ApproachAbout UsBlogPortfolioFAQContact us
portfolioBack to Portfolio

H2L Chatbot

Goal

The project is designed to get the degree of damage to the window in the user`s car and send the link with the total cost for repair.

The main concept was to use the sms for the user's dialog with a chatbot, control and analyze the dialogs, and monitor all the errors.

H2L Chatbot

Solution

We selected the Dialogflow platform to create the chatbot because it's easy to design and integrate. For sending SMS, we chose Twilio. Twilio provides webhooks, which were used to get answers from users.

As the bridge between Dialogflow and Twilio, we decided to use the PHP framework Laravel. In order to communicate with Dialogflow and Twilio from Laravel, we used open-source SDKs. PostgreSQL was chosen as a database to store users' data. The functionality was expanded with the Javascript framework Vue.Js to build the front end for easy and convenient chatbot testing.

The REST API was implemented to give the ability for the client to start the dialog with users and get the result of the dialog; as well we used Swagger to generate API documentation. Amazon S3 is used as storage for the images from users' MMS. Amazon SQS used for incoming messages to reduce the server load. We used dashbot.io to track detailed statistics of the dialogs and analyze them for further bot flow optimization.

We also decided to implement the Small Talk to engage end-users in conversation. It instigates them to build interactions with the bot and improves the recall rates.

For application monitoring and errors tracking we chose Sentry. It helped us to diagnose, fix, and optimize the performance of the code.


Technologies

AWS S3, AWS SQS, Dashbot.io, Dialogflow, Laravel, PostgreSQL, Swagger, Twilio, Vue.js


Team

- Two backend developers - development of the application functionality
- QA tester - testing of the application

Duration

The development of this project took us 3 months