Skip to main content

​
Overview

FigAI is your AI assistant for workflow building. Instead of manually creating nodes one by one, describe what you want in natural language and let your FigAI Analyst build it for you! What FigAI Can Do:
  • Build entire workflows from natural language descriptions
  • Add or modify existing nodes in existing workflows
  • Configure complex formulas and conditions
  • Suggest optimizations for workflow performance
  • Explain what a workflow does
[SCREENSHOT: FigAI chat interface in workflow canvas]

​
How FigAI Works

Your FigAI Analyst appears as the blue diamond on the bottom right corner of your screen. To Open FigAI:
  • Click the FigAI diamond button
  • Or press Ctrl+K (Windows) / Cmd+K (Mac)
[SCREENSHOT: FigAI button in toolbar and FigAI panel open] How It Works:
  1. You describe what you want in natural language
  2. FigAI analyzes your request and your current workflow
  3. FigAI generates nodes and connections
  4. You review and accept the changes

​
Building and Modifying Workflows with FigAI

​
Example 1: Creating a Simple Workflow

Your Prompt:
“Create a workflow that filters sales over $1000, groups by region, and calculates total sales per region”
FigAI Response: FigAI creates a workflow with these nodes:
  1. Input node (you select the data source)
  2. Filter node configured with sales > 1000
  3. Aggregation node grouped by region, summing sales
  4. Output node
[SCREENSHOT: FigAI generating a workflow with 4 nodes based on prompt]

​
Example 2: Adding to Existing Workflow

Your Prompt:
“Add a node that sorts the results by total sales, highest first in the @Weekly Sales Orders workflow”
FigAI Response: FigAI adds a Sort node between Aggregation and Output:
  • Sort column: total_sales (the aggregated column)
  • Sort direction: Descending
[SCREENSHOT: FigAI adding Sort node to existing workflow]

​
Example 3: Complex Formula

Your Prompt:
“Add a calculated column called profit_margin that’s (revenue - cost) / revenue * 100 in the @Weekly Sales Orders workflow”
FigAI Response: FigAI adds a Formula node with:
  • New column name: profit_margin
  • Formula: ([revenue] - [cost]) / [revenue] * 100
[SCREENSHOT: FigAI configuring Formula node with calculation]
Be Specific: The more details you provide, the better FigAI’s suggestions. Include column names, conditions, and desired output.

​
Effective FigAI Prompts

​
Good Prompts

  • Specific: “Filter customers where status = ‘active’ AND created_date > ‘2024-01-01’”
  • Clear Goal: “Calculate average order value by customer segment”
  • Column Names: “Join orders table with customers table on customer_id”
  • Step-by-Step: “First filter sales by date, then group by product, then sort by total descending”

​
Less Effective Prompts

  • Too Vague: “Clean my data”
  • Missing Details: “Calculate something with sales” (what calculation?)
  • Ambiguous: “Fix the workflow” (what’s wrong?)
Tip: If FigAI asks clarifying questions, answer them to get better results.

​
FigAI Prompt Examples

​
Data Filtering

“Show only rows where region is ‘West’ or ‘East’ and sales_amount > 500”
“Remove rows with null values in the email column”
“Keep only the top 100 rows after sorting by date”

​
Data Transformation

“Convert the created_date column from text to date format”
“Rename ‘cust_name’ to ‘customer_name’ and ‘qty’ to ‘quantity’”
“Add a full_name column by combining first_name and last_name with a space”

​
Aggregation

“Count the number of orders per customer”
“Calculate total revenue and average order value by product category”
“Group by month and year, summing sales for each period”

​
Joining Data

“Join this workflow with the customers table using customer_id as the key”
“Left join with products table on product_id, keeping all rows from orders”

​
Complex Logic

“Add a column called ‘customer_tier’ that shows ‘Gold’ if total_purchases > 10000, ‘Silver’ if > 5000, otherwise ‘Bronze’”
“Calculate year-over-year growth percentage for each product”

​
Reviewing AI-Generated Workflows

Always review FigAI’s changes, as LLMs can make mistakes:

​
Check Configuration

  1. Verify Column Names: Ensure FigAI used the correct column names from your data
  2. Check Formulas: Review calculated fields for accuracy
  3. Validate Filters: Confirm filter conditions match your intent
  4. Test Logic: Run the workflow and preview results
[SCREENSHOT: Reviewing FigAI generated node configuration]

​
FigAI Workflow Explanations

FigAI can explain existing workflows: Your Prompt:
“Explain what the @Weekly Sales Orders workflow does”
FigAI Response:
“This workflow:
  1. Loads sales data from the Input node
  2. Filters to sales over $1,000
  3. Groups by region and calculates total sales
  4. Sorts regions by total sales (highest first)
  5. Outputs the top 10 regions
Use Case: Identify your best-performing sales regions”
[SCREENSHOT: FigAI workflow explanation with step-by-step breakdown]

​
Best Practices

Start Simple: Begin with basic requests to get familiar with FigAI’s capabilities. Add complexity gradually.
Iterate: If the first result isn’t perfect, ask FigAI to modify it instead of rejecting and starting over.
Use Examples: Include example values in your prompts. “Filter where region is ‘West’ (like California, Oregon)”
Verify Results: Always run the workflow and check the data preview after accepting FigAI suggestions.