Winners - Challenge #1

Build a RAG Based Assistant to Deliver Role-Specific Insights Across Departments in a Fintech Company
Difficulty: 2/5
Domain: FinTech Function: AI Engineering
FinSolve Technologies, is a leading FinTech company providing innovative financial solutions and services to individuals, businesses, and enterprises.
Recently, teams have been facing delays in communication and difficulty accessing the right data at the right time, which has led to inefficiencies. These delays and data silos between different departments like Finance, Marketing, HR, and C-Level Executives have created roadblocks in decision-making, strategic planning, and project execution.
To address these challenges, Tony Sharma, the company’s Chief Innovation Officer, has launched a new project focusing on digital transformation through AI. He has reached out to Peter Pandey, an AI Engineer, who is ready to apply his recent learnings.
Tony proposed developing a role-based access control (RBAC) chatbot to reduce communication delays, address data access barriers, and offer secure, department-specific insights on demand. The aim is to design a chatbot that enables different teams to access role-specific data while maintaining secure access for Finance, Marketing, HR, C-Level Executives, and Employees.
Task:
Imagine yourself as Peter Pandey and develop a RAG-based role-based access control system for the chatbot, ensuring each user receives the correct data based on their role. The chatbot should process queries, retrieve data, and generate context-rich responses.
Roles and Permissions:
- Finance Team: Access to financial reports, marketing expenses, equipment costs, reimbursements, etc.
- Marketing Team: Access to campaign performance data, customer feedback, and sales metrics.
- HR Team: Access employee data, attendance records, payroll, and performance reviews.
- Engineering Department: Access to technical architecture, development processes, and operational guidelines.
- C-Level Executives: Full access to all company data.
- Employee Level: Access only to general company information such as policies, events, and FAQs.
Key Requirements:
- Authentication and Role Assignment: The chatbot should authenticate users and assign them their roles.
- Data Handling: Respond to queries based on the corresponding department data (Finance, Marketing, HR, General), also providing reference to the source document.
- NLP: Process and understand natural language queries.
- Role-Based Access Control: Ensure role-based data access.
- RAG: Retrieve data, augment it with context, and generate a clear, insightful response.
Tech Stack:
- Python: Core programming language
- FastAPI: Backend framework for the server
- GPT-3/4, Llama or any LLM: Response generation
- Vector Store (Qdrant, Chroma, Pinecone or any other): Document search and retrieval
- Streamlit: Chatbot UI
Note: You're free to use any additional tools or technologies that enhance your solution.
Resources Provided:
- Data
- Metadata
- Starter GitHub Repo (Fork this repository to start your project!)
Note:
- We recommend you create a video presentation of 15 minutes or less for the business stakeholders. Additionally, make a LinkedIn post that includes relevant links, your video presentation, and a reflection on your experience while working on this challenge.
- You can check out sample presentations to gain some inspiration: Sample Presentation
- Please see the detailed evaluation criteria, which are provided in the document “evaluation criteria”.
- Submit your post link on the resume project challenge page of Codebasics. If the post link is not submitted before the deadline, we won't be able to consider it.
All the best from Team Codebasics! 🫡
Feel free to reach out at Discord server for any support: Discord Link
Download Problem Files
Download Files HereCurrent Challenge
Difficulty : 2/5 Active
CureviaAI is a forward-thinking health-tech innovation company dedicated to transforming healthcare.With a strong focus on real-world problems in drug safety, patient care, and clinical decision support, CureviaAI combines AI, machine learning, natural language processing, and biomedical research to deliver actionable insights.
Since the COVID-19 pandemic outbreak in early 2020, the world has seen an unprecedented scale of mass vaccinations. With this, reports of Adverse Drug Events (ADEs) — ranging from mild reactions to severe, life-threatening complications — have risen significantly.
These reactions are captured in large-scale, real-world surveillance systems like the Vaccine Adverse Event Reporting System (VAERS), maintained by the CDC and FDA.  The VAERS data, particularly from 2020 to 2025, offers a treasure trove of information - including structured symptom codes and free-text symptom notes.
However, these structured entries are limited and miss context like duration, intensity, or location. The free-text notes, while rich, are noisy and lack standardized severity or age-specific patterns - making it difficult for regulators, healthcare providers, and pharma companies to make informed, timely decisions.  
To bridge this gap, Tony Sharma, the visionary Chief Innovation Officer at CureviaAI, has launched a high-priority AI project, entrusting its execution to the expertise of Peter Pandey, AI Engineer at CureviaAI.
Download Problem Files
Download Files HerePast Challenges
How to Get Started
View RulesWhat will you get?
- A real-world AI & Data Science project to showcase on your resume.
- Hands-on experience applying AI/ML techniques to real business problems and datasets.
- Exclusive Codebasics swag for the top 3 submissions.
- An appreciation certificate for every qualified submission.