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
When an agentic system fails, the problem is often larger than a single bad response. A handoff may happen too late, a specialist agent may
OpenAI's gpt-image generation models are designed for production-quality visuals and highly controllable creative workflows. They are well-s
A great image should work on any background. Transparent image assets (in preview) make it easy to reuse the same visuals across campaigns,
AI agents often need information from external services to complete a task. A procurement agent might check a supplier against a sanctions d
Goals are persistent objectives in Codex that keep a thread working toward a defined outcome across turns. A Goal gives Codex a completion c
This cookbook shows how to build a ChatGPT workspace agent. Currently available in research preview for ChatGPT Business, Enterprise, and Ed
Workspace Agents let teams save repeatable work in ChatGPT: instructions, connected context, app actions, approvals, and output format. API
Lessons from how Perplexity Computer's voice agent was built with the Realtime API.
Provide more detailed rules for Codex to spot issues and better adhere your conventions during code review.
Use Remote in the ChatGPT mobile app to start, steer, review, and organize engineering work.
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 we preserved private network boundaries while supporting MCP streaming, authentication, and an inspectable client.
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.
How Runme and WebMCP turn recurring engineering tasks into reviewable, reusable workflows.
Function calling lets you connect GPT models to external tools and APIs. Here's how to get started.
