Articles from developers.openai.com

OpenAI cookbook demonstrates SchemaFlow, an agentic workflow for database change impact analysis, SQL generation, evaluation, and guardrails using the OpenAI Agents SDK.

A guide demonstrating how to configure and use OpenAI models via Amazon Bedrock's Responses API for production workflows covering text generation and structured outputs.

OpenAI's Secure MCP Tunnel lets users connect private MCP servers to OpenAI products via an outbound-only tunnel, keeping servers behind firewalls.

OpenAI's gpt-image-2 model offers production-quality image generation with high-fidelity photorealism, text rendering, and flexible quality-latency tradeoffs, supported by a prompting guide covering generation, editing, and creative workflows.

Using skills, AGENTS.md, and GitHub Actions, OpenAI accelerated OSS maintenance in their Agents SDK repos, merging 457 PRs in three months, up from 316.

OpenAI released gpt-realtime, a speech-to-speech model in the API, and published a prompting guide detailing techniques for instruction following, voice quality, and tool calling.

OpenAI's Codex prompting guide details how to optimize the model's performance through autonomy, tool use, and compaction features.

OpenAI's Codex successfully built a design tool from scratch over 25 hours, demonstrating long-horizon agentic coding with milestone-based planning and continuous verification.

Prompt caching reduces latency by up to 80% and costs by up to 90% by reusing computed key/value tensors for repeated prompt prefixes in OpenAI's API.

OpenAI introduces Skills, a reusable bundle of instructions, scripts, and assets mounted into shell environments, enabling versioned, conditionally invoked workflows that keep system prompts lean.

OpenAI advises developers to build ChatGPT apps as focused, model-callable capabilities—small APIs that let users know, do, or show new things—rather than porting full products into chat.

Coding agents like Codex can now sustain multi-hour reasoning tasks, transforming the entire software development lifecycle by delegating mechanical work across planning, design, build, test, review, and deployment.