Source: Current speak node
Extraction instructions: Extract the maximum home budget the caller states as a plain number in USD, with no commas or text. If a range is given (for example "200 to 250k"), choose the upper bound. If not provided, leave empty.
Format: Number
Use with: Rule outcome `budget >= 250000` -> High-intent path.
Source: Conversation history
Extraction instructions: Extract the caller's email. Normalize to lowercase and remove spaces. If multiple addresses are present, choose the most recent. If none, leave empty.
Format: Text
Use with: Rule outcome `email` matches `/.+@.+\\..+/` -> Collect address details.
Source: Current speak node
Extraction instructions: Determine whether the caller has explicitly agreed to a call-back. Return `true` for clear consent like "Yes, call me later," otherwise return `false`.
Format: Boolean
Use with: If `callback_ok == true` -> trigger [Actions](/agents/actions) to create a follow-up task.
Account / Configure
Output
Next step
Connect the account (if required) and configure step-specific options.
AI
✨
Extract Fields
✨
Custom Prompt
Condition
🔀
Filter
🔀
If Else
🔀
Switch
🔀
Random Outcome
When a new lead is added to your CRM, you can trigger an Automation to trigger your Voice Agents to make a call, who can then reach out to the lead and update the CRM with the outcome.
This allows your Voice Agents to have all the information they need to have a productive conversation with the caller, whether it's real-time stock prices, customer purchase history, or current inventory levels.
When used in conjunction with other Actions, you can create complex workflows that run automatically, without any manual intervention.
This allows you to reach out to leads while they're still engaged, increasing the likelihood of a successful conversation.
Low hallucination risk"| H["🤖 Genius Knowledge Base"] Caution -->|"Higher risk
Convert to Q&A format"| H style H fill:#e3f2fd,stroke:#1976d2,stroke-width:4px style Recommended fill:#f1f8f4,stroke:#388e3c,stroke-width:2px style Caution fill:#fff8e1,stroke:#f57c00,stroke-width:2px ``` ## Getting Started ### Step 1: Create a Genius Database 1. **Navigate** to **Tools → Genius** in the primary navigation 2. **Click** "Create New Genius" button 3. **Enter** a descriptive database name 4. **Save** to create your new knowledge base The new database appears in the Genius list and is ready for content addition. ### Step 2: Add Content Sources 1. **Select** your newly created database from the Genius list 2. **Choose** content type (Text, Audio, PDF, CSV, or URL) 3. **Provide** a descriptive name for the source 4. **Upload file** or **enter URL** as appropriate 5. **Save** to begin processing ### Processing Time Content processing typically takes **2-10 minutes** depending on: * File size and complexity * Content type (text processes faster than audio) * Current system load A progress indicator shows processing status in the Genius source table. ## Content Management ### Viewing Processed Content After processing completes: 1. **Click** the three-dot menu next to any source in the table 2. **Select** "View" to see processed content 3. **Review** how your content was transformed into Q\&A format The processed format shows how agents will understand and access your information during calls. ### Managing Sources **Edit Sources**: Use the three-dot menu to modify source names or settings **Delete Sources**: Remove outdated or incorrect content sources **Add Multiple Sources**: Build comprehensive databases with diverse content types ### Database Management **Database Settings**: Click the gear icon to modify database name or settings **Delete Database**: Permanently remove entire databases and all contained sources **Duplicate Content**: The same source can be added to multiple databases if needed ## Agent Integration ### Connecting to Agents Genius databases must be explicitly connected to agents through: **Automations Interface**: * Select Genius database within automation workflows * Configure how knowledge is accessed during automated processes **Agent Builder Interface**: * Choose Genius database for specific agent configurations * Set up when and how knowledge is retrieved during calls ### Multiple Database Support * **Different agents** can use different Genius databases * **Single agents** can access multiple databases if configured * **Scope selection** happens during automation or agent setup ## Content Optimization ### Writing for RAG Processing **Use Natural Language**: Write content as if explaining to a knowledgeable colleague **Include Context**: Provide background information that helps agents understand when to use specific information **Ask Questions**: Include common customer questions and comprehensive answers **Be Specific**: Avoid vague statements that could lead to ambiguous agent responses ### Example Optimization **Less Effective**: ``` Product A: $50 Product B: $75 Product C: $100 ``` **More Effective**: ``` Our product pricing is structured to meet different customer needs: Product A is our entry-level solution at $50, ideal for small businesses just getting started with our service. It includes basic features and email support. Product B at $75 represents our most popular package, offering advanced features, phone support, and integration capabilities that most growing businesses require. Product C at $100 is our enterprise solution with all premium features, dedicated account management, and custom integration support for large organizations. ``` ## URL Content Considerations ### Static Content Only **Important Limitation**: URLs are fetched **once** during setup and are not automatically refreshed or updated. **Best Practices for URLs**: * Use stable, long-term content sources * Avoid frequently changing pages * Consider downloading and uploading as