The main goal of the project is to explore and implement prompt engineering techniques to enhance Ada Analytics' AI-enabled derivatives trading platform. By leveraging prompt engineering, the project aims to enable interactive user interventions and adaptive learning within the platform, allowing traders to receive tailored and context-specific derivatives trading strategies and automated trade position adjustments. The ultimate objective is to revolutionize the derivatives market and provide traders with sophisticated and adaptable solutions to optimize their trading performance.

1. Familiarize with Prompt Engineering: Learners will need to understand the concept of prompt engineering, its applications in language models, and how it enables user-driven interventions and adaptive learning.
2. Study AI in Financial Trading: Learners should gain insights into the applications of AI and machine learning in the financial industry, with a focus on derivatives trading strategies and risk management.
3. Review Ada Analytics' Platform: Learners will explore the existing AI-enabled derivatives trading platform of Ada Analytics to understand its functionalities, data integration capabilities, and AI models.
4. Identify Potential Prompt Techniques: Learners will research and identify various prompt engineering techniques applicable to derivatives trading, such as single-prompt interventions, multiple-prompt interventions, and prompting to disclose uncertainty.
5. Design Prompt-Driven Features: Working with the Ada Analytics team, learners will design prompt-driven features for the platform, such as generating AI-driven trading strategies and providing dynamic trade position adjustments based on user prompts.
6. Implement Prompt Engineering: Learners will implement the selected prompt engineering techniques into Ada Analytics' platform using appropriate programming languages and tools.
7. Test and Validate: Learners will conduct rigorous testing and validation of the prompt-driven features to ensure their effectiveness and accuracy in generating trading strategies and trade position adjustments.
8. Explore Automatic Prompt Generation: Learners will research and experiment with automatic prompt generation techniques, such as retrieval-augmented generation, to enrich the range of prompt options available to users.
9. Optimize Prompt Tuning: Learners will explore gradient descent-based prompt tuning to optimize prompt embeddings and maximize the log-probabilities on outputs for improved performance.
10. Collaborate with Ada Analytics: Learners will work closely with the Ada Analytics team to integrate prompt engineering seamlessly into the platform, addressing any challenges and refining the features based on feedback.
11. Documentation and Reporting: Learners will document their research, implementation, and testing processes, creating clear and comprehensive reports to communicate the project's findings and outcomes effectively.
12. Presentation and Demo: Learners will present their project outcomes and demonstrate the prompt-driven features to the Ada Analytics team and other stakeholders.

By completing these tasks, the learners will achieve the main goal of the project: to successfully integrate prompt engineering into Ada Analytics' derivatives trading platform, providing traders with innovative and adaptive solutions to optimize their trading strategies and positions.

At Ada Analytics, we are committed to providing comprehensive support to the learners undertaking the prompt engineering project. Our support system is designed to ensure that the learners have the necessary resources, guidance, and assistance to complete the project successfully. Here's how we will support them:

1. Collaboration Platform: We will set up a collaborative platform, such as WhatsApp or Element/Matrix, where learners can communicate with mentors and other team members, share ideas, and seek feedback.
2. Regular Meetings: Scheduled meetings with mentors and the project team will provide an opportunity to discuss progress, address challenges, and strategize for the next steps.
3. Peer Collaboration: Learners will have the chance to collaborate with other teams or students working on similar projects, fostering a supportive and collaborative learning environment.

By offering this comprehensive support system, we aim to empower the learners to excel in the prompt engineering project and gain valuable skills and experiences that will benefit them in their academic and professional journeys.