Using the AI chatbot
GreekManage includes an AI assistant trained on your org's data — schedules, members (within your privacy rules), documents, and more. It answers questions in natural language so you don't have to navigate the UI to find things.
Open the chatbot
Look for the floating chat bubble in the bottom-right corner of any page. Click it to open.
You'll see a clean chat interface with a text input at the bottom. Type a question, press Enter.
The AI chatbot answering a member question.
What it can answer
| You ask | It can answer because… |
|---|---|
| "When is the next chapter meeting?" | It reads your events |
| "How much do I owe in dues?" | It reads your invoices |
| "What's the dress code for formal?" | It reads event descriptions and documents |
| "Who is the treasurer?" | It reads your member roster |
| "Where's the bylaws document?" | It reads your documents library |
| "When does the spring election open?" | It reads scheduled elections |
What it can't answer
- Anything outside your access — you can't ask about another chapter's roster
- Personal data about other members beyond what's in their public profile
- Future events that haven't been created yet
- Real-time external data (weather, current news, etc.)
How responses are generated
The chatbot uses retrieval-augmented generation:
- Your question is embedded and matched against your org's data.
- Relevant snippets are sent to a language model along with your question.
- The model returns an answer, citing sources where possible.
Responses are streamed in real time. You'll see them type out as the model generates.
Cite sources
Each response includes Sources at the bottom — links to the underlying document, event, profile, or invoice. Click to verify.
Privacy and the chatbot
- The chatbot respects your role. A member never gets data they couldn't access through the UI.
- Conversations are logged for quality improvement; org admins can disable logging in Org Settings → AI.
- Chats are not shared across users — your conversation is private.
Provide feedback
Each response has a 👍 / 👎 button. Hit 👎 if the answer is wrong; an optional comment box lets you explain. Org admins see this feedback to improve prompts.
Tips
- Be specific. "What time is the meeting on Tuesday?" beats "When's the meeting?"
- Ask follow-ups. The chatbot keeps context within a conversation.
- Verify financial answers. Don't pay anything based solely on a chatbot response — open the actual invoice.