Build Hour: API en Codex Build Hour: API & Codex

Bouw workflows die draaien op agents voor echt engineeringwerk met Codex en de API's van OpenAI. In deze Build Hour leer je hoe teams verder gaan dan pair programming en overstappen op delegeren aan agents, waarbij AI-systemen complete engineeringtaken oppakken, van planning tot uitvoering. Charlie Guo (DevEx), Ryan Lopopolo (Future of Work) en Mitch Troyanovsky (medeoprichter, Basis) laten zien hoe je: • Nieuwe features sneller shipt met Codex, met echte voorbeelden van Basis: https://www.getbasis.ai/ • Systemen bouwt die door agents worden aangestuurd, met nieuwe API-mogelijkheden zoals hosted shell, skills en websockets • Agents evalueert en verbetert met het framework Agent Legibility Score • Harness Engineering-technieken toepast om agent-workflows betrouwbaar te maken in productie • GPT-5.4 inzet voor reasoning met grote context, computer-use-taken en agent-workflows op basis van tools • Handmatig werk vermindert door complexe logica om te zetten in herbruikbare flows die door agents worden aangestuurd 👉 Codex-documentatie: https://developers.openai.com/codex 👉 API-documentatie: https://developers.openai.com/api/docs 👉 Blog over Harness Engineering: https://openai.com/index/harness-engineering/ 👉 Blog over GPT-5.4: https://openai.com/index/introducing-gpt-5-4/ 👉 Volg mee met de code-repo: http://github.com/openai/build-hours 👉 Meld je aan voor komende live Build Hours: https://webinar.openai.com/buildhours 00:00 Introductie 01:58 Wat is er nieuw: Codex 05:01 Wat is er nieuw: API 08:33 Demo: Agent Legibility Score 21:53 Harness Engineering 32:32 Klant in de spotlight: Basis 47:57 Vragen en antwoorden

Build agent-powered workflows for real engineering work with Codex and OpenAI APIs. In this Build Hour, you'll learn how teams are moving beyond pair programming to agentic delegation, where AI systems can take on entire engineering tasks from planning to execution. Charlie Guo (DevEx), Ryan Lopopolo (Future of Work), Mitch Troyanovsky (Cofounder, Basis) cover how to: • Ship new features faster using Codex, with real examples from Basis: https://www.getbasis.ai/ • Build agent-driven systems using new API capabilities like hosted shell, skills, and websockets • Evaluate and improve agents using the Agent Legibility Score framework • Apply Harness Engineering techniques to make agent workflows reliable in production • Use GPT-5.4 for large-context reasoning, computer-use tasks, and tool-based agent workflows • Reduce manual overhead by turning complex logic into reusable agent-driven flows 👉 Codex docs: https://developers.openai.com/codex 👉 API docs: https://developers.openai.com/api/docs 👉 Harness Engineering Blog: https://openai.com/index/harness-engineering/ 👉 GPT-5.4 Blog: https://openai.com/index/introducing-gpt-5-4/ 👉 Follow along with the code repo: http://github.com/openai/build-hours 👉 Sign up for upcoming live Build Hours: https://webinar.openai.com/buildhours 00:00 Introduction 01:58 What's New: Codex 05:01 What's New: API 08:33 Demo: Agent Legibility Score 21:53 Harness Engineering 32:32 Customer Spotlight: Basis 47:57 Q&A