AI Field Intelligence
AI Field Intelligence makes your fields smarter. Instead of accepting whatever someone types, AI can ask follow-up questions, validate against rules, and extract information from documents.
Why Use AI Intelligence?
Section titled “Why Use AI Intelligence?”Without AI: Someone types “car accident” in your incident description field. You have to follow up manually to get details.
With AI: The AI asks “Where and when did this happen? Were there injuries? What’s the damage?” until it has a complete picture, automatically.
Types of AI Intelligence
Section titled “Types of AI Intelligence”1. Socratic Negotiation
Section titled “1. Socratic Negotiation”AI asks follow-up questions until it gets a complete answer.
Best for:
- Description fields
- Complex information
- Qualitative data
2. Strict Validation
Section titled “2. Strict Validation”AI validates answers against specific rules.
Best for:
- Format requirements
- Specific criteria
- Structured data
3. Document Extraction (Vision AI)
Section titled “3. Document Extraction (Vision AI)”AI reads uploaded documents and extracts information.
Best for:
- Resumes → Name, experience, skills
- IDs → Name, DOB, address
- Invoices → Amount, dates, line items
Setting Up Socratic Negotiation
Section titled “Setting Up Socratic Negotiation”Socratic Negotiation is perfect for fields where you need complete, detailed answers.
Step 1: Select a Field
Section titled “Step 1: Select a Field”This works best with:
- Textarea fields (long descriptions)
- Text fields (shorter responses)
Step 2: Open AI Settings
Section titled “Step 2: Open AI Settings”- Click the field to edit it
- Find AI Intelligence in the settings panel
- Click to expand
Step 3: Enable Socratic Mode
Section titled “Step 3: Enable Socratic Mode”Toggle Socratic Negotiation to On.
Step 4: Define the Goal
Section titled “Step 4: Define the Goal”Tell the AI what a “complete” answer looks like. Be specific!
Example goals:
| Field | Goal |
|---|---|
| Accident Description | ”Include: date/time, location, parties involved, what happened, damage to vehicles, injuries, and any witnesses” |
| Project Requirements | ”Include: project goals, target audience, desired features, timeline, and budget constraints” |
| Job Experience | ”Include: job title, company name, duration, main responsibilities, and key achievements” |
| Support Issue | ”Include: what happened, when it started, steps to reproduce, what they’ve already tried, and error messages” |
Step 5: Set Strictness Level
Section titled “Step 5: Set Strictness Level”How persistent should the AI be?
| Level | Behavior |
|---|---|
| Low | Asks 1-2 follow-ups, then accepts |
| Medium | Asks until most criteria are met |
| High | Insists on complete information |
Tip: Start with Medium. Adjust based on feedback.
Example Conversation
Section titled “Example Conversation”Field: “Describe the accident”
Goal: “Include date/time, location, parties involved, what happened, damage, and witnesses”
IntakeBot: Please describe what happened.
User: I was in a car accident.
AI: I need a few more details. When and where did the accident happen?
User: Yesterday afternoon on Main Street.
AI: What exactly happened, and what damage was there?
User: A truck ran a red light and hit my driver's side door.My door is dented and won't open properly.
AI: Were there any other parties, injuries, or witnesses?
User: No injuries, just me and the truck driver.A pedestrian saw it happen.
AI: Thank you, I have all the details I need.The AI continues until it has a complete picture, no manual follow-up needed.
Setting Up Strict Validation
Section titled “Setting Up Strict Validation”Strict Validation ensures answers meet specific criteria before accepting them.
Step 1: Select a Field
Section titled “Step 1: Select a Field”Works with any field type.
Step 2: Enable Strict Validation
Section titled “Step 2: Enable Strict Validation”- Open AI Intelligence settings
- Toggle Strict Validation to On
Step 3: Define the Rules
Section titled “Step 3: Define the Rules”Tell the AI what makes an answer valid.
Example rules:
| Field | Validation Rule |
|---|---|
| Policy Number | ”Must be format: two letters, dash, six digits, dash, two letters (e.g., AB-123456-CD)“ |
| Phone Number | ”Must be a valid US phone number with area code” |
| Date | ”Must be within the last 30 days” |
| ”Must be a company email, not personal (no gmail, yahoo, hotmail)“ | |
| URL | ”Must be a working website URL starting with https” |
Example Conversation
Section titled “Example Conversation”Field: “Enter your policy number”
Rule: “Format: XX-123456-YY”
IntakeBot: What's your policy number?
User: 123456
AI: Policy numbers should be in the format XX-123456-YY(two letters, dash, six digits, dash, two letters).Please check and try again.
User: AB-123456-CD
AI: Got it, thank you!Setting Up Document Extraction
Section titled “Setting Up Document Extraction”Let AI read uploaded documents and pre-fill fields.
How It Works
Section titled “How It Works”- Someone uploads a document (resume, ID, invoice)
- AI analyzes the document using Vision
- Relevant fields are pre-filled
- User confirms or edits the extracted data
Step 1: Add a File Upload Field
Section titled “Step 1: Add a File Upload Field”- Add a File field to your IntakeBot
- Configure allowed types (PDF, images, etc.)
