GPT-5.5 Bio Bug Bounty

Top 10 uses for Codex at work

Top 10 uses for Codex at work Try these 10 prompts to move real work forward with dashboards, decks, workflows, and more. You’ve seen what Codex can do. Now it’s time to put it to work. These use cases show how to use Codex to do real work: create deliverables, pull together context from multiple tools, take action on real inputs, and move tasks forward faster. Start with the generic prompt if you want something you can use right away, then use the customization suggestions and example to make it your own. You start the day by bouncing between your calendar, messages, email, and notes, trying to figure out what matters most. Codex can pull that context together, keep watch for changes, and turn it into one clear brief so you spend less time triaging and more time acting on…

Codex settings

Codex settings Make Codex work the way you want, with fewer interruptions. You can access settings from the menu in the bottom left corner of Codex. For your first few tasks, focus on a few key settings: personalization, prevent sleep, detail level, and appearance. General > Prevent sleep while running keeps your computer awake while Codex is running. This is useful for longer tasks. If your computer goes to sleep, Codex may stop working. General > Detail level controls how much information Codex shows while it is working. Coding mode shows the specific commands Codex is executing. If this is more information than you need, switch to Default to keep your conversation cleaner. Personalization works a lot like personalization in ChatGPT. You can decide whether you want Codex to speak to you in a friendly tone or a direct tone.…

How to get started with Codex

How to get started with Codex Tips to set up Codex, create your first project, and start completing real tasks. Start by downloading the Codex desktop app and signing in with your ChatGPT account. Once you open Codex, create your first thread. A thread is like a chat in ChatGPT: a space where you go back and forth with Codex to accomplish a task. You can create a standalone thread, but most of the time you’ll want to work inside a project. A project is connected to a folder on your computer: Tip: To keep things simple, create a folder on your computer named Codex. Inside that Codex folder, you can have a separate folder for each project. If you want Codex to work with specific files for a project, just drag them into the folder. If not, you can…

GPT-5.5 System Card

GPT‑5.5 is a new model designed for complex, real-world work, including writing code, researching online, analyzing information, creating documents and spreadsheets, and moving across tools to get things done. Relative to earlier models, GPT‑5.5 understands the task earlier, asks for less guidance, uses tools more effectively, checks it work and keeps going until it’s done. We subjected the model to our full suite of predeployment safety evaluations and our Preparedness Framework, including targeted red-teaming for advanced cybersecurity and biology capabilities, and collected feedback on real use cases from nearly 200 early-access partners before release. We are releasing GPT‑5.5 with our strongest set of safeguards to date, designed to reduce misuse while preserving legitimate, beneficial uses of advanced capabilities. We generally treat GPT‑5.5’s safety results as strong proxies for GPT‑5.5 Pro, which is the same underlying model using a setting that…

Introducing GPT-5.5

Update on April 24, 2026: GPT‑5.5 and GPT‑5.5 Pro are now available in the API. The system card has also been updated to describe the additional safeguards that apply. We’re releasing GPT‑5.5, our smartest and most intuitive to use model yet, and the next step toward a new way of getting work done on a computer. GPT‑5.5 understands what you’re trying to do faster and can carry more of the work itself. It excels at writing and debugging code, researching online, analyzing data, creating documents and spreadsheets, operating software, and moving across tools until a task is finished. Instead of carefully managing every step, you can give GPT‑5.5 a messy, multi-part task and trust it to plan, use tools, check its work, navigate through ambiguity, and keep going. The gains are especially strong in agentic coding, computer use, knowledge work,…

What is Codex?

What is Codex? Understand what Codex is and how it fits into your work Codex is an AI agent that you can delegate real work to. ChatGPT is great for asking questions, brainstorming, and drafting in conversation. Codex is designed for a different kind of task—it can work across files, tools, and repeatable workflows to help move work forward. A simple way to think about it: ChatGPT helps you think through the work, while Codex helps you hand off parts of the work itself. You don’t need to be a developer or working on software to use Codex. It goes beyond coding and is especially useful for tasks that require more than a single answer—like gathering information from multiple sources, creating and updating files, or producing outputs such as documents, slides, and spreadsheets. Codex can connect to tools, take action,…

Automations

Automations Run recurring tasks automatically using schedules and triggers in Codex. Codex can automatically run tasks on a schedule. This makes Codex proactive. Instead of waiting for you to come back and ask for an update, Codex can return at the scheduled time, do the work, and surface the result for you to review. This is useful for recurring work, like preparing for the day, reviewing what changed, checking for updates, summarizing recent activity, or creating a weekly report. For example, you might use a thread automation to: - Write a weekly review every Friday - Create a morning brief from yesterday’s work - Summarize new files added to a folder - Clean up a weekly data export - Check for missing or inconsistent information - Create a recurring project status update Some automations can also return to the same…

Plugins and skills

Plugins and skills Plugins and skills help Codex do more specific kinds of work. Plugins help Codex connect to other tools and sources of information. For example, a plugin might help Codex reference files in Google Drive, scan your email inbox, or work with information from another tool you use. Plugins can be simple and useful right away. If you already have the information you need in a connected plugin, you can ask Codex to use it instead of copying and pasting everything into the thread. To access plugins, select plugins in the top left corner of Codex. From there, you can see plugins that are recommended or already installed, browse the plugins library, or create a new plugin. Creating a new plugin usually requires more technical expertise than creating a skill. A skill is like a playbook Codex can…

