Software Engineer - ACB Chatbot

*Please note: the service contract for this position will not be concluded with Henkel AG & Co. KGaA but with an external party”.

Projektname /project name

ACB Chatbot

Projektbeschreibung/project description

The service is requested as part of the project ACB Chatbot (ACB = Construction Adhesives Unit of Henkel). The project has the purpose of building and constantly improving (with content and functionalities) a fully functional virtual assistant (chatbot) for the Construction Adhesives customers (craftsmen). The MVP was launched in December 2021, and it was initially deployed on the webiste. Along with content and feature updates, the chatbot will be also deployed within many other channels, such as mobile applications (where applicable), as well as Facebook Messenger, WhatsApp, Viber, Telegram and other messaging applications. 
 

Leistungsbeschreibung/task description

The service of the contractor is delivered using an agile working method. External resources are needed as there is no internal staff with the required expertise in the following areas:

• Development of an ACB custom chatbot solution that will run on the Cognigy platform (Cognigy is an external vendor for chatbots; Henkel’s Laundry and Home Care Unit already owns a license and this chatbot will run on that platform as well)

Therefore, the external contractor is in a unique position and performs significantly different tasks than the internal employees.

One sprint consists of three to four weeks and there is a weekly jour fixe. During these meetings, the team discusses the current requirements and the contractor independently performs the following tasks:
 

• Chatbot Dialog Design within the Cognigy.AI platform
  • Work on content and functionality updates of the chatbot in the Henkel Cognigy.AI platform
  • Creation of a user-friendly, natural conversation flow
  • Design information architecture for the chatbot
  • Training of the chatbot regarding intents and synonyms 
  • Implementation of the bot / specific functionalities as needed
  • Configure multi-language localizations of the bot which are specified in the project plan
    • Scaling up globally in the second half of 2022 if MVP is successful
  • Conception of additional channels; possible channels include Facebook Messenger, WhatsApp Business, Viber, and Telegram 
• Chatbot Data Management Design
  • Define data structures for the chatbot
  • Define technical structures for the bot to use
  • Create human-manageable data structures for data exchange and providing by Henkel Employees 
    • Independently create data files that will allow Henkel brand employees to define the chatbot content
    • Transform these data files for input for the chatbot implementation; the specific formats and processes are determined as part of the project plan.
  • Define and implement data usage in the bot
  • Conception of connecting to other Henkel data sources like PIM, mail services or others if discussed during the sprints
    • The pilot implementation will lead to knowledge about what kind of data sources should be included. Only then will we be able to find Henkel systems that provide this data, and then we will know if we can access that data and how. Listing the systems is not possible at this point in time.
• Platform Management and Training
  • Set up all necessary artifacts in the Cognigy.AI platform
  • Define bot integration for all channels 
  • Train both the brand team and Henkel dx Smartbot Factory Team to use and implement the Cognigy.AI platform
    • The training will include a short session for the brand team (up to 5 participants) to add intents and lexicon entries for enhancing the bot – 2 hours max. 
    • DX training is planned to be part of the implementation.

• Chatbot Analytics and Reporting
  • Extend the existing reporting in Power BI as needed and based on the platform’s Data analytics interface. The details will be part of the sprint work and be defined with the global, regional and local Henkel teams.
  • Connect the Power BI data (and the data available from Gognigy.AI) with the data from the website behaviour (Google Analytics) into one source of truth.
  • Create useful insights from all data sources into one single reporting/dashboard and help the Henkel team to make conclusions regarding the MVP testing period of 6 months, based on these available insights. 

• Technical Project Documentation
  • Preparation of all documentation necessary for the ACB Chatbot Project which is subject to approval by Henkel, namely: 
• The content of the trainings
• Steps for editing and publishing content (with steps of where to click - The most helpful and clear form for our colleagues in TCS to add/edit content)
• Explanation of the structure for intents, flows and utterances
• Code changes - code documentation/explanation 
• Steps to create a snapshot for testing changes before moving them to production
• Steps to upload the bot on the website and additional channels (if deployed within additional channels)
• Analytics – how to add/edit KPIs and how to connect to Power BI; as well as how to connect all data sources (Cognigy.AI, PowerBI and Google Analytics) 

• Chatbot Dialog Implementation within the Cognigy.AI platform
  • Training of the chatbot regarding intents and synonyms 
  • Implementation of a user-friendly, natural conversation flow according to Henkel best case scenarios provided to the contractor in advance
  • Implementation for multi-language localizations of the bot
    • Scaling up globally in the second half of 2022 if MVP is successful
  • Additional channels discussed include Facebook Messenger, WhatsApp Business, Viber, and Telegram 
  • Independently create and manage test and integration environments

• Chatbot Data Management
  • Implement data storage and services for the chatbot
  • Transformation of Henkel data formats to chatbot data sources
  • Define and implement data usage in the bot

• Platform Management 
  • Manage Cognigy.AI platform in terms of users and projects: 
    • User management
    • Cognigy Agent administration
    • Create technical users and API keys for programmatic access and reporting 
    • Create and update chatbot endpoints for inclusion on web pages and Facebook Messenger

• Additional Project Tasks
  • Communications with external Cognigy.AI technical support and architect to add platform features necessary for Henkel
  • Implementation of new content updates, as agreed on in the sprint meetings
  • Development and implementation of new features as needed and agreed on in the sprint meetings (nearby store locator, calculators and other features and functionalities as necessary and decided with the local teams) 
  • Communication with external localization/translation agency if/when the Ceresit Bot is ready for a global rollout 

The service provision of the contractor has the goal of creating and constantly improving a consumer helping chatbot that fulfils the given use cases and enabling Henkel brand team and Henkel dx to understand the platform, maintain parts of the chatbot themselves and be knowledgeable about what additional features should be added to the chatbot. 

Timelines

The following timelines are to be adhered to by the contractor during the provision of the service:

The MVP of the Ceresit chatbot was launched in December 2021. The MVP will be tested for approximately 6 months (testing period might be extended if needed), during which more functionalities and features will be developed as needed and the content will be constantly updated. If the MVP is successful, localisations to other counties are planned from the second half of 2022.