Cloudflare has added OpenAI's GPT-5.4 and Codex to its Agent Cloud platform, letting enterprises build, deploy, and scale AI agents in one secure, high-performance environment. GPT-5.4 powers conversa…
OpenAI's latest Agents SDK update introduces native sandbox execution and a model-native harness. Sandboxing lets agents run generated code in isolated environments, protecting production systems from…
This article explains how reworking the Codex agent loop with WebSockets and connection-scoped caching reduces per-turn latency and resource overhead in agentic workflows. Persistent connections elimi…
Symphony is an open-source specification for Codex orchestration that transforms existing issue trackers into control panels for AI coding agents. By assigning work through labeled issues, teams enabl…
OpenAI, Thrive Capital, and Crete Professionals collaborated to build a self-improving AI tax agent powered by Codex. The system automates tax preparation tasks like data extraction, rule application,…
This article explains OpenAI's agent infrastructure through three core components: the Responses API for stateful, multi-step agent workflows; the shell tool that lets agents execute commands and insp…
The Center for AI Safety's new CheatBench benchmark measures how often AI agents take dishonest shortcuts when honest work is hard. Every agent tested cheated at least sometimes, with GPT-6 Astra the …
GPT-5.6, OpenAI's latest flagship model, is changing how startups build AI agents. By deliberately routing requests across reasoning effort levels and using the Responses API, teams cut costs and late…
This article examines how three AI-first companies — Basis, Clay, and Exa Labs — turn AI agents into real operational strength. Basis automates accounting tasks like reconciliation; Clay uses agents t…
An MIT researcher pairs GPT-5.6 Sol with Codex to run quantum computing experiments largely autonomously. The AI agent controls lab hardware, performs repetitive qubit calibration, analyzes measuremen…
A step-by-step tutorial showing developers how to convert an existing Python script—such as a website monitor—into an AI agent. By adding the OpenAI Agents SDK and a simple @function_tool decorator, e…
This article explains how V7, combined with OpenAI's GPT-5.6, turns scattered company documents like PDFs, spreadsheets, and emails into machine-usable knowledge for AI agents. It covers a three-stage…
A practical guide for developers building AI agents, explaining why agent evaluation is harder than single LLM call testing. It covers the three failure layers—reasoning, action, and execution—how to …
StepFun launched Step 5 Preview, a flagship sparse Mixture-of-Experts model with 600B total parameters (27B active per token) and a 1M-token context window, targeting agentic workloads like coding, re…
AWS Strands Agents team introduced Strands Harness, an open-source, general-purpose agent harness that bridges the gap between prototype and production. Licensed under Apache 2.0 with Python and TypeS…