Working with Codex

Working with Codex Learn how to set up your Codex workspace and start working with threads and projects. When you open Codex, you’ll see a few core elements: a sidebar menu, projects, settings, and a chat window. You don’t need to understand everything right away, but we’ll cover the basics here. The sidebar is where you navigate between threads, projects, and tools. Most of your work will begin by creating a new thread. When you’re using Codex, think of a “thread” the same way you would think of a “chat” in ChatGPT. You can have a thread which stands on its own, or a thread which is nested within a project. Select New thread to begin. You can select an existing project to associate it with, create a new project, or leave it as a standalone conversation. Search to find…

Lowe’s puts project expertise into every hand

Lowe’s puts project expertise into every hand With OpenAI, Lowe’s brings their Mylow Companion app to all retail associates, applying the same AI foundation behind their customer-facing Mylow virtual advisor. Home improvement projects aren’t simple shopping trips. They're major investments, often involving thousands of dollars, multiple visits, and specialized expertise. “When you’re buying a t-shirt and it doesn’t fit, you just return it. No big deal,” says Seemantini Godbole, EVP, Chief Digital and Information Officer at Lowe’s. “But if you’re renovating a kitchen or redoing your floors, those are expensive decisions. You want to feel confident. And that requires expertise.” Lowe’s Red Vest associates have long helped customers navigate that complexity. But with stores up to 130,000 square feet and tens of thousands of SKUs in store, even seasoned team members can’t know everything. And online shoppers face similar challenges:…

Making ChatGPT better for clinicians

Making ChatGPT better for clinicians Built for clinical work, ChatGPT for Clinicians is now available for free to verified individual clinicians in the U.S. We’re introducing ChatGPT for Clinicians, a version of ChatGPT designed to support clinical tasks like documentation and medical research so clinicians can focus on delivering high-quality patient care. We’re making it free for any verified physician, NP, PA, or pharmacist, starting in the U.S. The U.S. healthcare system today is under extraordinary strain. Clinicians are being asked to care for more patients while managing growing administrative demands and a rapidly expanding body of medical research. Many are already turning to AI tools like ChatGPT for support. According to a 2026 survey by the American Medical Association(opens in a new window), physician use of AI is now at an all-time high, with 72% of physicians reporting they…

Speeding up agentic workflows with WebSockets in the Responses API

Speeding up agentic workflows with WebSockets in the Responses API By Brian Yu and Ashwin Nathan, Members of the Technical Staff When you ask Codex to fix a bug, it scans through your codebase for relevant files, reads them to build context, makes edits, and runs tests to verify the fix worked. Under the hood, that means dozens of back-and-forth Responses API requests: determine the model’s next action, run a tool on your computer, send the tool output back to the API, and repeat. All of these requests can add up to minutes that users spend waiting for Codex to complete complex tasks. From a latency perspective, the Codex agent loop spends most of its time in three main stages: working in the API services (to validate and process requests), model inference, and client-side time (running tools and building model…

Introducing workspace agents in ChatGPT

Introducing workspace agents in ChatGPT Codex-powered agents for teams. Today, we’re introducing workspace agents in ChatGPT. Teams can now create shared agents that handle complex tasks and long-running workflows, all while operating within the permissions and controls set by their organization. Workspace agents are an evolution of GPTs. Powered by Codex, they can take on many of the tasks people already do at work—from preparing reports, to writing code, to responding to messages. They run in the cloud, so they can keep working even when you’re not. They’re also designed to be shared within an organization, so teams can build an agent once, use it together in ChatGPT or Slack, and improve it over time. AI has already helped people work faster on their own, but many of the most important workflows inside an organization depend on shared context, handoffs,…

Workspace agents

Workspace agents Understand, build, and use agents for repeatable work in ChatGPT. Most ChatGPT users already know how to use AI for one-off tasks—like drafting, summarizing, brainstorming, or answering questions. The next phase of AI use is broader and more embedded in day-to-day work. Instead of helping with isolated moments, AI is increasingly being used to support repeatable workflows that depend on shared systems, standard handoffs, consistent outputs, and real-world constraints like timing, accuracy, and process. That’s where workspace agents in ChatGPT fit. They’re designed to be used for repeatable workflows—work you’d otherwise do manually, re-explaining the steps each time, and copying information between tools. Learn more about workspace agents in our blog post. If you’re new to agent building, let’s focus on the core concepts first so when you start building, you’ll know how to set up your workspace…

Introducing OpenAI Privacy Filter

Today we’re releasing OpenAI Privacy Filter, an open-weight model for detecting and redacting personally identifiable information (PII) in text. This release is part of our broader effort to support a more resilient software ecosystem by providing developers practical infrastructure for building with AI safely, including tools and models that make strong privacy and security protections easier to implement from the start. Privacy Filter is a small model with frontier personal data detection capability. It is designed for high-throughput privacy workflows, and is able to perform context-aware detection of PII in unstructured text. It can run locally, which means that PII can be masked or redacted without leaving your machine. It processes long inputs efficiently, making redaction decisions in a quick, single pass. At OpenAI, we use a fine-tuned version of Privacy Filter in our own privacy-preserving workflows. We developed Privacy…

