Building with AI
How to structure an AI project, navigate the tools landscape (RAG, agents, vector databases, APIs), write basic code, and evaluate outputs against cost and latency.
Everyone talks about building with AI. Most people are still stuck admiring the demo. This block moves you from spectator to builder, and it does it without pretending you need a computer science degree to have an opinion that matters in the room.
You start where every serious project should start, before a single line of code. Framing the problem. Deciding whether you need a prompt, a RAG setup, a fine-tune, or an agent. Setting scope, data, and success criteria so you know what winning looks like. This is the discipline that separates real initiatives from expensive science experiments.
Then you go into the machinery. You map the tools landscape, from APIs to no-code platforms to vector databases. You learn how retrieval-augmented generation puts your own data behind the model, so it stops guessing and starts answering. You see how agents take actions instead of just producing text, and where that power gets dangerous if nobody scoped it properly.
Finally, you get your hands dirty. Your first API call in Python, so you understand what your teams actually do. Real evaluation, because a system that feels smart and a system that works are two different things. And the tradeoffs that decide budgets, cost, latency, and model selection, the choices that quietly make or break your unit economics.
By the end you can sit across from any technical team and hold the conversation as a peer. You will know what is easy, what is hard, what is a red flag, and what is a excuse. That is leverage. Leaders who understand how AI gets built stop being sold to and start directing the work.
What you'll master
- Frame an AI problem before anyone touches a keyboard
- Choose between prompting, RAG, fine-tuning, and agents with confidence
- Scope a project with clear data needs and success criteria
- Design a RAG system that puts your own data behind the model
- Evaluate outputs to prove a system actually works
- Weigh cost, latency, and model tradeoffs like an operator
- Hold a peer-level conversation with any technical team
Modules
How to frame an AI problem, pick an approach, and define scope, data, and success criteria.
An overview of AI tooling plus how RAG and agents extend models with data and actions.
Making your first API call and evaluating outputs against quality, cost, and latency.
Frequently asked questions
Do I need to know how to code to follow Building with AI?
No. Building with AI assumes no programming background: the only hands-on coding is a first API call in Python, included so you understand what your technical teams actually do. The rest is about framing problems, choosing an approach, and judging results.
What exactly does Building with AI cover?
Three modules, nine lessons in total: structuring an AI project (framing, approach, scope and success criteria), the tools landscape with RAG and agents, then coding basics and evaluation including cost, latency and model selection. It sits inside the AI Essentials track.
Who is this for, a technical lead or a business leader?
A business leader who has to direct AI work without building it personally. The stated goal of Building with AI is to let you hold a peer-level conversation with any technical team: knowing what is easy, what is hard, and what is an excuse.
How do I decide between prompting, RAG, fine-tuning, and an agent?
That decision is the subject of a dedicated lesson, and it comes after framing the problem, never before. The logic runs through what the model needs to know, whether it must act, and what your data and success criteria actually require, which is also why the RAG and agents lessons come next.
What is RAG and why does it get its own lesson?
Retrieval-augmented generation puts your own data behind the model so it answers from your documents instead of guessing. It gets a full lesson because it is the most common way companies make a general model useful on their specific content, and it involves choices about embeddings and vector databases.
How do you prove an AI system actually works and not just looks impressive?
Through evaluation, treated as a distinct lesson in Building with AI: a system that feels smart and a system that works are two different things. You define success criteria at the scoping stage, then measure outputs against them alongside cost and latency, since those tradeoffs decide the unit economics.