AI Agents

1. Navigate to AI Agents in the left sidebar
2. Click "AI Employees" category
3. Select the employee type you want to create
4. Click "Create" and follow the setup wizard:
   • Name: Give your employee a descriptive name
   • Department: Select which department to analyze (pre-set based on employee type)
   • Schedule: Choose when reports are generated (daily, weekly, monthly)
   • Recipients: Select who receives the reports
   • Focus Areas: Choose specific metrics or topics to emphasize
5. Review configuration and click "Activate"

Real-world example of a Sales Analyst AI Employee configuration:

Name: "Q1 Sales Performance Analyst"
Department: B2B Sales
Schedule: Every Monday at 8 AM
Recipients: [email protected], [email protected]

Focus Areas:
✓ Pipeline velocity
✓ Conversion rates by stage
✓ Average deal size trends
✓ Top objections encountered
✓ Win/loss patterns
✓ Individual rep performance

Output Format:
- Executive summary (3-5 key insights)
- Pipeline metrics table
- Conversion funnel visualization
- Top coaching opportunities
- Recommended actions for coming week

Result: Sales managers receive actionable insights every Monday morning, identifying coaching opportunities and pipeline risks before weekly team meetings.

• Be specific with focus areas: The more targeted your configuration, the more actionable the insights
• Align schedule with meetings: Send reports before key meetings (e.g., Monday morning before sales standup)
• Start narrow, expand later: Begin with one department, then add more as you see value
• Use consistent naming: Name employees by their purpose (e.g., "Enterprise Sales Q1 Analyst")
• Review first reports: Check initial outputs and adjust focus areas if needed

1. Go to AI Agents → AI Fields
2. Click "Create Field"
3. Choose field type and configure:
   • Field Name: What you're extracting (e.g., "Budget Range")
   • Description: Help AI understand what to look for
   • Extraction Prompt: Instructions for the AI
   • Validation Rules: Format requirements or constraints
   • Default Value: What to use if nothing is found
4. Configure CRM sync (optional):
   • Map to CRM field (Salesforce, HubSpot, Pipedrive)
   • Set sync direction (one-way or two-way)
   • Choose sync frequency (real-time or daily)
5. Test on sample conversations
6. Activate for all conversations

The quality of your extraction prompt directly impacts accuracy:

DO: 'Extract the specific dollar amount or range mentioned for annual budget'
DON'T: 'Get budget info'

DO: 'Extract decision maker titles (e.g., VP, Director, C-level) and their departments'
DON'T: 'Get decision makers'

DO: 'If no budget is mentioned, return "Not Discussed". If they say "flexible", note that.'
DON'T: 'Extract budget'

DO: 'Return dates in YYYY-MM-DD format. If only a month is mentioned, use the last day of that month.'
DON'T: 'Extract dates'

1. Navigate to AI Agents → AI Summaries
2. Click "Create Custom Summary"
3. Configure summary:
   • Summary Name: Descriptive name (e.g., "Enterprise Sales Summary")
   • Template: Start from template or create from scratch
   • Prompt: Define what to include and how to format
   • Length: Specify desired length (brief, moderate, detailed)
   • Format: Choose output style (bullets, paragraphs, sections)
4. Preview on sample conversations
5. Adjust prompt based on results
6. Activate for department or all conversations

Create a sales call summary with these sections:

## Deal Status
- Current stage in pipeline
- Changes from last conversation
- Overall deal health (Green/Yellow/Red)

## Key Discussion Points
- Top 3 topics discussed
- Customer sentiment on each

## Stakeholders
- Who participated
- New stakeholders identified
- Decision-making authority

## Objections & Concerns
- Any objections raised
- How they were addressed
- Remaining concerns

## Next Steps
- Agreed action items with owners
- Timeline for follow-up
- Success criteria for next meeting

Keep each section concise (2-3 sentences). Highlight any red flags in bold.