Scaling Codex to enterprises worldwide

Scaling Codex to enterprises worldwide OpenAI is launching Codex Labs and partnering with top GSIs to bring it to thousands of engineering organizations. In early April, we shared that more than 3 million developers were using Codex every week. Just two weeks later, that number has grown to more than 4 million. Beyond individual adoption, we are seeing enterprises moving quickly to roll Codex into real workflows across engineering and beyond. Companies are using Codex across the software development lifecycle. Virgin Atlantic is using it to increase test coverage and increase team velocity - reducing technical debt and improving performance. Ramp is using it to accelerate code review. Notion is using it to quickly build new features. Cisco is using it to understand and reason across large, interconnected repositories. Rakuten is using it for things like incident response. What starts…

Introducing ChatGPT Images 2.0

April 21, 2026ProductReleaseCompanyIntroducing ChatGPT Images 2.0A new era of image generationTry in ChatGPT(opens in a new window)ShareImage modeClassic modeHorizontalSquareVerticalPage 1Page 2Page 3Page 4

OpenAI helps Hyatt advance AI among colleagues

OpenAI helps Hyatt advance AI among colleagues Key takeaways: - Hyatt has deployed ChatGPT Enterprise. - With ChatGPT Enterprise, Hyatt employees can access frontier AI capabilities like GPT 5.4, Codex, and more. - Departments including finance, marketing, and operations will use ChatGPT Enterprise to improve Hyatt guest and customers’ experience. Hyatt’s innovative approach with OpenAI reflects how Hyatt is elevating its use of technology and enhancing human connections. The company is making artificial intelligence broadly accessible to its employees, enabling teams to spend less time on manual tasks and more time focused on delivering exceptional guest experiences. As part of this effort, Hyatt has made ChatGPT Enterprise available to employees across its global corporate and hotel workforce, making it a core component of how the business runs day to day. ChatGPT Enterprise is just one example of how Hyatt is…

Codex for (almost) everything

We’re releasing a major update to Codex, making it a more powerful partner for the more than 3 million developers who use it every week to accelerate work across the full software development lifecycle. Codex can now operate your computer alongside you, work with more of the tools and apps you use everyday, generate images, remember your preferences, learn from previous actions, and take on ongoing and repeatable work. The Codex app also now includes deeper support for developer workflows, like reviewing PRs, viewing multiple files & terminals, connecting to remote devboxes via SSH, and an in-app browser to make it faster to iterate on frontend designs, apps, and games. With background computer use, Codex can now use all of the apps on your computer by seeing, clicking, and typing with its own cursor. Multiple agents can work on your…

Introducing GPT-Rosalind for life sciences research

Introducing GPT‑Rosalind for life sciences research A new purpose-built model to accelerate scientific research and drug discovery. Today, we’re introducing GPT‑Rosalind, our frontier reasoning model built to support research across biology, drug discovery, and translational medicine. The life sciences model series is optimized for scientific workflows, combining improved tool use with deeper understanding across chemistry, protein engineering, and genomics. On average, it takes roughly 10 to 15 years to go from target discovery to regulatory approval for a new drug in the United States. Gains made at the earliest stages of discovery compound downstream in better target selection, stronger biological hypotheses and higher-quality experiments. Progress in the life sciences is constrained not only by the difficulty of the underlying science, but by the complexity of the research workflows themselves. Scientists must work across large volumes of literature, specialized databases, experimental…

Accelerating the cyber defense ecosystem that protects us all

Trusted Access for Cyber is designed around a simple premise: advanced cyber capabilities should reach defenders broadly, but access should scale with trust, validation, and safeguards. Today we’re sharing the first organizations helping put that approach into practice, from open-source security teams and vulnerability researchers to enterprises operating some of the world’s most complex digital environments. The strength of this approach comes from the breadth of defenders involved. Cybersecurity is a team sport, and the systems people rely on are protected by organizations of many kinds, from major enterprises and security vendors to researchers, maintainers, public institutions, nonprofits, and smaller teams with limited security resources. Not every organization has the benefit of a 24x7 security team who is able to respond to incidents when they are disclosed on a Friday night(opens in a new window). It’s important for all software…

The next evolution of the Agents SDK

The next evolution of the Agents SDK The updated Agents SDK helps developers build agents that can inspect files, run commands, edit code, and work on long-horizon tasks within controlled sandbox environments. We’re introducing new capabilities to the Agents SDK(opens in a new window) that give developers standardized infrastructure that is easy to get started with and is built correctly for OpenAI models: a model-native harness that lets agents work across files and tools on a computer, plus native sandbox execution for running that work safely. For example, developers can give an agent a controlled workspace, explicit instructions, and the tools it needs to inspect evidence: Developers need more than the best models to build useful agents—they need systems that support how agents inspect files, run commands, write code, and keep working across many steps. The systems that exist today…

Trusted access for the next era of cyber defense

We are scaling up our Trusted Access for Cyber (TAC) program to thousands of verified individual defenders and hundreds of teams responsible for defending critical software. For years, we’ve been building a cyber defense program on the principles of democratized access, iterative deployment, and ecosystem resilience. In preparation for increasingly more capable models from OpenAI over the next few months, we are fine-tuning our models specifically to enable defensive cybersecurity use cases, starting today with a variant of GPT‑5.4 trained to be cyber-permissive: GPT‑5.4‑Cyber. In this post, we share how we expect our approach of scaling cyber defense in lockstep with increasing model capabilities to guide the testing and deployment of future releases. The progressive use of AI accelerates defenders – those responsible for keeping systems, data, and users safe – enabling them to find and fix problems faster in…

