B1 Learn: The API Paradigm
OpenAIAPI Basics
- Transitioned from ChatGPT UI to OpenAI API usage.
- Learned core parameters: Temperature, Top-P, and Max Tokens.
- Studied 'System Prompting' frameworks to control AI persona.
Sprint Log
A weekly changelog of technical learnings, blockers, and shipping velocity.
B1 Build: Scripting Logic
PythonScripting
- Wrote my first Python script to loop through a CSV of meeting notes.
- Connected script to GPT-3.5-turbo for cost-effective summarization.
- Handled basic API errors (Rate Limits) with try/catch blocks.
B1 Polish: Prompt Optimization
Prompt EngineeringOptimization
- Refined prompts to enforce specific formatting (Bullet points vs Paragraphs).
- Calculated token costs for batch processing.
- Documented the tool for non-technical team members.
B2 Learn: Vector Math
EmbeddingsMath
- Deep dive into Embeddings: How text becomes numbers.
- Learned Cosine Similarity vs. Euclidean Distance.
- Set up a Supabase Vector database.
B2 Build: The Search Engine
SupabaseSQL
- Built an ingestion script to chunk long documents.
- Generated embeddings using `text-embedding-3-small`.
- Wrote a SQL Remote Procedure Call (RPC) to match vectors in Supabase.
B2 Polish: Tuning Retrieval
ETLData Cleaning
- Experimented with different Chunk Sizes (256 vs 512 tokens).
- Added metadata filters (e.g., filter by 'Date' or 'Author').
- Visualized vector clusters using PCA.
B3 Learn: RAG Architectures
LangChainRAG
- Studied the Retrieval Augmented Generation (RAG) pattern.
- Learned LangChain fundamentals: Chains, Retrievers, and Loaders.
- Mapped out the architecture for a Corporate Handbook Chatbot.
B3 Build: The Chat Interface
StreamlitUI
- Built a frontend using Streamlit for rapid prototyping.
- Connected the LangChain backend to the Vector Store.
- Implemented 'Conversation Memory' so the bot remembers context.
B3 Polish: Trust & Citations
UXHallucination
- Solved hallucination issues by forcing the model to cite sources.
- Added a UI component to expand and read the source document.
- Deployed the app to Streamlit Cloud.
B4 Learn: Fine-Tuning Theory
LLMsUnsloth
- Studied LoRA (Low-Rank Adaptation) and QLoRA.
- Learned the difference between 'Pre-training' and 'Instruction Tuning'.
- Prepared the dataset: Formatted CSVs into Alpaca JSONL format.
B4 Build: Training Llama-3
ColabTraining
- Ran the training job on Google Colab T4 GPU.
- Optimized hyperparameters (Learning Rate, Epochs) to prevent overfitting.
- Hit hardware limits and pivoted to Hosted Inference Endpoints.
B4 Polish: The API Wrapper
Node.jsHuggingFace
- Built a Node.js API to wrap the Python inference model.
- Created a 'Golden Set' of tickets to benchmark performance.
- Calculated final ROI: Buy (GPT-4) vs Build (Llama-3).
B5 Learn: Agentic Patterns
AgentsReAct
- Studied the ReAct pattern (Reasoning + Acting).
- Learned strict JSON Schema definitions for Function Calling.
- Designed the 'Triple Threat' architecture (Cluster -> Context -> Story).
B5 Build: The PM Bot
LangChainZod
- Implemented the CLI tool using Node.js and Commander.
- Built the 'Reflexion Loop' for automated quality control.
- Integrated Zod to force INVEST-compliant JSON output.
B5 Polish: Enterprise Features
FinOpsStrategy
- Added '--dry-run' flag for cost estimation (FinOps).
- Implemented RICE Scoring logic within the prompt.
- Refactored the CLI into an Express.js API for scalability.