Crack your next interview in 2 weeks — cohort starts Jul 27 — Join free →

Get the next real AI project in your inbox — free, no path commitment.

You know you need AI skills.
We built the plan.

Most engineers spend months watching videos and reading docs without building anything they can show. Confident Prep gives you a structured path of real, deployable AI projects — matched to where you are and where you want to go.

Written and curated by a mentor with 22 years of production experience. No theory dumps. No padding. Every project ships to AWS.

$ aws bedrock invoke-model \
   --model-id anthropic.claude-3-haiku-20240307-v1:0 \
   --body '{"prompt": "Build something real."}'

Real articles, not a sales page

Practitioner-level AI/ML writing — no fluff, no fabricated claims.

Read all articles →

Where are you headed?

Pick the path that fits you. If you're not sure, we'll help you figure it out.

36 projects, all open source on GitHub ↗

FRESHER

AI Engineering Fundamentals

You're newer to engineering and want to get into AI/ML. You don't need ML math — you need to build and deploy real things.

12 projects · Starts from Python

Outcome: junior AI engineer–ready

First project: Document Chat — A CLI tool that loads a PDF or text file and answers questions about it, with streaming output and exact source citations for every answer.

MID-CAREER

AI-Augmented Engineering

You have 2–8 years of software experience. AI is everywhere and you feel behind. These projects put AI into the work you already know how to do.

12 projects · Any language welcome

Outcome: AI in your toolkit

First project: Code Review Bot — A CLI that reads a git diff, chunks it per file, and uses an LLM in JSON mode to return prioritized, structured findings by severity and category.

ML-FOCUSED

ML Engineering on AWS

You've done some ML or data science and want to own the full system — training, serving, monitoring — in production on AWS.

12 projects · Python + ML exposure

Outcome: own ML systems end-to-end

First project: Local to SageMaker — Trains an XGBoost classifier on the UCI Adult dataset locally with a CLI script, then submits the identical script as a managed SageMaker training job via a least-privilege CDK-provisioned IAM role, with a cost estimator and CloudWatch metric fetcher.

CUSTOM

Build Your Own Path

None of the above quite fit? Answer 4–5 questions about your situation and we'll assemble a custom path from our project library and email it to you.

Takes 2 minutes · Reply in 48h

Tell us about yourself

Not sure which path fits you? Answer 3 questions.

Q1: How long have you been writing code?

Q2: What's your goal right now?

Q3: What have you already tried?

How it works

01

Pick your path

You tell us where you are and where you're headed. We give you the exact sequence.

02

Get projects delivered

Every fortnight, one project lands in your inbox: what to build, how to build it, what you'll learn.

03

Build and ship

Each project has a GitHub repo you fork, deploy to AWS, and own. Add it to your portfolio today.

Stuck? Reply to any email and the mentor responds personally.