Enterprises power agentic workflows in Cloudflare Agent Cloud with OpenAI

Enterprises power agentic workflows in Cloudflare Agent Cloud with OpenAI Key Takeaways: - Millions of enterprises can now access OpenAI frontier models directly within Cloudflare Agent Cloud. - With OpenAI, enterprises using Cloudflare’s Agent Cloud can deploy agents powered by models like GPT‑5.4 to perform real work. - Enterprises can now deploy agents built on Codex harness to Cloudflare. Cloudflare is expanding access to OpenAI frontier models, including GPT‑5.4, making them available to millions of customers across Agent Cloud. Agent Cloud is a platform that enables businesses to deploy AI agents powered by OpenAI models to perform real work. For example, companies can use it with OpenAI to deploy agents that automatically handle tasks like responding to customers, updating systems, and generating reports - all within a secure, production-ready environment. Agent Cloud runs on top of Cloudflare Workers AI(opens in…

Brainstorming with ChatGPT

Brainstorming with ChatGPT Generate ideas, organize thinking, and turn direction into actionable plans. ChatGPT can act as a structured thought partner. It helps you generate options quickly, organize ideas into clearer themes, and turn a rough direction into a plan you can execute. It’s especially useful when you’re starting from a blank page, working through many competing ideas, or creating a “first pass” before you bring others in. It won’t replace your context, expertise, or judgment—but it can make the thinking process faster, more consistent, and easier to share. Most brainstorming gets stuck in one of two places: not enough ideas, or too many ideas with no structure. ChatGPT helps by doing three things well: - Expands your option set: It can propose angles, experiments, messages, and alternatives quickly so you’re not starting from scratch. - Adds structure: It can…

Prompting fundamentals

Prompting fundamentals Learn how to write clear prompts to get better, more useful responses. Prompt engineering is the process of designing and refining your input in a way that helps ChatGPT give the best possible answer. It’s about figuring out how to ask so you get the result you want—whether that’s a clear summary, comprehensive report, or detailed analysis. ChatGPT works best when you give it clear instructions. There’s no single “perfect” way to write a prompt. Think of it as a conversation with a colleague, where you might need to adjust your phrasing or tone to help them understand what you need. Experimentation and iteration are the best ways to discover how AI can be most useful to you. Be clear about what you need ChatGPT to do. Outline what you want, who it’s for, and why it matters.…

ChatGPT for research

ChatGPT for research Use ChatGPT to move from questions to evidence-backed insights and decisions. Researching with ChatGPT helps you move from question to evidence to decision more quickly. You can use it to gather and synthesize information, compare sources, and produce structured reports that include citations—so your output is easier to trust and easier to share. It’s useful for both quick orientation and for deeper, multi-step investigations. Why use ChatGPT for research? - Turn a fuzzy question into a clear research plan and set of sub-questions. - Sift through many sources faster and capture the important details with citations. - Produce consistent deliverables such as briefs, memos, competitor tables, annotated bibliographies. - Identify gaps, contradictions, and weak signals early—before committing to a direction. ChatGPT offers two main approaches for research, depending on how deep you need to go: Search is…

Getting started with ChatGPT

Getting started with ChatGPT Learn the basics of using ChatGPT and how to begin your first conversation. ChatGPT is a conversational AI assistant that helps you think, write, and solve problems by understanding natural language and generating human-like responses in real time. ChatGPT is built on large language models, enabling it to assist with a wide range of tasks. Learn more about large language models in What is AI. Take a look at the video below to learn about the different parts of the ChatGPT interface. Open ChatGPT.(opens in a new window) A new chat is already waiting for you. To get started, simply enter a prompt. A prompt is the question or instruction you type or share with ChatGPT to start a conversation. It is usually text, but it can also be an image, audio, file. Your prompt guides…

Using skills

Using skills Create reusable workflows that guide ChatGPT through recurring tasks. Skills turn the way you already work into reusable workflows that ChatGPT can follow consistently—so you spend less time re-explaining steps, formats, and requirements, and more time getting to a solid result. If you’ve ever found yourself reusing the same prompt or pasting the same template again and again, skills are designed to fix that. A skill is a reusable, shareable workflow that tells ChatGPT how to do a specific task. Rather than starting from scratch each time, you define the process once so it can be applied reliably whenever the task comes up. A skill typically includes: - Name and description: Help ChatGPT recognize when the skill is relevant. - Workflow instructions: Step-by-step guidance for the worflow—usually written in a file called SKILL.md. - Resources: Supporting materials the…

ChatGPT for finance teams

ChatGPT for finance teams Improve reporting, streamline planning, and communicate insights more clearly. Finance teams spend a lot of time turning incomplete inputs into something reliable—reconciling numbers, explaining variances, updating forecasts, and responding to business questions. The challenge is often the overhead such as organizing context, drafting narratives, and maintaining consistency across recurring work. ChatGPT helps reduce that overhead by structuring messy inputs, drafting first-pass outputs, and standardizing common workflows. It doesn’t replace finance judgment, but it reduces time spent on formatting, rewriting, and starting from scratch. - Helps you organize the work before you write or build. When you’re reviewing a spreadsheet export, a set of notes, and different explanations from stakeholders, the hardest part is often structuring the problem. ChatGPT can help you outline the questions to answer, the drivers to test, and the follow-ups to request—so you…

