Training Your AI Twin

Your AI Twin’s intelligence comes from the content you provide. Through your dashboard at dashboard.steno.ai , you can upload content, customize personality, set guardrails, and keep your AI Twin updated.

Content Types

You can train your AI Twin on almost any type of digital content.

Audio Content

• Podcasts: Public or private podcast episodes
• Voice Memos: Recorded thoughts and teachings
• Seminar Recordings: Workshop and event audio
• Interviews: Conversations and Q&A sessions
• Audio Books: Narrated books and courses

Video Content

• YouTube Videos: Public channel content with auto-sync
• Online Courses: Pre-recorded course modules
• Webinars: Live or recorded webinar sessions
• Event Recordings: Conference talks and presentations
• Vlogs: Personal or business video content

Text Content

• Books: Published or unpublished manuscripts
• PDFs: Guides, workbooks, manuals
• Articles: Blog posts and long-form articles
• Whitepapers: Research and thought leadership documents
• Emails: Email newsletters and courses
• Website Content: Website copy and knowledge bases
• Transcripts: Transcribed conversations and teachings

Content Best Practices

Quality Over Quantity

More content isn’t always better. Focus on:

• High-quality, authoritative content that represents your best thinking
• Well-organized materials with clear structure
• Consistent messaging across all content
• Updated information that reflects your current perspective

Content Organization

When uploading content, organize it by:

1. Core Teachings: Fundamental concepts and frameworks
2. Advanced Material: Specialized or advanced topics
3. Practical Application: Examples, case studies, exercises
4. FAQs: Common questions and answers

This helps prioritize what the AI Twin learns first and ensures the most important content is emphasized.

Personality & Tone Customization

Through your dashboard, you have full control to shape your AI Twin’s behavior. This is where Steno.ai invests the most to give you market-leading creative control.

Voice & Style

Configure these settings in your dashboard:

• Tone: Professional, casual, inspirational, direct, nurturing, etc.
• Vocabulary: Technical jargon vs. simple language
• Formality Level: Formal business tone vs. conversational style
• Humor: Whether your AI Twin should use humor and what kind

Behavioral Guidelines

• Response Length: Short and punchy vs. detailed and thorough
• Question Handling: Socratic method vs. direct answers
• Proactivity: Reactive (only answers) vs. proactive (guides conversation)
• Empathy Level: How much emotional intelligence to display

You can shape your AI Twin to match your brand perfectly—whether you need a “Tough Love” style or a “Gentle Support” guide.

Knowledge Base Control

You decide your AI Twin’s boundaries and how it handles different scenarios.

Constraint Options

Strict Constraint (Recommended):

• AI Twin only answers based on your provided knowledge base
• Ensures every answer has a verifiable source
• Minimizes hallucination risk
• Best for protecting IP and brand accuracy

By default, the Steno Twin Engine forces your AI Twin to stick strictly to the content you provided. This ensures it relies on your intelligence rather than making things up.

Adaptive Mode:

• AI Twin can tap into wider knowledge when appropriate
• Useful for general questions outside your specific domain
• Still prioritizes your content first
• Requires careful guardrail configuration

Handling Off-Topic Questions

Configure how your AI Twin responds when users ask questions outside the knowledge base:

Option 1: Polite Decline

“That’s outside my area of expertise. I’m specifically trained on [your domain]. Is there something related to [your domain] I can help you with?”

Option 2: Escalation

“That’s a great question, but it’s outside my training. Let me connect you with our team for help with that.”

Option 3: General Knowledge (if Adaptive Mode)

AI Twin provides a general answer while noting it’s not based on your specific content

Guardrails & Boundaries

Set strict guardrails through your dashboard to prevent your AI Twin from:

• Discussing off-limit topics (competitors, pricing debates, etc.)
• Making promises or commitments on your behalf
• Providing advice in regulated areas (legal, medical, financial) unless appropriate
• Sharing information not in the knowledge base (if in Strict mode)
• Engaging with inappropriate or abusive users

Custom Guardrails

You can specify additional boundaries:

• Topics to Avoid: Specific subjects the AI Twin should not discuss
• Required Disclaimers: Specific warnings or disclaimers to include
• Escalation Triggers: Keywords or scenarios that should escalate to human support
• Brand Guidelines: Specific terminology to use or avoid

Keeping Your AI Twin Updated

Automatic Content Syncing

Connect your public content sources for automatic updates:

• YouTube Channels: New videos automatically added
• Podcast Feeds: New episodes automatically ingested
• RSS Feeds: Blog posts and articles automatically processed

Your AI Twin automatically learns from your latest content as soon as you publish it.

Manual Content Updates

For private content, log in to your dashboard at any time to upload new files (PDFs, videos, text) to expand your AI Twin’s intelligence instantly.

1. Log in to dashboard.steno.ai 
2. Navigate to Content Management
3. Upload new files
4. Content is processed and available quickly

Update Frequency

Recommended Schedule:

• Quarterly: For evergreen content businesses
• Monthly: For actively creating new content
• Weekly: For rapidly evolving topics or frequent content creation

Hallucination Prevention

We use several methods to ensure your AI Twin provides accurate answers:

Source-Based Responses

The primary method is constraining responses to only your provided knowledge base. This ensures every answer has a verifiable source from your content.

Confidence Scoring

Your AI Twin is trained to recognize when it’s uncertain and either:

• Ask clarifying questions
• Admit uncertainty
• Offer to escalate to human support

Quality Monitoring

Access conversation logs through your dashboard to review:

• Responses that may drift from source material
• Inconsistent messaging
• Areas where guardrails need adjustment

Testing & Refinement

Before going live:

1. Test Extensively: Try various questions and scenarios
2. Flag Issues: Use thumbs up/down feedback in the interface
3. Provide Context: Note why certain responses should be different
4. Iterate: Refine settings based on your testing

See the Dashboard Access & Testing guide for more details.

Questions about training your AI Twin? Contact support@steno.ai.