48 Hour Competition AI for Cultural Change
Leverage existing platform capabilities and Agentic AI to create experiences that empower our customers to transform their organizational culture. By moving the needle on culture, we not only increase adoption and unlock the value of our platform but also reinforce our commitment to helping customers become a "Great Places to Work"
Updated Feb 2024
Scoring
2 Points: Submit 1 MongoDB Challenge Form per team
1 Points: Submit Skill Scanner Codes: SW Dev: skillscanner-softwaredeveloper
1 Point: Use MongoDB Atlas as a data store for your solution
2 Points: Build an AI powered experience using Atlas Vector Search
1 Point: Integrate Full Text Search for fuzzy matching, autocomplete, or faceting for a google like search experience
2 Points: Include real-time analytics and data visualization using Atlas Charts
1 Point: Use Time Series Collections for storing sequences of measurements over a period of time
Bonus Points:
1 -2 Points: Creative approach
1 Point: Attend one of our Spark [tech] Sessions
The personal data of UKG users participating in this hackathon will be handled by MongoDB in accordance with our Privacy Policy.
Have Questions? Ask MongoDB AI or
Join MongoDB Office Hours with MongoDB Experts!
IN PERSON SUPPORT
Lowell Office: TBD
IN PERSON SUPPORT
Weston Office: TBD
Prizes 🥇
TBD: SWAG & Trophies
General Coding Challenge Ideas
Use MongoDB Atlas as the data store for your solution
MongoDB is a general purpose, document-based, distributed database built for application developers. It provides an integrated suite of products and services, including Atlas Search, that developers can use to build applications faster than ever before.
Example: Data Platform for microservices and Flexible Data Model
Build an AI powered experience using Atlas Vector Search - More info
Atlas Vector Search lets you search unstructured data. You can create vector embeddings with machine learning models like OpenAI and Hugging Face, and store and index them in Atlas for retrieval augmented generation (RAG), semantic search, recommendation engines, dynamic personalization, and other use cases.
Example: Semantic Search, AI Chatbot, AI Recommendation Engine
Provide relevance based app features using Atlas Search - More info
Atlas Text Search allows for fine-grained text indexing and querying of data on your Atlas cluster. It enables advanced search functionality for your applications without any additional management or separate search system alongside your database. Some use cases for Atlas Text Search include enabling users to quickly find what they are looking for on a website, promoting certain products on an e-commerce site, and providing fast, relevant search results for any application.
Example: Advanced Search
Include real-time analytics and data visualization using Atlas Charts - More info
MongoDB provides real-time analytics and data visualization capabilities through its built-in data visualization tool, Atlas Charts. With Atlas Charts, developers can easily create, share, and embed rich dashboards built from their own data in the cloud. Charts provides a wide variety of chart types to visualize data, including bar charts, scatter plots, geospatial charts, and more. Additionally, Charts provides built-in aggregation functionality, allowing developers to process collection data by a variety of metrics and perform calculations such as mean and standard deviation to provide further insight into their data.
Example: Dashboard, Embedded Charts
Use Time Series Collections for storing sequences of measurements over a period of time - More Info
MongoDB Time Series Collections are optimized for the demands of analytical and IoT applications by offering reliable data ingestion, a columnar storage format, and fast query processing. This cost-effective solution is designed to meet the most demanding requirements for performance and scale.
Example: Event analytics
Why MongoDB for this theme?
Flexible Schema Design: MongoDB's document-based model allows for flexible and dynamic schema design, which is particularly beneficial for handling customer feedback and insights. This flexibility enables you to:
Store diverse types of feedback (e.g., ratings, comments, survey responses) in a single collection without predefined structure constraints
Easily add new fields or modify existing ones as your feedback collection methods evolve, without needing to alter the entire database schema
Accommodate varying levels of detail in customer responses without wasting space on null values
Sentiment Analysis
Store sentiment scores alongside the original feedback text in the same document.