Writing with ChatGPT

Writing with ChatGPT Draft, revise, and refine written work with clarity and intent. ChatGPT can support many common workplace writing tasks: drafting from scratch, rewriting and tightening, adjusting tone for a specific audience, and turning rough notes into clear communication. It’s especially useful when you’re short on time, staring at a blank page, or trying to land the right level of polish. Tip: ChatGPT can work with uploaded files, or access files via connected apps. Learn more here. Most workplace writing has the same goal: help someone understand something quickly and know what to do next. ChatGPT can speed up the parts that often take the most time—finding a strong opener, organizing ideas, and refining wording—so you can focus on the decisions and details that matter. It is also effective for adapting tone across audiences. You can take the same…

Personalizing ChatGPT

Personalizing ChatGPT Customize ChatGPT’s behavior with instructions and memory to fit your needs. ChatGPT works best when you treat it less like a search box and more like a collaborator. It’s a new kind of tool—one that responds in a conversational way, can take on a “personality,” and adapts based on the guidance you give it. The more context and direction you provide, the more useful (and consistent) it becomes. In this section, you’ll learn two simple ways to personalize ChatGPT so it behaves more like a reliable teammate: Custom instructions and Memory. Custom instructions tell ChatGPT what it should know about you and how you prefer it to respond. These settings apply to new conversations until you change, disable, or remove them. Even small details can meaningfully improve results, such as: - Your role and responsibilities (“I lead customer…

Responsible and safe use of AI

Responsible and safe use of AI Learn best practices for using ChatGPT safely and effectively. AI is a transformative new technology that is reshaping knowledge work. The large language models (LLMs) that power ChatGPT are trained on vast amounts of publicly available text and other data to predict and generate human-like language. This enables them to assist with tasks such as drafting, summarizing, brainstorming, and answering questions, helping people work more efficiently and creatively. As this technology continues to evolve, it is important to use AI responsibly. These models may sometimes produce incorrect information or be misused if their outputs are applied without care. OpenAI’s mission is to ensure that artificial general intelligence (AGI) benefits all of humanity, and achieving this goal requires safe and thoughtful use by everyone. The tips on this page are designed to help anyone using…

Research with ChatGPT

Research with ChatGPT Use search and deep research to find, analyze, and synthesize information from across the web. ChatGPT can be a helpful research partner because it quickly brings together information from many sources, making it easier to explore ideas, spot patterns, and understand complex topics. By reasoning through context, citing sources, and producing clear, structured summaries, it helps turn open questions into well-defined insights. There are two different ways to search the public internet with ChatGPT—search and deep research. Below is an explanation of both, and when to use each. ChatGPT search allows ChatGPT to pull in the latest information from the internet directly into your conversations. This means you can go beyond ChatGPT’s built-in training knowledge and get up-to-date answers on things like current events, market trends, competitor activity, or niche details not included in its training data.…

ChatGPT for customer success teams

ChatGPT for customer success teams Manage accounts, improve communication, and drive better customer outcomes. Customer success work blends relationship management with operational follow-through—onboarding, adoption, troubleshooting, renewals, and cross-functional coordination. The challenge is often the overhead including pulling context from calls and tickets, turning notes into plans, writing clear follow-ups, and keeping everyone aligned on next steps. ChatGPT helps reduce that overhead by turning scattered inputs into clear, structured outputs so teams can focus more on customers and less on coordination. - Turns scattered customer context into a clear plan. CSMs often have the information—they just don’t have it in one place. ChatGPT can synthesize notes, emails, and product signals into a simple view of goals, current state, risks, and a concrete action plan you can share internally and with the customer. - Makes customer communication clearer and easier to act…

ChatGPT for operations teams

April 10, 2026 OpenAI AcademyChatGPT for operations teams Bring structure and clarity to operational work with ChatGPT. Operations teams sit at the intersection of information and execution. ChatGPT behaves like an always-on chief of staff. It reduces coordination friction by turning fragmented inputs into decision-ready summaries, documenting outcomes as reusable SOPs, and reinforcing the operating rhythm with consistent updates and artifacts. The result is less time stitching information together and more time driving execution. Why operations teams use ChatGPT - Helps you turn scattered inputs into a clear set of next steps. Operational work often pulls from many sources—notes, trackers, messages, and updates. ChatGPT helps organize this into a simple structure: what’s known, what’s unclear, what needs a decision, and who’s responsible. - Makes status updates clear enough that people stop asking the same questions. Status updates often stall because…

ChatGPT for managers

ChatGPT for managers Prepare for conversations and manage team work more effectively with ChatGPT. People management is a series of high-stakes moments: 1:1s, feedback, hiring decisions, performance cycles, team updates, and hard conversations. Much of the work is preparation and follow-through—capturing what you heard, deciding what to do next, and communicating clearly. ChatGPT can help with the time-consuming, repetitive parts such as organizing notes, drafting first-pass messages, and creating reusable templates for recurring tasks like 1:1 agendas, interview kits, onboarding plans, and performance documentation. It doesn’t replace your judgment or responsibility to follow HR or legal policy, but it helps you get past the blank page and move faster. - Prepare for conversations without overthinking them. You know what needs to be addressed, but planning how to approach the conversation takes time—how to be direct, which examples to use, and…

