GPT-5 is OpenAI’s most steerable reasoning model yet. This Build Hour walks through its new capabilities, how to use it in the Responses API, and practical prompting techniques for coding and agentic tasks.
Bill Chen (Applied AI), Eric Han (Research), and Anoop Kotha (Applied AI) cover:
– GPT-5 capabilities: stronger code quality, front-end/UI generation, agentic task reliability
– New parameters: minimal reasoning, verbosity, and free-form function calling
– Live demo: building a Minecraft clone using GPT-5 in the Responses API
– Prompting best practices: avoiding conflicting instructions, meta prompting, and controlling agentic behavior
– Customer spotlight: Charlie Labs shows how they built an autonomous coding agent that works directly in GitHub and Slack workflows (
– Live Q&A
👉 Follow along with the code repo:
👉 GPT-5 Docs:
👉 Prompt Optimization Cookbook:
👉 Prompting Guide:
👉 Sign up for upcoming live Build Hours:
source