Include multiple sentiment dimensions (e.g., positive, negative, neutral) as separate fields.
Social Media Information:
Capture platform-specific data (e.g., likes, shares, retweets) in nested documents.
Store user profiles, post content, and engagement metrics in a single document.
Use arrays to store lists of comments or reactions associated with a post.
Integrated Analysis
Store sentiment analysis results, social media metrics, geolocation, and timestamp in a single document.
Use MongoDB's aggregation framework to perform complex analyses across multiple data types.
Create compound indexes to optimize queries that combine time-based, geospatial, and other criteria.
Efficient Querying and Analysis: MongoDB offers powerful querying capabilities that can significantly enhance your ability to analyze customer feedback:
Ad-hoc queries allow for real-time analytics and flexible exploration of your data
The aggregation framework enables complex data transformations and analysis directly within the database
Indexing support for various field types improves query performance, allowing for fast retrieval of specific feedback or insights
Rich Text Search and Analytics: Customer feedback often contains valuable textual data. MongoDB's features support advanced text analysis:
Full-text search capabilities allow you to quickly find relevant feedback based on specific keywords or phrases.
Support for regular expressions enables pattern matching within text fields, useful for identifying trends or specific types of feedback1.
Data Visualization and Reporting
MongoDB Charts allows you to create visualizations directly from your data without needing to move it to another system.
Integration with popular business intelligence tools enables advanced reporting and dashboard creation.
Inspiration
Customer reviews are everywhere — on social media, review sites, and even directly on business websites. These reviews offer a wealth of opinions, but they're often buried in paragraphs of text or hidden within videos and photos. We wanted to make sense of the reviews’ sentiments and use the multimodal nature of data to our advantage while helping customers talk to our agent (chat assistant) to make decisions based on the summary of feedback.
Real-time Customer Feedback Dashboard
Use MongoDB's real-time data processing capabilities to create a live dashboard that aggregates and analyzes customer feedback from multiple sources (surveys, social media, support tickets, etc.).
Implement MongoDB Atlas Vector Search to categorize and cluster feedback based on topics and sentiment.
AI-Powered Customer Insight Generator
Leverage MongoDB's AI capabilities to process unstructured customer feedback data and generate actionable insights.
Use MongoDB's flexible schema to store diverse types of customer data and feedback.
Predictive Customer Needs Analyzer
Utilize MongoDB's time series collections to track customer behavior and feedback over time.
Implement machine learning models to predict future customer needs based on historical data.
Voice of Customer-Driven Product Roadmap Tool
Create a tool that links customer feedback directly to product features and enhancements.
Use MongoDB's document model to store and relate customer feedback to specific product areas.
Sentiment-Based Customer Journey Mapper
Build a tool that maps the customer journey and overlays sentiment analysis at each touchpoint.
Leverage MongoDB's geospatial capabilities for location-based customer experience insights.
Voice of Customer Chatbot for Internal Teams
Create an AI-powered chatbot that internal teams can query to get instant insights on customer feedback and trends.
Use MongoDB Atlas Vector Search for efficient similarity searches in large datasets of customer feedback.
Customer Feedback Prioritization Engine
Develop a system that automatically prioritizes customer feedback based on impact, frequency, and strategic alignment.
Utilize MongoDB's aggregation framework for complex data analysis and scoring.
Cross-Functional Collaboration Platform for Customer-Centric Decisions
Build a platform that facilitates collaboration between different departments (product, marketing, support) based on customer feedback.
Use MongoDB's real-time capabilities to ensure all teams have access to the latest customer insights.
Voice of Customer-Driven Innovation Hub
Create a platform where employees can submit and vote on ideas inspired by customer feedback.
Implement MongoDB's search capabilities to help employees find relevant customer insights for their ideas.
Technical Resources
General
RAG
AI Agents
Additional resources
Building an Advanced RAG System With Self-Querying Retrieval
How to Improve LLM Applications With Parent Document Retrieval Using MongoDB and LangChain