• Balance detail and brevity: More detail isn't always better - focus on actionable insights
• Use consistent formatting: Structured summaries are easier to scan than paragraphs
• Include context clues: Dates, participant names, and call type help orientation
• Highlight urgency: Use formatting (bold, caps) to call out time-sensitive items
• Test with diverse calls: Ensure your prompt works for short and long calls, positive and negative outcomes
• Version your prompts: Keep track of what changes improve quality

1. Go to AI Agents → AI Playbooks
2. Select "Create New Playbook" or choose template
3. Define playbook structure:
   • Playbook Name: E.g., "Enterprise Discovery Methodology"
   • Department: Which team uses this playbook
   • Call Type: When this playbook applies
4. Add playbook steps (minimum 3, maximum 15):
   • Step Name: What should happen (e.g., "Budget Discovery")
   • Description: Detailed explanation of the step
   • Success Criteria: What good execution looks like
   • Key Questions: Specific questions that should be asked
   • Required: Is this step mandatory or optional?
5. Set scoring weights (optional - how important is each step)
6. Test on past conversations
7. Activate playbook

After each conversation, the playbook generates:

• Start with your best rep: Document what your top performers do consistently
• Keep steps clear and actionable: "Ask about budget" not "Discuss financials"
• Don't overcomplicate: 5-8 steps is ideal; more than 12 becomes unwieldy
• Allow flexibility: Mark optional steps as such; not every call follows the same path
• Update regularly: Review and refine based on what actually works
• Use for onboarding: Playbooks are excellent training tools for new hires

Advanced agents require more configuration than simple fields:

1. Navigate to AI Agents → Advanced AI Agents
2. Choose agent template or start from scratch
3. Configure agent workflow:
   • Input Sources: What data the agent analyzes
   • Processing Steps: Multi-step analysis workflow
   • Decision Logic: Rules and criteria for decisions
   • Tools & Integrations: External systems to access
   • Output Actions: What happens with results
4. Define permissions and access
5. Test thoroughly on historical data
6. Monitor performance after activation

For Basic Keyword Trackers:

1. Go to AI Agents → Keyword Trackers
2. Click "Basic Keyword Tracker"
3. Enter keywords/phrases (one per line)
4. Choose case-sensitive matching (optional)
5. Save and activate

For AI Keyword Trackers:

1. Click "AI Keyword Tracker"
2. Name your concept (e.g., "Budget Objections")
3. Provide positive examples (phrases that match):
   • "That's outside our budget"
   • "We can't afford that right now"
   • "Price is a concern for us"
4. Provide negative examples (similar phrases that shouldn't match):
   • "Our budget is flexible"
   • "Price isn't an issue"
5. Train on past conversations
6. Review accuracy and adjust examples
7. Activate when satisfied

Once activated, trackers provide:

• Statistical Widgets: View mention frequency over time
• Conversation Filtering: Find all conversations where keyword was mentioned
• Trend Analysis: Track how often concepts come up week-over-week
• Correlation Analysis: See which keywords appear together
• Dashboard Integration: Add tracker widgets to Insights dashboard

From the AI Agents page, you can see:

• Active Status: Running, paused, or inactive
• Performance Metrics: Accuracy, usage, error rate
• Processing Stats: How many conversations processed
• Last Run: When the agent last executed
• Resource Usage: Processing time and credits used

To modify an automation:

1. Click the automation name
2. Click "Edit"
3. Make your changes
4. Choose update behavior:
   • Future Only: Apply changes to new conversations only
   • Reprocess All: Re-run automation on historical conversations
   • Reprocess Failed: Only retry previously failed conversations
5. Save changes

Get more value by using AI agents together:

• Start small: Begin with 2-3 high-impact automations, add more as you see value
• Audit regularly: Review which automations are actually being used quarterly
• Consolidate where possible: Use one well-configured field instead of three similar ones
• Set clear owners: Assign someone to maintain each automation
• Track ROI: Measure time saved vs. effort to maintain