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
A plugin that scores well in your own evaluation can still fail once it runs inside the product it ships in. The harness around the model ac
A full-duplex voice agent must do two things at once: sustain a natural, continuously unfolding conversation and complete a user’s task corr
How OpenAI’s Core Experimentation team uses Codex to remove unused code, clean up stale experiments, and improve CI.
How Runme and WebMCP turn recurring engineering tasks into reviewable, reusable workflows.
How I built a procedural space exploration game in Codex, from concept art to planets you can land on.
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.
Sign in with ChatGPT lets users sign in to your app with their ChatGPT account and, when eligible, use their ChatGPT plan to power its AI fe
Revisit skill descriptions, AGENTS.md, and task prompts to avoid bloated context.
Use AWS Lambda MicroVMs to run your agent's tools in your AWS account. OpenAI runs the agent harness; each MicroVM runs codex exec-server an
A support router turns a customer's message into a queue your application can assign. In this walkthrough, you'll define four queues, send t
How guided tasks, scientific viewers, and sequencing analysis help researchers follow a question from data to evidence.
Why direct OpenAI access matters for previews and critical workloads.
How I used Codex, GPT-Live-1, and a Raspberry Pi to turn an LED display into a voice-controlled assistant.
Databricks Sandbox now supports the OpenAI Agents API, enabling developers to run AI agent code and tool calls in an isolated, serverless en
A great image should work on any background. Transparent image assets make it easy to reuse the same visuals across campaigns, websites, pre
Function calling lets you connect GPT models to external tools and APIs. Here's how to get started.
