Skip to content

An extensible LLM-powered customer support chatbot with a no-friction AI-to-Human handoff. Won 1st Place Overall in the Beginner Track at the 2023 AI ATL Hackathon.

Notifications You must be signed in to change notification settings

Support-Flow/.github

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 

Repository files navigation

Support Flow

An extensible LLM-powered customer support chatbot with a no-friction AI-to-Human handoff.

Won 1st Place Overall Beginner Track in the 2023 AI ATL Hackathon

Team Members: Saketh Reddy, Colin Fluek, Cullen Steber, Anisha Ali

Devpost: https://devpost.com/software/supportflow

Project Components:

  • supportflow-chatbot: Streamlit chatbot application. Leverages OpenAI's function calling to: determine it's capabilities, intelligently prompt customers for necescary information, and transfer the conversation to a human representative when it is given a task it knows it cannot fulfil.

  • supportflow-agent: React application that monitors our Firestore database for updates and sends agents to an agent dashboard when a new chatbot escalation is created. Agent dashboard includes customer information, the full chat history, the customer pain point the chatbot was unable to resolve, and instructions on what the agent needs to do in order to resolve the customers' issues.

  • supportflow-agent-ui: Flask application for rendering static templated agent dashboards based off of URL parameters.

About

An extensible LLM-powered customer support chatbot with a no-friction AI-to-Human handoff. Won 1st Place Overall in the Beginner Track at the 2023 AI ATL Hackathon.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published