The library
Nine maps.
No theater.
Education for people who will implement — not a tour of possibility. Front-end through data science. The same standard as the practice: judgment, then tools, then the staff who keep it.
01
Pick a track
Start with the work in front of you. The map is the syllabus — not a course to finish.
02
Read the map
Each page lists concepts, tools, and failure modes in order of importance.
03
Ask a model the right questions
Copy the vocabulary. Ask it to explain what you do not recognize — against your own stack.
04
Build something
The only proof is a thing that breaks and gets fixed by the people who will run it.
The tracks
Start where the work is.
Front-end
Front-end
HTML, CSS, JavaScript, TypeScript, React, Next.js, performance, accessibility. The layer users actually touch.
Back-end
Back-end
APIs, databases, authentication, caching, queues, security, scaling. The engine room.
Infra
Infra
AWS, Docker, Kubernetes, CI/CD, observability, networking, secrets. The foundation everything sits on.
Prefect orchestration
Prefect orchestration
Flows, tasks, deployments, work pools, Airflow migration, and AWS/Snowflake/Pulumi medallion examples.
AI engineering
AI engineering
Foundation models, prompts, evals, RAG, agents, finetuning, inference, and production system design.
Agents
Agents
LCEL, agents, tools, memory, RAG, streaming, evaluation, deployment. The framework layer for LLM apps.
Design
Design
Typography, color, layout, components, UX patterns, accessibility, design tokens. Making it usable.
Data engineering
Data engineering
ETL, warehouses, pipelines, modeling, orchestration, data quality. Turning raw data into decisions.
Data science
Data science
Statistics, ML, experimentation, feature engineering, model deployment. From correlation to causation.
Apply the map
Need this knowledge inside a working system?
clt_AIGuy helps Charlotte-area teams turn source knowledge, engineering choices, evaluation, and operator training into an implemented workflow.
Discuss an implementation