Scribd
Upload
40 views

Generative AI Engineer Assignment

Uploaded by

aryan.10119011621
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
40 views

Generative AI Engineer Assignment

Uploaded by

aryan.10119011621
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Market Research & Use Case Generation Agent

Your goal is to design a Multi-Agent architecture system that generates relevant AI and
Generative AI (GenAI) use cases for a given Company or Industry. The system will conduct
market research, understand the industry and product, and provide resource assets for AI/ML
solutions, focusing on enhancing operations and customer experiences.

The Multi-agent architecture must have the following agents:

● Research the Industry or the Company


○ Use a Web browser tool and understand the industry and segment the company is
working in (e.g., Automotive, Manufacturing, Finance, Retail, Healthcare, etc.).
○ Identify the company’s key offerings and strategic focus areas (e.g., operations,
supply chain, customer experience, etc.). A vision and product information on the
industry should be fine as well.

● Market Standards & Use Case Generation


○ Based on the industry conducted, analyze industry trends and standards within the
company’s sector related to AI, ML, and automation.
○ Propose relevant use cases where the company can leverage GenAI, LLMs, and
ML technologies to improve their processes, enhance customer satisfaction, and
boost operational efficiency.

● Resource Asset Collection


○ Collect the above use cases generated and search for relevant datasets on
platforms like Kaggle, HuggingFace, and GitHub.
○ Save the resource links fetched in a text or markdown file.
○ [OPTIONAL: BONUS] If applicable, propose GenAI solutions like document
search, automated report generation, and AI-powered chat systems for internal or
customer-facing purposes.

Final Proposal

● List down the top use cases that can be delivered to the customer, ensuring they are
relevant to the company’s goals and operational needs.
○ Ensure to add references through which certain use cases were suggested
○ Resource Asset links should be clickable.
Additional Resources:

● You may recommend the agents to refer to reports and insights on AI and digital
transformation from industry-specific sources such as McKinsey, Deloitte, or Nexocode.
● Search for industry-specific use cases (e.g., “how is the retail industry leveraging AI and
ML” or “AI applications in automotive manufacturing”).

Deliverables
● Source code: Submit the source code of your Multi-Agentic workflow, along with any
necessary scripts, configuration files, and documentation.
● Report: Write a report that explains your methodology, results, and conclusions. Include
anything that helps illustrate your findings. Architecture flowchart of your
implementation is MUST.
● Demo Video: A video showcasing the architecture flowchart and the output generated.
Bonus: Deploy the application on Streamlit or Gradio or any other relevant tools.

Assignment Evaluation Criteria:

● Your agent will be evaluated based on the following parameters:


○ Depth of market research and competitor analysis.
○ Relevance and creativity of use cases generated for the customer.
○ Feasibility and practicality of implementing the proposed solutions.
○ Quality and clarity of the final proposal, including actionable insights.

Suggested Tools & Frameworks

● Agent Frameworks: Use OpenAGI, BeyondLLM, LangChain, LLamaIndex, Autogen, or


CrewAI for building AI agents. You can check DeepLearning AI short courses for quick
tutorials or RAG & Agents Bootcamp.
● Search & Retrieval:
○ Leverage Tavily or Exa or Serper for advanced web search
● Dataset Sources: Find relevant datasets on Kaggle, HuggingFace, or GitHub etc.

Feel free to use any other tools you're comfortable with.

Learning Resources
● Deep learning Short sources:
○ https://www.deeplearning.ai/short-courses/multi-ai-agent-systems-with-crewai/
○ https://www.deeplearning.ai/short-courses/ai-agents-in-langgraph/
● RAG Agents Bootcamp: https://aiplanet.com/courses/rag-agents-bootcamp
● AutoGen Documentation detailed docs:
https://microsoft.github.io/autogen/docs/Getting-Started/
Sample Output Reports:
● Market research (only selected links are added); the competitors' list and their annual
reports could be fetched (even here, we added selected links); this allows one to tell what
industry leaders are doing wrt AI adoption
● Use Case Proposal
● Feasibility check for datasets and building use cases

You might also like