files for content you control * Plan to manually update URL sources when content changes significantly ### URL Content Quality **Choose High-Quality Sources**: Select comprehensive, well-written pages that provide complete information **Avoid Dynamic Content**: Pages with frequently changing information may become outdated **Test Accessibility**: Ensure URLs are publicly accessible and not behind authentication ## Safety and Accuracy ### Source Citation Genius provides **both approaches** for information delivery: * **Behind-the-scenes processing**: Enhanced agent knowledge without explicit citation * **Source attribution**: Agents can reference specific sources when appropriate ### Content Grounding The system is designed to **ground agent responses** in provided source material, reducing hallucinations and ensuring accuracy. However, content quality directly impacts response quality. ### Quality Control **Review Processed Content**: Always check how your sources were transformed **Test Agent Responses**: Verify agents provide accurate information from your sources **Update Regularly**: Remove outdated sources and add current information **Monitor Performance**: Track how well agents utilize Genius knowledge in real calls ## Expected Results After successful Genius setup and integration: **Enhanced Agent Knowledge**: * Agents provide accurate, company-specific information during calls * Consistent responses across all agents using the same database * Reduced need for agent training on factual information **Improved Call Quality**: * Faster resolution of customer questions * More detailed and accurate responses * Professional handling of complex or specialized inquiries **Operational Benefits**: * Centralized knowledge management across all agents * Easy updates to business information affecting multiple agents * Scalable knowledge distribution for growing teams ## Limitations ### Current Limitations * **URL content** is not automatically refreshed * **Processing time** varies based on content complexity * **No real-time content updates** for existing sources ### Content Processing Considerations * **CSV hallucination risk** with complex structured data * **Processing capacity** may affect upload times during peak usage * **File size limits** may apply (specific limits not currently published)
# Zapier integration Source: https://docs.thoughtly.com/integrations/automations/zapier Connect Thoughtly to Zapier to trigger voice agents from any Zap, push call outcomes to thousands of apps, and automate workflows without writing code. # Gmail integration Source: https://docs.thoughtly.com/integrations/communication/gmail Connect Gmail to Thoughtly so your voice agents can send personalized follow-up emails, share recordings, and route email replies into agent workflows.
Access Integrations] Step1 --> Step2[Step 2:
Initiate Integration] Step2 --> Step3{Step 3:
Choose Auth Type} Step3 -->|OAuth| OAuth[Authorize via
vendor consent screen] Step3 -->|API Key| API[Enter API key
from platform] Step3 -->|Credentials| Cred[Enter username
and password] OAuth --> Step4[Step 4:
Verify & Save] API --> Step4 Cred --> Step4 Step4 --> End([Ready to Use]) classDef step1 fill:#6366f1,stroke:#4f46e5,color:#fff classDef step2 fill:#8b5cf6,stroke:#7c3aed,color:#fff classDef step3 fill:#ec4899,stroke:#db2777,color:#fff classDef step4 fill:#10b981,stroke:#059669,color:#fff class Step1 step1 class Step2 step2 class Step3,OAuth,API,Cred step3 class Step4 step4 ``` ## Post-Setup Configuration ### Making Integrations Available After successful connection, integrations become available in: **Automations Interface**: 1. Navigate to **Tools → Automations** in the primary navigation 2. Create or edit automation workflow 3. Add actions using connected integrations 4. Configure integration-specific parameters 5. Select which connected account to use (if you have multiple accounts for the same integration) **Agent Builder Interface**: 1. Open Agent Builder for target agent 2. Open a [Speak node](/agents/nodes#speak-node) and navigate to the Actions section 3. Add integration [actions](/agents/actions) to your agent workflow 4. Configure real-time integration behavior 5. Select which connected account to use from the Account tab (if you have multiple accounts for the same integration) ### Integration Usage Patterns Integrations work in two distinct contexts, each serving different use cases: | Automation Workflows | Mid-call Actions | | ---------------------------- | ----------------------------- | | Post-call CRM updates | Real-time data lookup | | Appointment scheduling | Live calendar checking | | Team notifications | Instant team alerts | | Lead qualification processes | Dynamic information retrieval | ## Testing and Validation ### Initial Connection Testing 1. **Verify** connection status remains "Connected" 2. **Test** basic functionality through simple automation 3. **Check** data flow between systems 4. **Confirm** permissions work as expected ## Multiple Accounts You can connect multiple accounts for the same integration. This is useful when: * Different team members need to use their own credentials * You manage multiple client accounts * You need separate production and testing environments * You work with multiple sub-accounts (e.g., GoHighLevel locations) When you have multiple accounts connected: 1. Each account appears as a separate connection in your integrations list with a descriptive label 2. You can select which account to use when configuring actions in Automations or Agent Builder 3. The account selector appears in the **Account** tab when setting up integration actions 4. For integrations with many accounts, use the search feature to quickly find the right one
Resources, templates, and walkthroughs to help you build powerful, fully integrated Voice Agents.