Become an AI Engineer | Cohort-Based Course

Here’s what makes this cohort special:

• Learn by doing: Build real world AI applications, not just by watching videos.

• Structured, systematic learning path: Follow a carefully designed curriculum that takes you step by step, from fundamentals to advanced topics.

• Live feedback and mentorship: Get direct feedback from instructors and peers.

• Community driven: Learning alone is hard. Learning with a community is easy!

We are focused on skill building, not just theory or passive learning. Our goal is for every participant to walk away with a strong foundation for building AI systems.

If you want to start learning AI from scratch, this is the perfect time to begin.Become an AI Engineer | Cohort-Based Course

WEEK 2        

Prompt engineering is the process of structuring, refining, and optimizing natural language instructions (prompts) to effectively guide generative AI models, like large language models, toward generating desired and accurate outputs. It involves using specific phrasing, relevant context, examples, and other techniques to influence the AI's behavior and ensure the generated content meets specific requirements and goals. 

Why Prompt Engineering is Important

·  Improves Output Quality: It directly influences the relevance, accuracy, and overall quality of the AI's responses. 

· Ensures Alignment: It helps align AI-generated content with the specific goals and criteria of the user. 

· Increases Efficiency: Well-engineered prompts lead to more satisfying and efficient interactions with AI systems. 

· Unlocks Potential: It's essential for harnessing the full capabilities of generative AI and tailoring models for diverse applications. 

Key Aspects of Prompt Engineering

· Crafting Instructions: This involves selecting the right words, phrases, and grammar to clearly convey the task to the AI. 

· Providing Context: Including relevant background information or constraints helps the AI understand the user's intent. 

· Specifying Output: Prompts can detail the desired style, format, or even a character for the AI to mimic. 

·  Iteration and Testing: Because AI outputs can be non-deterministic, prompt engineering often involves a process of testing and refining prompts to achieve consistent results. 

· Art and Science: It combines the art of creative communication with the science of structured experimentation and optimization. 

How it Works

Imagine you want an AI to write a story. 

· Basic Prompt: "Write a story about a cat."

· Engineered Prompt: "Write a short, humorous story about a mischievous black cat named Shadow, who lives in a magical city and tries to steal a glowing fish from a grumpy wizard's shop. Include a scene where he uses his agility to avoid magical traps."

By adding details like a character name, a setting, and a specific plot point, the prompt guides the AI to produce a much more specific and desirable output than a vague request. 

Project 2        

Build a Customer Support Chatbot using RAGs and Prompt Engineering

Overview of Adaptation Techniques Finetuning

• Parameter-efficient fine-tuning (PEFT)
• Adapters and LoRA

Prompt Engineering

• Few-shot and zero-shot prompting
• Chain-of-thought prompting
• Role-specific and user-context prompting

RAGs Overview Retrieval

• Document parsing (rule-based, AI-based) and chunking strategies
• Indexing (keyword, full-text, knowledge-based, vector-based, embedding models)

Generation

• Search methods (exact and approximate nearest neighbor)
• Prompt engineering for RAGs

RAFT: Training technique for RAGsEvaluation (context relevance, faithfulness, answer correctness)RAGs' Overall Design