Call Center¶
A dual-purpose AI-powered chat system that provides business coaching support through both a public chat interface and an integrated call center workflow for youth entrepreneurs in rural Kenya.
Purpose¶
No business context provided yet — add a context.md to enrich this documentation.
How It Works¶
This workflow operates as a sophisticated AI chat system with two main pathways:
- Public Chat Interface: Users can interact directly through a web-based chat trigger that provides immediate AI responses
- Call Center Integration: Business Advisors (BAs) can use the system during live phone calls to get real-time coaching advice and scripts
The system uses advanced AI agents powered by Google's Gemini model to analyze business situations and provide practical micro-actions. It maintains conversation memory and can retrieve business performance summaries to give contextual advice.
Key features include: - Real-time business coaching during calls - Youth business performance analysis - Micro-action generation with BA scripts - Escalation detection for serious issues - Multi-language support (primarily Swahili and English)
Mermaid Diagram¶
graph TD
A[When chat message received] --> B[AI Agent1]
C[OpenRouter Chat Model] --> B
D[Simple Memory] --> B
E[get_summary] --> B
F[getUserRecord] --> G[getProfitData]
G --> H[Aggregate]
H --> I[AI Agent - Disabled]
J[Postgres Chat Memory] --> I
K[OpenRouter Chat Model1] --> I
L[dailySalesDataCollection] --> I
M[updateUserDataTool] --> I
N[updateUserStatusTool] --> I
I --> O[Insert rows in a table]
P[setOutputField] --> Q[Output]
Trigger¶
Chat Trigger: A public webhook-based chat interface that accepts messages and provides an initial greeting: "Hi there! 👋I am your Business Adviser. How can I assist you today?"
Nodes Used¶
| Node Type | Purpose |
|---|---|
| Chat Trigger | Receives incoming chat messages from users |
| AI Agent | Primary business coaching agent with Mshauri system prompt |
| OpenRouter Chat Model | Google Gemini 3 Flash Preview language model |
| Simple Memory | Buffer window memory for conversation context |
| Postgres Database | User record retrieval and profit data storage |
| Workflow Tools | Integration with external workflows for data operations |
| Aggregate | Combines business records for analysis |
External Services & Credentials Required¶
- OpenRouter API: Access to Google Gemini models
- Credential: "OpenRouter KDP"
- PostgreSQL Database: User data and business records storage
- Credential: "PostgresOnSupabase" / "kdpTables"
Environment Variables¶
No specific environment variables are documented in the workflow configuration.
Data Flow¶
Input: - Chat messages from users - Phone numbers for user identification - Business performance queries
Processing: - User record lookup from PostgreSQL - Business performance data retrieval - AI analysis and coaching advice generation - Memory management for conversation context
Output: - Coaching advice and micro-actions - BA scripts for call center use - Business insights and recommendations - Chat log entries for tracking
Error Handling¶
The workflow includes escalation protocols for serious situations: - Debt collector harassment - Family conflicts over business money - Youth wanting to close business permanently - Signs of emotional distress - Safety concerns
When escalation triggers are detected, the system returns "⚠️ ESCALATION NEEDED" and provides instructions to connect youth with their Community Education Advisor (CEA).
Known Limitations¶
Based on the system prompts and configuration: - Designed specifically for youth entrepreneurs aged 18-30 in rural Kenya - Requires phone number identification for full functionality - Some nodes are currently disabled, indicating the workflow may be in development - Limited to business coaching scope - redirects off-topic queries
Related Workflows¶
The system integrates with several external workflows: - dailySalesDataCollection (ID: JCO3nAXlEn5vU9Bn) - updateUserDataTool (ID: 7P8o5PMHB3BlpXSB) - updateUserStatusTool (ID: 0KvFdX0T49lalwIw) - getSummary (ID: CP3EYANkFJM9Jzas)
Setup Instructions¶
- Import the workflow into your n8n instance
- Configure credentials:
- Set up OpenRouter API access with Google Gemini model access
- Configure PostgreSQL connection to your database
- Database setup:
- Ensure tables exist:
youthEntrepreneursReal,dailyProfitTracking,chatLog - Set up proper schema for user records and business data
- Ensure tables exist:
- Enable the workflow and activate the chat trigger
- Test the integration with a sample phone number and business query
- Configure related workflows for full functionality
- Set up monitoring for escalation scenarios and system performance
Note: Several nodes are currently disabled in this workflow, suggesting it may require additional configuration or be in a development state.