Pro

AI Reply

Intelligent, AI-powered responses to form submissions

AI Reply automatically generates personalized, contextual responses to form submissions using AI. Unlike static auto-responders, AI Reply understands the content of each submission and generates unique, helpful replies based on your knowledge base.

Pro Feature

AI Reply is available on the Pro and Advanced plans. Upgrade to Pro to unlock this feature.

How It Works

AI Reply uses your configured AI provider (OpenAI, Anthropic, or Google) to generate responses:

1

Form Submitted

User submits your form with their message, question, or inquiry.

2

AI Generates Reply

AI processes the submission with your knowledge base to craft a relevant response.

3

Response Sent

The AI-generated reply is automatically emailed to the form submitter.

Bring Your Own Key (BYOK)

AI Reply uses a "Bring Your Own Key" model. You provide your own API key from your preferred AI provider, giving you:

Full Control Over Costs

Pay only for what you use directly to the AI provider

Provider Choice

Use OpenAI (GPT-4), Anthropic (Claude), or Google (Gemini)

Model Selection

Choose from various models based on your needs

Security

Your API key is encrypted at rest using AES-256 encryption

Setting Up AI Reply

1

Navigate to Settings

Go to your dashboard and navigate to Settings → AI Reply.

2

Choose Your AI Provider

Select your preferred AI provider: OpenAI, Anthropic, or Google. Each provider offers different models with varying capabilities. See the Supported Models section below for details.

3

Enter Your API Key

Get an API key from your chosen provider and enter it in the settings. The key is encrypted before being stored.

OpenAI: Get your key from platform.openai.com

Anthropic: Get your key from console.anthropic.com

Google: Get your key from aistudio.google.com

4

Add Your Knowledge Base

Provide context for the AI to generate relevant responses:

  • Text content: Enter information directly (FAQs, product details, policies)
  • Files: Upload .txt or .md files with detailed information (up to 25MB total)
5

Configure Settings

Customize the AI behavior: set rate limits, exclude sensitive fields, and configure fallback options.

6

Test Configuration

Use the "Test Configuration" button to verify everything works correctly before going live.

Knowledge Base

The knowledge base provides context for the AI to generate accurate, relevant responses. The more detailed your knowledge base, the better the AI replies will be.

What to Include

Business Information

Company name, services, products, pricing, hours, contact methods

FAQs

Common questions and their answers

Policies

Shipping, returns, privacy, terms of service

Response Guidelines

Tone of voice, key phrases, things to avoid

Knowledge Base Example

MARKDOWN

Excluding Sensitive Fields

You can exclude certain form fields from being sent to the AI for privacy reasons. Common fields to exclude:

  • Credit card numbers
  • Passwords
  • Social security numbers
  • Internal reference numbers

Enter field names (comma-separated) in the "Exclude Fields" setting. Field matching is case-insensitive.

Fallback Configuration

If the AI fails to generate a reply (API error, rate limit, etc.), you can configure a fallback static response:

Enable Fallback

Toggle on to send a static message when AI fails

Fallback Subject

Email subject for the fallback message

Fallback Message

Static message to send when AI fails

When AI fails, you'll also receive a notification email with details about the error.

Rate Limits

Configure rate limits to control usage and prevent abuse:

PlanDefault Per HourDefault Per Day
Pro100500
Advanced5002,000

You can set custom limits lower than the defaults in your settings to further control usage.

Viewing AI Reply Logs

Monitor your AI reply activity in the AI Reply Logs dashboard:

  • View success/failure status of each AI reply
  • Track token usage for each request
  • See error details for failed requests
  • Filter by success/failure status
  • Logs are retained for 14 days

Supported Models

Static Forms AI Reply supports the latest models from all major AI providers. For detailed pricing information, please visit the official documentation for each provider.

