saurabhkaushik/botreload-agent-assist

Botreload Agent Assist

Answer Bot for Customer Service (Zendesk Marketplace)

About The Project

BotReload Agent Assist is a Smart Reply Bot for Customer Support system which automatically identifies intent and entitites of incoming customer query and generates a reply using AI Tech (NLP / ML). This bot was launched on Zendesk in 2017, serving multiple clients with thousends of query per day.

Key Features:

• Suggest most Relevant Reply - Suggest quick and most relevant reply to customer query. Its algorithm is design based on Research paper published by Google.
• Cold Start Capability - Engine is trained on large enterprise helpdesk data to start serving without even any custom training.
• Continuously Serve and Learn - Its AI Engine learns from everything from past as well as present in near-realtime. It can even serve without any training (Cold start).
• Automatic ticket tagging - Agent Assist understands the content of each ticket and categorize it accordingly using both existing tags as well as newly discovered ones.
• Generates Performance Analytical Dashboard by business unit

Key Technical Capability:

• Automatically curates and learns Intents of queries for each business unit seprately
• Automatically curates and generates Smart Replies for each business unit separately

More internal details are at medium article. Developing Answer Bot for Customer Service

Built With

• Python 3.7
• Scikit-learn
• NLTK
• Spacy
• Flask
• Node JS
• Google Cloud App Engine
• Google Cloud Datastore
• Bootstrap
• JQuery

Getting Started

This project has two parts - Client and Server.

• Client is Zendesk App (deployed in Zendesk Marketplace) which reads customer queries and suggests Smart Reply with confidence level.
• Server is Smart Reply AI Engine (deployed on Google Cloud Platform - App Engine) which serves response to incoming queries from Client

Roadmap

• Intent Classification using LSTM and CNN combination
• Response generation using Transfer Learning and GAN

Contributing

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Saurabh Kaushik @Twitter - @saurabhkaushik

Saurabh Kaushik @LinkedIn - @saurabhkaushik