Dashboard
Track onboarding, course, location, and mentor response trends
Filters
📢
0
Tracked Mentees
👥
0%
1st Location Rate
✉️
0%
Course Completion
⏰
-
Avg Biz Response
OT
-
Avg Overtime Response
Trend Snapshot
| Window | New Mentees | Start OB | Finish OB | Start Course | Finish Course | 1st | 2nd | 3+ | Success | Biz Response | OT Response |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Loading analytics... | |||||||||||
Mentor Response Times
| Mentor | Mentees | 1st Location Rate | Replies | Avg Biz Response | Avg OT Response |
|---|---|---|---|---|---|
| Loading mentor analytics... | |||||
Response-time logic:
Biz hours are 9:00 AM to 10:00 PM Eastern.
Messages first sent between 10:00 PM and 9:00 AM Eastern are tracked under overtime.
The first mentor reply after a mentee message is what counts toward the average.
Biz hours are 9:00 AM to 10:00 PM Eastern.
Messages first sent between 10:00 PM and 9:00 AM Eastern are tracked under overtime.
The first mentor reply after a mentee message is what counts toward the average.
Quick Broadcast
Groups
All groups and channels the bot is in
Connected Groups
| Group Name | Type | Members | Tracked | Joined | Actions |
|---|---|---|---|---|---|
Broadcast Message
Send messages to all groups or schedule for later
Compose Message
Scheduled Messages
View and manage your scheduled broadcasts
Pending Messages
| Message | Scheduled For | Status | Actions |
|---|---|---|---|
Custom Commands
Configure bot commands and responses
Commands
| Command | Response | Type | Status | Actions |
|---|---|---|---|---|
Webhooks
Send events to external services like Go High Level
Configured Webhooks
| Name | URL | Event | Status | Actions |
|---|---|---|---|---|
Recent Webhook Logs
| Webhook | Event | Status | Sent At |
|---|---|---|---|
| No webhook logs yet | |||
Message Logs
History of all sent broadcasts
Recent Activity
| Message | Type | Delivered | Failed | Sent At |
|---|---|---|---|---|
Mentees
Review each mentee's timeline, mentor, and current location count
Filters
Mentee Groups
| Mentee | Mentor | Location | Status | Timeline | Setup Date | Actions | |
|---|---|---|---|---|---|---|---|
| No mentees yet. Use /setup in a group to onboard. | |||||||
📡 GHL Inbound Webhook:
Use this URL in GHL workflows to push data back to GeekBot.
Loading...
Use this URL in GHL workflows to push data back to GeekBot.
Admin Whitelist
Users automatically promoted to admin in mentee groups
Whitelisted Users
| Telegram User ID | Username | Name | Role | GHL User ID | Actions |
|---|---|---|---|---|---|
| No users in whitelist | |||||
💡 How to find a Telegram User ID:
1. Have the user message the bot privately, or
2. Forward their message to
1. Have the user message the bot privately, or
2. Forward their message to
@userinfobot on Telegram
Welcome Templates
Messages sent automatically during /setup onboarding
Setup Templates
| Name | Message Preview | Format | Order | Active | Actions |
|---|---|---|---|---|---|
| No templates yet | |||||
📝 Template Variables:
{email} — Customer email
{invite_link} — Generated invite link
{group_title} — Telegram group title
AI Settings
Configure LLM responses, provider, and business hours
Global LLM Configuration
💡 How it works:
• @Mention Only: Bot responds when someone says @GeekBot in a group
• Always: Bot also auto-responds to all messages outside business hours
• Off: LLM is disabled, no AI responses
• @Mention Only: Bot responds when someone says @GeekBot in a group
• Always: Bot also auto-responds to all messages outside business hours
• Off: LLM is disabled, no AI responses
Knowledge Base
Upload documents to power RAG-enhanced AI responses
Upload Document
Documents
| Name | Size | Chunks | Status | Uploaded | Actions |
|---|---|---|---|---|---|
| No documents uploaded yet | |||||
📚 How RAG works:
Uploaded documents are split into chunks and embedded. When someone asks the bot a question, relevant chunks are retrieved and injected into the LLM's context to give accurate, knowledge-based answers.
Uploaded documents are split into chunks and embedded. When someone asks the bot a question, relevant chunks are retrieved and injected into the LLM's context to give accurate, knowledge-based answers.