- Give it a descriptive label like “Upload your resume”
Step 2: Add Fields to Extract Into
Section titled “Step 2: Add Fields to Extract Into”Add the fields where you want extracted data to go:
- Name (text)
- Email (email)
- Phone (phone)
- Years of Experience (number)
- Skills (multi-select or text)
Step 3: Enable Vision Extraction
Section titled “Step 3: Enable Vision Extraction”- On each target field, open AI Intelligence
- Enable Extract from documents
- Specify what to look for
Example extraction prompts:
| Field | Extraction Prompt |
|---|---|
| Name | ”Extract the person’s full name” |
| ”Extract the email address” | |
| Years of Experience | ”Calculate total years of work experience” |
| Skills | ”Extract technical skills and tools mentioned” |
Example Flow
Section titled “Example Flow”- User uploads their resume PDF
- AI analyzes: “John Smith, [email protected], 8 years experience in marketing, skills: SEO, Google Ads, Analytics”
- Name, email, experience, and skills fields are pre-filled
- User reviews and confirms
Result: What used to require manual data entry now happens automatically.
Privacy: Protecting Sensitive Data
Section titled “Privacy: Protecting Sensitive Data”Some information should never be processed by AI.
Private Fields
Section titled “Private Fields”Mark fields as Private when they contain:
- Social Security Numbers
- Medical information
- Financial account numbers
- Passwords or credentials
- Other sensitive PII
How to enable:
- Edit the field
- Open Privacy settings
- Enable Private Field
What happens:
- Data is stored separately
- AI never sees or processes it
- Only workspace admins can view
- Field is marked with a lock icon
When to Use Private Fields
Section titled “When to Use Private Fields”| Data Type | Use Private? |
|---|---|
| Name, email, phone | No (standard PII is fine) |
| Social Security Number | Yes |
| Medical conditions | Yes |
| Credit card numbers | Yes |
| Login credentials | Yes |
| Salary information | Consider it |
Important: Private fields cannot use AI Intelligence features (no Socratic mode, no extraction). This is by design, the AI never sees this data.
Practical Examples
Section titled “Practical Examples”Example 1: Insurance Claim Intake
Section titled “Example 1: Insurance Claim Intake”Field: “Describe the incident”
Socratic Goal:
“A complete incident description includes: date and time, location (address or intersection), what happened, parties involved (names if known), damage to property, injuries if any, witness information, and police report number if available.”
Strictness: High (insurance claims need details)
Example 2: Project Brief
Section titled “Example 2: Project Brief”Field: “Tell us about your project”
Socratic Goal:
“Include: what you’re trying to accomplish, who the target audience is, what success looks like, timeline expectations, and any constraints or requirements.”
Strictness: Medium (creative projects can be more flexible)
Example 3: Support Ticket
Section titled “Example 3: Support Ticket”Field: “Describe your issue”
Socratic Goal:
“Include: what’s happening, when it started, steps to reproduce, what you’ve already tried, and any error messages you’ve seen.”
Strictness: Medium (balance detail with user frustration)
Example 4: Job Application Screening
Section titled “Example 4: Job Application Screening”Field: “Why are you interested in this role?”
Socratic Goal:
“Response should mention: specific interest in the company or mission, relevant experience, and what they hope to contribute.”
Strictness: Low (don’t interrogate candidates)
Tips for Best Results
Section titled “Tips for Best Results”Be Specific in Your Goals
Section titled “Be Specific in Your Goals”❌ “Get a complete answer”
✅ “Include: date, location, parties involved, damage assessment, and witnesses”
Match Strictness to Context
Section titled “Match Strictness to Context”- High: Legal, insurance, compliance
- Medium: Business intake, support
- Low: Feedback, casual inquiries
Test with Real Scenarios
Section titled “Test with Real Scenarios”Before publishing, test your AI settings with realistic answers, both complete and incomplete, to see how the AI responds.
Don’t Overuse AI
Section titled “Don’t Overuse AI”Simple fields (email, phone, dropdown selections) don’t need AI intelligence. Reserve it for fields where incomplete answers are actually a problem.
Combine with Conditional Logic
Section titled “Combine with Conditional Logic”Use conditional fields to show AI-enabled fields only when needed. No point using AI credits on a follow-up question that wasn’t triggered.
AI Credits Usage
Section titled “AI Credits Usage”AI Intelligence uses your AI credits:
- Each Socratic exchange uses credits
- Vision document extraction uses credits
- Strict validation uses fewer credits
Monitor usage in Settings → Usage.
Troubleshooting
Section titled “Troubleshooting””AI isn’t asking follow-ups”
Section titled “”AI isn’t asking follow-ups””- Verify Socratic Negotiation is enabled
- Check that you’ve defined a goal
- Ensure the field type supports AI (text/textarea)
- Verify you have AI credits remaining
”AI is being too persistent”
Section titled “”AI is being too persistent””- Lower the strictness level
- Simplify your goal (fewer required elements)
- Add “nice to have” vs “required” distinction in goal
”Extraction isn’t working”
Section titled “”Extraction isn’t working””- Check file type is supported
- Ensure document is readable (not scanned poorly)
- Verify extraction is enabled on target fields
- Check Vision credits balance
Next Steps
Section titled “Next Steps”- Workflow Routing: Auto-route based on AI-extracted data
- Process Boards: Track submissions through stages
- Contacts: AI-enriched contact profiles