Skip to Content
View all events

Getting Started with GPT-5.5

Published by O'Reilly Media, Inc.

Beginner content levelBeginner

Using, prompting, and building with GPT-5 from OpenAI

Course Outcomes:

  • Understand GPT-5’s advantages compared to previous models
  • Describe GPT-5’s key features, release context, and implications for work and development
  • Interpret the GPT-5 system card and preparedness framework for practical application
  • Apply GPT-5-specific prompting strategies to produce high-quality, targeted outputs
  • Understand the impact of GPT-5 single model (router) approach to general ChatGPT usage
  • Understand and use GPT-5’s new parameters and developer tools

Get a rundown of the just-released GPT-5’s improved capabilities, drawn from official OpenAI resources, system documentation, and curated third-party insights. Through presentations, demos, and structured exercises, expert Lucas Soares takes you from basic interactions all the way to building and deploying functional GPT-5-powered applications with the new API. Along the way, you’ll also examine updated prompting guidelines, explore new developer parameters, review practical applications for the new model, and consider safety issues, gaining a deep understanding of the latest LLM from OpenAI. And you’ll take home a set of working code examples to adapt for your own projects.

What you’ll learn and how you can apply it

  • Design project workflows that incorporate GPT-5 for increasingly complex use cases
  • Build interactive React/JS/HTML apps that incorporate the improved capabilities of this new model

This live event is for you because...

  • You’re a developer who’s familiar with LLMs and wants to explore GPT-5’s latest capabilities.
  • You’re an engineer who’s interested in building AI-powered tools and applications.
  • You’re an AI practitioner who wants practical, example-driven exposure to GPT-5’s new features.

Prerequisites

  • Python (latest version) and Node.js installed on your computer (to follow along with demos)
  • A code editor of your choice (instructor will use Cursor)
  • An OpenAI developer account and API keys
  • The course GitHub repository cloned (link provided prior to event)
  • Basic understanding of prompt engineering and LLMs
  • Programming experience in Python, JavaScript, or similar languages
  • Familiarity with running code locally or in notebooks
  • Comfort with APIs and developer documentation

Recommended follow-up:

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Introducing GPT-5 (50 minutes)

  • Presentation: GPT-5 overview and timeline; context of release compared to previous models; GPT-5 system card, router architecture, preparedness framework, risk categories, and mitigation strategies; key OpenAI resources (blog posts, release video, effects on work)
  • Demonstration: Building an interactive learning app with GPT-5
  • Q&A
  • Break

Prompting with GPT-5 (50 minutes)

  • Presentation: GPT-5 prompting guide and prompting structure; impact of GPT-5 router approach on ChatGPT use (custom GPTs, agent mode, and deep research)
  • Demonstration: Testing the ChatGPT interface with GPT-5
  • Hands-on exercise: Explore prompting with GPT-5
  • Q&A
  • Break

GPT-5 for developers (60 minutes)

  • Presentation: APIs, SDKs, and model documentation; new GPT-5 parameters; examples from the OpenAI Cookbook
  • Demonstration: Building a simple GPT-5-powered app
  • Q&A
  • Break

Building with GPT-5 (80 minutes)

  • Presentation: Experiments and best practices for building with GPT-5
  • Demonstrations: Experimenting with GPT-5 and Canvas; building a simple data science workflow; building a React app with GPT-5
  • Q&A
  • Break

Use cases for GPT-5 applications (60 minutes)

  • Presentation: What to build with GPT-5?
  • Demonstrations: Voice-mode live interpreter with GPT-5 thinking and voice; FastAPI app to generate business reports from websites
  • Q&A

Your Instructor

  • Lucas Soares

    Lucas Soares is a machine learning engineer who has worked at K1 Digital and Biometrid, where he developed computer vision and NLP models for applications such as document verification, OCR-based applications, and recommender systems. Lucas has also developed various ML models, including neural networks, Siamese networks, convolutional neural networks, LSTMs, and genetic algorithms.

    linkedinXlinksearch

Skill covered

GPT