Research Layer
Focused guides, prompts, and workflows with a platform-specific visual system.
This notebook builds an improvement flywheel for an agent. We start with real traces, add human and model feedback, turn that feedback into
This cookbook is about closed-loop agent workflows: agents that produce an output, validate it, and use the feedback to improve the next pas
A full-duplex voice agent must do two things at once: sustain a natural, continuously unfolding conversation and complete a user’s task corr
In this cookbook, you'll build a private flight assistant for a fictional airline and learn how to connect ChatGPT to an OpenAI Agents SDK w
Goals are persistent objectives in Codex that keep a thread working toward a defined outcome across turns. A Goal gives Codex a completion c
ChatGPT workspace administrators can restrict the SharePoint app to approved SharePoint site collections. This example resolves ordinary Sha
Complete applications and sandbox integrations for the Agents API. | Example | What it does | | --- | --- | | Incident response | Investig
A great image should work on any background. Transparent image assets make it easy to reuse the same visuals across campaigns, websites, pre
How I used Astra to design a house, refine its everyday details, and explore it through Blender camera tours and an Unreal Engine 5 walkthrough.
How guided tasks, scientific viewers, and sequencing analysis help researchers follow a question from data to evidence.
How I built a procedural space exploration game in Codex, from concept art to planets you can land on.
From a short-staffed veterinary clinic to speech accessibility, spatial audio, and ancient machines, the winning projects started with problems their builders knew well.
How Runme and WebMCP turn recurring engineering tasks into reviewable, reusable workflows.
Use ChatGPT, Codex Security, and open-source tools to investigate threats, validate vulnerabilities, and move from findings to reviewed, verified fixes.
Build Codex into the products and workflows your users already know.
Revisit skill descriptions, AGENTS.md, and task prompts to avoid bloated context.
Function calling lets you connect GPT models to external tools and APIs. Here's how to get started.