Analyzing data with ChatGPT

Analyzing data with ChatGPT Explore, analyze, and turn data into clear insights and actions. Loading… ChatGPT can help you move from raw data to useful insights with minimal setup. You can upload a CSV or Excel file, paste in a table, or connect a data source (if supported in your workspace), then start asking questions in plain language. Instead of building formulas, pivot tables, or dashboards for every question, you can quickly explore data, clean up tables, generate simple visualizations, and extract key takeaways in a format that's easy to share. It’s especially useful early in the process—when you’re still figuring out what’s in the data, identifying anomalies, and deciding where to dig deeper. It also helps translate findings into summaries others can review and act on. - Start with the decision you’re trying to support. A simple frame is:…

Financial services

Financial services Explore resources to evaluate, deploy, and scale AI in regulated financial environments. This page brings together essential resources to help financial institutions evaluate, adopt, and scale AI in regulated environments. Whether you’re exploring early use cases or supporting teams already deploying AI, these tools, guides, and examples are designed to help you move forward with confidence. All resources are tailored specifically for the needs of banks, asset managers, insurers, and other financial services organizations. Learn more about OpenAI for Financial Services. A curated set of ready-to-use prompts vetted for day-to-day financial services work, including: - Data analysis and financial modeling - Research, search, and synthesis - Policy, tax, and regulatory interpretation - Contract, covenant, and document analysis - Data extraction and support for Excel, BI, and ERP workflows These prompts are built to accelerate time-to-value while maintaining clarity,…

Using custom GPTs

Using custom GPTs Build purpose-built ChatGPT assistants that follow your instructions, use your context, and streamline repeatable work. Some versions of ChatGPT let you build custom GPTs—purpose-built versions of ChatGPT designed for a specific task or workflow. Instead of starting from a blank chat each time, a custom GPT can follow your preferred format, use your team’s context, and produce more consistent outputs—whether you’re drafting content, analyzing recurring datasets, generating visuals, or answering common questions. Custom GPTs are powered by tailored instructions that define how the GPT behaves. You can also add knowledge (files you upload) and enable tools (such as web search, data analysis, or connected actions). The result: less re-explaining, less copy/pasting, and fewer “wait—what’s the context again?” moments. You can explore custom GPTs here(opens in a new window). A regular chat is well-suited for quick, one-off tasks—brainstorming…

Working with files in ChatGPT

Working with files in ChatGPT Upload and work with files to analyze, edit, and generate content. ChatGPT allows you to upload and work with files directly in your conversations. This means you can analyze spreadsheets, edit documents, summarize PDFs, or work with images without leaving your chat. - Start a chat with ChatGPT. - Upload your file by opening the tools menu and selecting “Add photos or files” (supported formats include CSV, XLSX, PDF, DOCX, JPEG, PNG, TXT, and more). 3. Ask a question or give a task, for example: - “Summarize the main findings in this report and call out any risks or open questions.” - “Visualize this sales data by region and highlight the biggest changes month over month.” - “Rewrite this document to be clearer and more concise, while keeping the same tone.” - “Extract the key…

Applications of AI at OpenAI

Applications of AI at OpenAI Explore how OpenAI products and APIs bring AI into real-world use. OpenAI was founded with a long-term goal: to ensure advanced AI benefits humanity. Early work focused on research and experimentation, followed by large-scale model development. Over time, OpenAI began releasing models through both consumer-facing products and developer platforms, allowing individuals, teams, and organizations to apply AI to their work. At a high level, OpenAI currently supports AI applications in two ways: 1) Direct access through OpenAI products, like ChatGPT or Codex. These are tools people can use immediately for learning, work, creativity, and building. 2) Composable building blocks through APIs. These allow developers to integrate model intelligence into their own workflows, products, and systems. The sections below summarize the most common OpenAI products and what they’re designed for. ChatGPT is OpenAI’s main user-facing product—a…

Healthcare

Healthcare AI resources for clinical workflows and decision support. This page brings together practical examples of how AI can support day-to-day clinical work. Whether you’re exploring early use cases or supporting teams already deploying AI, these prompts and guides are designed to help you move forward with confidence. Clinicians spend significant time searching for evidence, reconciling guidelines, and documenting care—time that could be spent with patients. ChatGPT for Healthcare is a secure workspace built for hospital providers and designed for HIPAA-compliant use, providing cited answers from trusted medical sources. It can support tasks like drafting clinical documentation, preparing prior authorizations, and summarizing patient information—helping reduce administrative overhead and improve focus on care. The prompt templates below illustrate how clinicians can use ChatGPT for Healthcare in common workflows.

