A visual guide to the key roles and activities involved in building production-grade AI agents from concept to deployment.
An initial, small-scale project to test the core idea and technical feasibility of the AI agent.
Rapid Prototyping, Python, LangChain, LLM APIs, Streamlit
Analyzing available data sources to understand their quality, structure, biases, and potential value.
Data Analysis, Statistics, Pandas, NumPy, Matplotlib, SQL
The art and science of designing effective inputs (prompts) to guide an LLM to produce the desired output.
LLM Behavior, Creative Writing, Logical Reasoning, JSON
Building the core ML models that power the agent, or pre-training domain-specific models.
Adapting a pre-trained model to a specific domain using a smaller, high-quality dataset.
Generating, storing, and retrieving vector embeddings for Retrieval-Augmented Generation (RAG).
Measuring an agent's performance using robust datasets and metrics to benchmark changes.