the play icon in a specific cell to run the variable for an individual record.

Once created, AI Variables appear as columns in your Contact or Company lists. There are several ways to run them:

All AI Variables are managed from the AI Playbook > AI Variables tab. The left panel displays all variables organized in folders, with two tabs: Contacts and Companies.

Click the three dots on any variable card to access the following actions:

You can use AI Variables to generate variations of a message template — either personalized based on contact data or randomized for variety.

Step 1 — Write your base message outside of Enginy.

Step 2 — Identify the parts to change. Replace variable sections with [TAG] placeholders (e.g., [GREETING], [PRODUCT], [PERSONA], [CLOSING_LINE]).

Step 3 — Define the rules for each tag:

Step 4 — Create the AI Variable at Enginy > AI Playbook > AI Variables > Create AI Variable using the prompt structure above.