Usage Examples
These examples show real conversations between users and AI assistants connected to SmartAlex via MCP. Each example shows the natural language prompt, the tools the assistant calls, and the result.These examples work with any MCP-compatible client , Claude Desktop, Claude Code, Cursor, VS Code, or ChatGPT. The AI assistant automatically selects the right tools based on your request.
Example 1: Contact Management Workflow
Import and organize contacts
You: “Add a new contact Sarah Chen, email sarah@acmerealty.com, phone +1 415 555 0123, company Acme Realty. Tag her as enterprise and buyer.” Assistant calls:smartalex_create_contact
smartalex_create_deal
Example 2: Call Analysis and Follow-Up
Review recent calls and take action
You: “Show me my last 5 calls.” Assistant calls:smartalex_list_calls with per_page: 5
Assistant: “Here are your 5 most recent calls:
| # | Contact | Direction | Duration | Sentiment | Status |
|---|---|---|---|---|---|
| 1 | Sarah Chen | Outbound | 3:05 | 0.72 (positive) | Completed |
| 2 | Mike Rodriguez | Inbound | 1:45 | 0.31 (negative) | Completed |
| 3 | Lisa Park | Outbound | 4:22 | 0.85 (positive) | Completed |
| 4 | James Wilson | Outbound | 0:30 | 0.15 (negative) | No answer |
| 5 | Anna Taylor | Inbound | 2:10 | 0.65 (positive) | Completed |
smartalex_get_call with the call UUID
Assistant: “Here’s the transcript from Mike’s call. He expressed frustration about scheduling delays. Key objections: timing conflict with the Q2 deadline, and pricing concerns for the premium tier. I’d recommend a follow-up call with a discount offer or flexible scheduling options.”
You: “Update Mike’s contact , add a tag ‘needs-follow-up’.”
Assistant calls: smartalex_update_contact
Example 3: Pipeline Review and Deal Management
Analyze your sales pipeline
You: “Give me a pipeline overview. How many deals in each stage?” Assistant calls:smartalex_list_deals (all stages)
Assistant: “Here’s your pipeline breakdown:
| Stage | Deals | Total Value |
|---|---|---|
| Lead | 8 | $42,000 |
| Qualified | 5 | $187,500 |
| Showing | 3 | $95,000 |
| Offer | 2 | $150,000 |
| Under Contract | 1 | $82,000 |
smartalex_update_deal
Example 4: Full Campaign Workflow
Launch an outbound campaign end-to-end
You: “I want to set up an outbound campaign.” Assistant calls:smartalex_list_agents and smartalex_list_phone_numbers
Assistant: “Here’s what’s available:
Agents:
| Agent | Language | Status |
|---|---|---|
| Sales Assistant | English | Active |
| Support Agent | English | Active |
| Number | Country |
|---|---|
| +1 (555) 123-4567 | US |
smartalex_create_campaign
smartalex_add_contacts_to_campaign
smartalex_start_campaign
Example 5: Webhook Integration
Set up real-time event notifications
You: “I want to send call completion events to my CRM at https://crm.example.com/webhooks/smartalex” Assistant calls:smartalex_create_webhook
smartalex_list_webhooks
Assistant: “You have 2 active webhooks:
| Webhook | URL | Events | Failures |
|---|---|---|---|
| CRM call sync | crm.example.com/webhooks/smartalex | call.completed, call.started | 0 |
| Slack notifier | hooks.slack.com/services/… | deal.stage_changed | 0 |
Example 6: Platform Health Check
Daily operations check
You: “How’s my SmartAlex platform doing?” Assistant calls:smartalex_get_platform_status
Assistant: “SmartAlex is operational. Here’s your account overview:
| Metric | Value |
|---|---|
| Status | Operational |
| Contacts | 247 |
| Campaigns | 4 active |
| Total Calls | 1,832 |
| Deals | 19 in pipeline |
Multi-Step Workflows
The AI assistant can chain multiple tools together in a single conversation to complete complex workflows.Lead qualification workflow
You: “Run a pipeline review. Show me my qualified leads, check if any have recent calls with negative sentiment, and flag deals that might need attention.” The assistant will automatically:- Call
smartalex_list_dealswithstage: "qualified" - For each deal with a contact, call
smartalex_list_callsto check recent activity - Cross-reference sentiment scores
- Provide a summary with recommendations
Campaign performance analysis
You: “How did my Q2 Enterprise Outreach campaign perform? Show me the calls, sentiment breakdown, and any deals that came from it.” The assistant will:- Call
smartalex_list_campaignsto find the campaign - Call
smartalex_list_callsto pull calls from that campaign - Call
smartalex_list_dealsto find related deals - Provide conversion analysis and ROI estimates
Using Prompts
SmartAlex includes 5 built-in prompts that guide the AI through complex analysis:Campaign Strategy
You: “Use the campaign-strategy prompt to help me design a follow-up campaign for my real estate leads.” The assistant will:- Pull your current contacts, agents, and campaigns
- Analyze which contacts haven’t been reached
- Recommend agent assignment, timing, and messaging
- Draft a campaign plan
Pipeline Review
You: “Run a pipeline review.” The assistant uses thepipeline-review prompt to:
- Analyze deals at every stage
- Identify bottlenecks (stages with stale deals)
- Flag at-risk deals (high value, no recent activity)
- Provide a forecast based on conversion rates
Lead Qualification
You: “Score my leads using the lead-qualification prompt.” The assistant will:- Pull contacts tagged as leads
- Check call history and transcript sentiment
- Score each lead on engagement, fit, and timing
- Rank leads by likelihood to convert
Tips
Be specific with names and numbers
Be specific with names and numbers
Instead of “update the deal”, say “move the Acme Realty deal to offer stage” , the assistant will search by name.
Chain requests naturally
Chain requests naturally
You can say “Create a contact, then create a deal for them” in one message. The assistant handles the sequencing.
Ask for analysis, not just data
Ask for analysis, not just data
Instead of “list my calls”, try “which calls had the lowest sentiment this week?” , the assistant will filter and analyze for you.
Use prompts for complex tasks
Use prompts for complex tasks
When you need multi-step analysis, reference a prompt by name: “Use the pipeline-review prompt” or “Run a lead qualification analysis.”
Next Steps
- npm Package Setup , Install locally with Claude Desktop, Cursor, or VS Code
- Tools Reference , Complete parameter reference for all 28 tools
- MCP Overview , Architecture, resources, and prompts

