Creating a LLM Prediction Game using Codex and Flask | CodeSignal Learn

Skip to main content

intermediate

Creating a LLM Prediction Game using Codex and Flask

Software Engineering

3 courses

24 practices

4 hours

Use Codex to build a Python-based LLM game where players guess the model’s next word. Across three courses, you’ll create a daily-refreshed, Wordle-style game with a web frontend. Players earn points by predicting the LLM’s next word based on semantic similarity.

Trusted by learners working at top companies

Turn screen time into skills time

Practice anytime, anywhere with our mobile app.

Sign up

Join the 1M+ learners on CodeSignal

Be a part of our community of 1M+ users who develop and demonstrate their skills on CodeSignal

Earn a shareable

Certificate of Achievement

Verified skills you'll gain

INTERMEDIATE

Back-End and API Development

INTERMEDIATE

Front-End Development

Tools you'll use

Codex

CSS

Flask

HTML

JavaScript

Python

spaCy

Course 1

Creating the base Word Play Game Data with Codex

4 lessons

7 practices

This course walks learners through the foundation of the LLM prediction game: how the game works, how prompts are structured, how they are generated for each day, and how LLM responses are used and tokenized. By the end of this course, you’ll have a self-contained daily dataset powering the game logic.

Course 2

Enhancing the Word Game with new Codex-powered functionalities

4 lessons

8 practices

Now that the base game logic is in place, this course introduces user interaction, semantic scoring, and a leaderboard system to bring competition and personalization into the experience. Learners will integrate server logic that connects the frontend with dynamic game behavior.

Course 3

Creating a frontend for the Word Play Game using Codex

3 lessons

9 practices

This course introduces learners to the process of building a web interface for the LLM prediction game using HTML, CSS, and JavaScript. By the end, players can interactively play the game, submit guesses, see scores, and compete on a leaderboard.

Scan to download

Other paths you may like

Fundamental Coding Interview Prep with Python

Introduction to Programming with Python

Mastering Algorithms and Data Structures in Python

Advanced Coding Interview Preparation with Python

Full-Stack Engineering with JavaScript

Prompt Engineering for Everyone

Journey into Data Science with Python

Java Programming for Beginners

Company

About Careers Leadership Talent Science Newsroom

Collections

Generative AI Business & Leadership Interview Prep AI & Machine Learning Learn to Code Data Science & Engineering

Platform

Platform Overview Skills Assessments Live Tech Interviews AI Interviewer AI Role-Play AI Tutoring with Cosmo

Roles

Talent Acquisition Engineering Leaders Sales Leaders CS & Support Leaders IO Psychologists Individuals

Resources

Resource Library Blog Customer Stories Interview Prep API Docs

Support

Copyright © 2026 CodeSignal

Privacy Terms Compliance & Trust

From our community

Hear what our customers have to say about CodeSignal Learn

I'm impressed by the quality and can't stop recommending it. It's also a lot of fun!

Francisco Aguilar Meléndez

Data Scientist

+11

I love that it's personalized. When I'm stuck, I don't have to hope my Google searches come out successful. The AI mentor Cosmo knows exactly what I need.

Faith Yim

Software Engineer

+14

It's an amazing product and exceeded my expectations, helping me prepare for my job interviews. Hands-on learning requires you to actually know what you are doing.

Alex Bush

Full Stack Engineer

+9

I'm really impressed by the AI tutor Cosmo's feedback about my code. It's honestly kind of insane to me that it's so targeted and specific.

Abbey Helterbran

Tech consultant

+8

I tried Leetcode but it was too disorganized. CodeSignal covers all the topics I'm interested in and is way more structured.

Jonathan Miller

Senior Machine Learning Engineer

+12

I'm impressed by the quality and can't stop recommending it. It's also a lot of fun!

name

Francisco Aguilar Meléndez

Data Scientist

+11