Daily AI Wizard

Daily AI Wizard

By Oliver Bodemer · DailyAIWizardEducationCourses
Download on the App Store

Daily AI Wizard episodes

  • Welcome to Daily AI Wizard: Learn AI by Building It (Trailer)

    Want to build real AI, not just read about it? This is the Daily AI Wizard trailer.Hosted by Oliver Bodemer, with AI tutor avatars Anastasia and Sophia. Start with Build Real AI (Season 7): fifteen short episodes from an empty folder to an AI app you've shipped.Follow the show so new lessons show up automatically. Prefer to watch? https://youtube.com/@dailyaiwizard

    1 min
  • Build Real AI E15: You Built It. You Shipped It!

    Fourteen episodes. An empty folder to a shipped AI app. In the season finale, every brick snaps into one finished project — and you see how to present it so it actually gets you noticed.

    This is episode 15 of 15 in Build Real AI. You leave with an assembled capstone, a polished README, a live demo link, and a portfolio piece that proves you build and ship. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    What you'll walk away with:

    • An assembled capstone app from everything you built this season
    • A polished README that recruiters actually read
    • A live demo link — your portfolio proof
    • A recap of your end-to-end AI skill set

    Watch the screen version: https://www.youtube.com/watch?v=TXhWBOH0Xdg

    5 min
  • Build Real AI E14: Cache the Repeats. Right-Size. Rate-Limit. Admit When Wrong

    AI isn't production-ready until it's affordable, fast, safe, and honest. This episode covers four pillars that separate a demo from a real product.

    This is episode 14 of 15 in Build Real AI. You leave with caching, rate limiting, right-sizing, and uncertainty handling. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    What you'll learn:

    • Cache repeated requests — save money and speed
    • Right-size your model — match the model to the job
    • Rate-limit your endpoints
    • Be honest about uncertainty — earn user trust

    Watch the screen version: https://www.youtube.com/watch?v=rxIERYW-Fig

    8 min
  • Build Real AI E13: It's Not Real Until It's Online

    It's not real until someone else can open it. In this episode you push to GitHub, connect your dashboard, set secrets, hit deploy — and get a live public URL for free.

    This is episode 13 of 15 in Build Real AI. You leave with requirements.txt, a GitHub-connected deploy, dashboard secrets, and a live URL you can text to anyone. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    What you'll learn:

    • Why a project on your laptop is invisible
    • How requirements.txt keeps your cloud environment in sync
    • How to store secrets in the dashboard — never in the repo
    • How to deploy straight from your GitHub repo
    • How to open your live public URL on any device

    Watch the screen version: https://www.youtube.com/watch?v=mg_wQHvaTaM

    6 min
  • Build Real AI E12: AI Doesn't Crash. It Lies to You.

    AI fails in strange, confident ways. In this episode: validate, catch, fallback, then three tests that stay green.

    This is episode 12 of 15 in Build Real AI. You leave with input validation, a try/except fallback, and three green pytest tests. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    What you'll learn:

    • Why AI bugs don't crash — they lie
    • How to validate input before it reaches the model
    • How to catch failures with a friendly fallback
    • Three pytest tests: normal, edge, and bad input

    Watch the screen version: https://www.youtube.com/watch?v=MncbljaSg-s

    9 min
  • Build Real AI E11: Make the LLM Answer From Your Own Data (RAG, Simply)

    An LLM knows a lot about the world — and nothing about your documents. In this episode you build a mini chatbot that answers from files you give it.

    This is episode 11 of 15 in Build Real AI. You leave with rag_chatbot.py — one hit, and one honest I-don't-know. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    What you'll learn:

    • Why a raw LLM invents answers about your files
    • Chunk, embed, retrieve, then ask
    • How to ground the answer in context you provided
    • How to make it say so when the answer isn't there

    Watch the screen version: https://www.youtube.com/watch?v=MLsj8ItG3sU

    12 min
  • Build Real AI E10: I Built an LLM Feature in Python — Then Almost Committed the Key

    The first time you talk to a large language model from your own file, it still feels like a person behind the glass. Then you see the loop: prompt in, response back. Then you almost paste the API key into the script “just for today.” Don’t.

    In episode 10 of Build Real AI, you call an LLM from Python, hide the key in an environment variable, and build a tiny real feature: any messy product review becomes one polite sentence. Then the experiment that should humble every prompt you write. Same model. Same review. Two instructions. The vague one is mush. The specific one is a product.

    You leave with llm_feature.py — an env-based key, a working summarizer, and a prompt you actually wrote. Next, the model learns to answer from your own documents.

    This is episode 10 of 15. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    Watch the screen version: https://www.youtube.com/watch?v=-poq-auWqL8

    9 min
  • Build Real AI E09: Stop Reinventing: Use a Pretrained Model in Five Lines

    In five lines of code you can use a model that took a company millions of dollars and thousands of GPUs to train.

    This is episode 9 of 15 in Build Real AI. You leave with pretrained.py — sentiment and summarization pipelines. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    What you'll learn:

    • When not to train from scratch
    • A Hugging Face pipeline in one line
    • Sentiment and summarization, with no training
    • How the first download and cache behave

    Watch the screen version: https://www.youtube.com/watch?v=-4GPFXQQoPQ

    14 min
  • Build Real AI E08: Give Your AI a Face — A Clickable App, No HTML, No JavaScript

    Right now, using your AI requires knowing code. That's a dealbreaker for real people. Today you build a text box, a button, and a result.

    This is episode 8 of 15 in Build Real AI. You leave with streamlit run app.py — an app a human can actually click. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    What you'll learn:

    • Why a UI is the product
    • Streamlit with no HTML and no JavaScript
    • How to wire the saved model to a box and a button
    • The shift from script to something a person can use

    Watch the screen version: https://www.youtube.com/watch?v=3Xcjqm59D6g

    18 min
  • Build Real AI E07: Turn Your Model Into an API

    Your model right now lives in a file on your laptop. That helps nobody. In this episode you turn it into an API other apps can actually call.

    This is episode 7 of 15 in Build Real AI. You leave with a saved model, a FastAPI /predict endpoint, and a live JSON response. Hosted by Oliver and Olga, with Anastasia and Sophia teaching.

    What you'll learn:

    • Train once, save, reuse
    • A minimal FastAPI /predict endpoint
    • How to call it and get JSON back
    • Why a callable model is the difference between a demo and a product

    Watch the screen version: https://www.youtube.com/watch?v=kRFQN0ZkT2Q

    13 min

About Daily AI Wizard

From the publisher's feed

Learn AI, Python and machine learning from zero in short daily lessons. Daily AI Wizard is a beginner-friendly podcast by Oliver Bodemer, with AI tutor avatars Anastasia and Sophia, that helps you go from your first line of Python to building and shipping real AI apps.