OpenAI

  • gpt-5.2 - Latest flagship model for coding and agentic tasks (400K context)
  • gpt-5.2-pro - Maximum intelligence for high-stakes research (400K context)
  • gpt-5-mini - Fast and cost-efficient for well-defined tasks
  • gpt-5 - Previous generation flagship model

View OpenAI model details and pricing →

Anthropic

  • claude-opus-4-5-20251101 - Most capable Claude model
  • claude-sonnet-4-5-20250929 - Best for coding and complex tasks

View Anthropic model details and pricing →

Google

  • gemini-3-flash - Fast with strong reasoning capabilities
  • gemini-3-pro - Complex agentic workflows and reasoning
  • gemini-2.5-pro - Stable with adaptive thinking
  • gemini-2.5-flash - First stable 2.5 Flash model

View Google Gemini model details and pricing →

Model Selection

Choose models based on your specific needs. Latest generation models (GPT-5, Claude Opus/Sonnet 4.5, Gemini 3) offer improved performance and capabilities. Legacy models remain available for backward compatibility.

Privacy and Security

Data Processing Disclosure

When AI Reply is enabled, form submission data is sent to your configured AI provider (OpenAI, Anthropic, or Google) for processing. This includes form field values (except excluded fields) and your knowledge base content. Please review your AI provider's privacy policy and ensure compliance with your data protection requirements.

API Key Encryption

Your API key is encrypted using AES-256-CBC before storage

Field Exclusion

Sensitive fields can be excluded from AI processing

You Control Your Data

Data is sent directly to your AI provider account, not stored by Static Forms

System Guardrails

To ensure safe, compliant, and professional email responses, Static Forms applies system guardrails to all AI-generated replies. These guardrails are prepended to your custom system prompt. Some guardrails are mandatory and always enforced, while others can be customized to fit your needs.

Mandatory Guardrails

These guardrails are always enforced and cannot be customized or disabled. They ensure proper email formatting and scope limitations:

Email Standards

The AI will never generate:

  • Harmful, offensive, discriminatory, or inappropriate content
  • Profanity, hate speech, or harassment
  • Adult or explicit content

Scope Limitations

The AI will:

  • Only answer based on information in your knowledge base
  • Acknowledge when information is not available
  • Never make up information or hallucinate facts
  • Stay focused on the form submission topic

These guardrails work alongside your custom system prompt to ensure all AI-generated emails meet professional and legal standards while maintaining the tone and style you specify.

Optional Guardrails

These guardrails are recommended defaults but can be customized in your settings:

Safety Rules

The AI will never generate:

  • Harmful, offensive, discriminatory, or inappropriate content
  • Profanity, hate speech, or harassment
  • Adult or explicit content

Legal and Compliance Rules

The AI will never:

  • Make unauthorized promises, guarantees, or commitments
  • Provide medical, financial, or legal advice
  • Claim to be a licensed professional
  • Share personal information beyond what's in the form submission

Customizing Optional Guardrails

You can customize the optional guardrails (safety and legal/compliance rules) in your AI Reply settings. The guardrails editor allows you to:

  • Modify existing rules to match your specific requirements
  • Add additional rules or guidelines
  • Use the "Use Default" button to restore the default optional guardrails
  • Leave blank to use the default optional guardrails

Note

Mandatory guardrails (email formatting and scope limitations) are always enforced and cannot be customized. Only optional guardrails (safety and legal/compliance rules) can be modified.

Important

Guardrails must be plain text format (no MDX, HTML, or markdown) to ensure email compatibility. The AI will generate complete, ready-to-send email content without any placeholders or template variables.

AI Reply vs Auto Responder

Choose the right feature for your needs:

Auto Responder

  • Static, templated message
  • Same response for all submissions
  • Supports template variables
  • No external API required
  • Instant, no latency

AI Reply

  • Dynamic, contextual responses
  • Unique reply for each submission
  • Uses knowledge base context
  • Requires AI provider API key
  • Slight latency (~1-3 seconds)

Troubleshooting

AI Reply Not Sending

  • Verify AI Reply is enabled in settings
  • Check that your API key is valid
  • Ensure form includes an email field
  • Check AI Reply logs for errors
  • Verify you haven't exceeded rate limits

Invalid API Key Error

  • Re-enter your API key in settings
  • Verify the key is active in your provider's dashboard
  • Check that you have billing set up with the provider
  • Ensure the key has the required permissions

Poor Quality Responses

  • Add more detail to your knowledge base
  • Include specific FAQs and answers
  • Try a more capable model (e.g., GPT-4o, Claude 3.5 Sonnet)
  • Adjust the system prompt with clear instructions

Rate Limit Exceeded

  • Wait for the next hour/day for limits to reset
  • Increase rate limits in settings (within tier limits)
  • Consider upgrading to Advanced plan for higher limits