Our response to the Axios developer tool compromise

Our response to the Axios developer tool compromise We recently identified a security issue involving a third-party developer tool, Axios, that was part of a widely reported, broader industry incident(opens in a new window). Out of an abundance of caution we are taking steps to protect the process that certifies our macOS applications are legitimate OpenAI apps. We found no evidence that OpenAI user data was accessed, that our systems or intellectual property was compromised, or that our software was altered. We are updating our security certificates, which will require all macOS users to update their OpenAI apps to the latest versions. This helps prevent any risk—however unlikely—of someone attempting to distribute a fake app that appears to be from OpenAI. You can update safely through an in-app update or at the official links below: The security and privacy of…

AI fundamentals

AI fundamentals Understand the basics of AI, including what it is, how it works, and how it’s used. Welcome! If you’re new to AI, you don’t need a technical background to get started. What helps most is a simple map of the landscape—so you can understand what AI systems can do, how they’re packaged, and how to choose the right tool for your needs. Artificial intelligence (AI) is a broad category of software that can recognize patterns, learn from data, and produce useful outputs. You’ve probably seen AI show up in everyday moments, like when: - Your map app reroutes you around traffic - Your bank flags a purchase as “unusual” - A customer support chatbot answers common questions AI is a category—not one single tool. Within that category are models: trained systems that learn from data and then apply…

ChatGPT for sales teams

ChatGPT for sales teams Learn how sales teams use ChatGPT to build stronger pipeline and sell more effectively. ChatGPT helps sales teams move faster through the parts of selling that often slow them down—research, prep, follow-up, and deal coordination. It turns messy inputs like account notes, call takeaways, and CRM data into clear outputs such as briefs, emails, and plans. The result is more time for customer conversations and more consistency across outreach, discovery, and deal execution. - Speeds up account and meeting prep without missing the basics. Before a call, reps often pull context from multiple sources. ChatGPT can research accounts, synthesize internal context, highlight gaps, and produce a clear prep brief and follow-up plan. - Makes outreach and follow-up more consistent—and easier to personalize. Good sales writing is specific, concise, and relevant. ChatGPT can draft first-pass emails, call…

Using projects in ChatGPT

Using projects in ChatGPT Organize your work into dedicated spaces with shared context and history. Projects in ChatGPT are dedicated spaces for a specific body of work or area of focus. A project can hold chats, files, instructions, and related context in one place, so you do not need to restate the same background every time you start a new conversation. Projects are especially useful for work that continues over time. Instead of spreading materials across separate chats, you can keep everything together in one place and return to the same context when needed. On some plans, you can also invite other people to collaborate within a project. - Open Projects from the left-hand menu. - Create a new project and give it a name. - You can now add files, set project instructions, or move existing chats into the…

ChatGPT for marketing teams

ChatGPT for marketing teams Plan campaigns, create content, and analyze performance faster with ChatGPT. Marketing teams often use ChatGPT to move smoothly from idea to brief to assets to launch—and then back again to review what worked. It helps bring scattered inputs into one place, turn them into clear messaging, and draft strong first passes of campaign content. Teams can also generate variations for testing and quickly summarize performance data into practical next steps. The result is less time spent starting from scratch or rewriting drafts, and more time focused on strategy, creativity, and execution. - Helps you think more clearly, faster. ChatGPT can take a messy starting point—notes, half-formed ideas, or lots of context—and turn it into a clear direction and next steps. It’s useful at both the beginning of a project, when you’re brainstorming or outlining, and at…

Creating images with ChatGPT

Creating images with ChatGPT Generate and refine images using clear, descriptive prompts. ChatGPT can generate original images from plain-language prompts. You can iterate quickly—request variations, adjust composition or size, or explore new visual directions—and produce production-ready assets in minutes. This makes it easier to explore concepts, communicate ideas visually, and adapt existing assets for different audiences, formats, or channels. A good image prompt does not need to be long. In most cases, 1–3 clear sentences are enough. The goal is to help ChatGPT understand what the image is, how it should feel, and what it needs to accomplish. In practice, this means grounding the prompt in a few key details: the purpose of the image, the main subject, what is happening, where it takes place, and the desired visual style. If framing, lighting, or specific constraints matter, include those too.…

CyberAgent moves faster with ChatGPT Enterprise and Codex

CyberAgent moves faster with ChatGPT Enterprise and Codex CyberAgent uses ChatGPT Enterprise and Codex to help teams work faster, raise quality, and improve decisions across its businesses. Results 93% Monthly active usage of ChatGPT Enterprise CyberAgent is a Japanese internet company engaged in businesses such as internet advertising, media & IP, and gaming. Guided by its vision of “creating a company that represents the 21st century,” the company leverages its strengths in technology and creativity to generate new value both domestically and internationally. At CyberAgent, AI is positioned not as a set of limited advanced initiatives, but as a foundational technology that supports both business growth and operational design. The company has made continuous investments in this area. In 2016, it established “AI Lab” to conduct research and development of a wide range of AI technologies related to digital marketing.…

OpenAI Full Fan Mode Contest: Terms & Conditions

OpenAI Full Fan Mode Contest: Terms & Conditions NO PURCHASE IS NECESSARY TO PARTICIPATE OR WIN. YOUR ENTRY INTO THE FULL FAN MODE CONTEST (THE “CONTEST”) CONSTITUTES ACCEPTANCE OF THESE CONTEST TERMS AND CONDITIONS. THIS CONTEST IS NOT SPONSORED OR ENDORSED BY INSTAGRAM, THE IPL, BCCI, OR ANY FRANCHISE. This Full Fan Mode Contest (the “Contest”) is organized and run by OpenAI via @chatgptindia on Instagram, and will run during the IPL 2026 season. The Contest is a skill-based competition where eligible participants must use the Full Fan Mode section on ChatGPT to generate an image, share it as an Instagram story, and tag @chatgptindia. All submissions (a “Submission”) will be evaluated by judges in accordance with these Terms & Conditions, and winners will be selected based on creativity and relevance, and may be eligible for prizes. By entering the…

The next phase of enterprise AI

I just wrapped my first 90 days with OpenAI and have had the opportunity to meet with hundreds of our customers. What has struck me most is their immense sense of urgency and readiness. I’ve spent my entire career at the intersection of technology and enterprise transformation, and yet, I have never seen this level of conviction spread so quickly and consistently across industries. These leaders recognize AI as the most consequential shift of their lifetime, and they’re asking us how to reinvent their companies around it. I also saw that conviction reflected in our business this quarter. Building on our consumer strength, enterprise now makes up more than 40% of our revenue, and is on track to reach parity with consumer by the end of 2026. Codex just hit 3 million weekly active users, our APIs process more than…

Introducing the Child Safety Blueprint

Introducing the Child Safety Blueprint A framework for combatting and preventing AI-enabled Child Sexual Exploitation Child sexual exploitation is one of the most urgent challenges of the digital age. AI is rapidly changing both how these harms emerge across the industry and how they can be addressed at scale. At OpenAI, we have built and continue to strengthen safeguards to prevent misuse of our systems, and we work closely with partners like the National Center for Missing and Exploited Children (NCMEC) and law enforcement to improve detection and reporting. This work has helped surface where stronger, shared standards are needed across the industry. Today, we’re introducing a policy blueprint that outlines a practical path forward for strengthening U.S. child protection frameworks in the age of AI. This blueprint reflects and incorporates feedback from several leading organizations and experts across the…

Announcing the OpenAI Safety Fellowship

Introducing the OpenAI Safety Fellowship A pilot program to support independent safety and alignment research and develop the next generation of talent Today we are announcing a call for applications to the OpenAI Safety Fellowship, a new program for external researchers, engineers, and practitioners to pursue rigorous, high-impact research on the safety and alignment of advanced AI systems. The program will run from September 14, 2026 through February 5, 2027. We are looking for applicants interested in safety questions that matter for existing and future systems. Priority areas include safety evaluation, ethics, robustness, scalable mitigations, privacy-preserving safety methods, agentic oversight, and high-severity misuse domains, among others. We are especially interested in work that is empirically grounded, technically strong, and relevant to the broader research community. Fellows will work closely with OpenAI mentors and engage with a cohort of peers. Workspace…

Industrial policy for the Intelligence Age

Industrial policy for the Intelligence Age Ideas to keep people first. As we move toward superintelligence, incremental policy updates won’t be enough. To kick-start this much needed conversation, OpenAI is offering a slate of people-first policy ideas(opens in a new window) designed to expand opportunity, share prosperity, and build resilient institutions—ensuring that advanced AI benefits everyone. These ideas are ambitious, but intentionally early and exploratory. We offer them not as a comprehensive or final set of recommendations, but as a starting point for discussion that we invite others to build on, refine, challenge, or choose among through the democratic process. To help sustain momentum, OpenAI is: - welcoming and organizing feedback through newindustrialpolicy@openai.com - establishing a pilot program of fellowships and focused research grants of up to $100,000 and up to $1 million in API credits for work that builds…

OpenAI acquires TBPN

Fidji Simo shared this message with the company earlier today: I’m excited to share that we’ve acquired TBPN(opens in a new window). This acquisition brings a team with strong editorial instincts, deep audience understanding, and a proven ability to convene influential voices across tech, business, and culture. TBPN has built something pretty special. It’s one of the places where the conversation about AI and builders is actually happening day to day. A lot of you already watch it, and rely on it to stay close to what’s going on. As I've been thinking about the future of how we communicate at OpenAI, one thing that's become clear is that the standard communications playbook just doesn't apply to us. We're not a typical company. We're driving a really big technological shift. And with our mission to ensure artificial general intelligence benefits…

Codex now offers more flexible pricing for teams

We’re making it easier to just build things. Starting today, teams on ChatGPT Business and Enterprise can add Codex-only seats to their workspaces with pay-as-you-go pricing, giving full access to Codex without a fixed seat fee. Now, small groups can begin pilots, prove value in a few critical workflows, and easily expand from there. We’re also making Codex pricing easier to understand. Codex-only seats have no rate limits, and usage is billed on token consumption. This gives you a clearer view of how usage turns into spend and makes it easier to track costs across budgets, workflows, and teams. Teams that need broad ChatGPT access can continue using standard ChatGPT Business seats that do include Codex usage limits. To make that path more accessible, we’re lowering the annual price of ChatGPT Business from $25 to $20 per seat. The best…

Gradient Labs gives every bank customer an AI account manager

Gradient Labs gives every bank customer an AI account manager Gradient Labs uses GPT‑4.1 and GPT‑5.4 mini and nano to run complex financial support workflows with high accuracy and low latency. Results 10x Revenue growth Results 98% Customer satisfaction with AI agent experience Results +11% Higher accuracy with GPT-4.1 vs. next-best provider In banking, resolving a customer issue is rarely simple. Cases like fraud or blocked payments require strict adherence to complex procedures across multiple teams. When systems fall short, customers are passed between teams, wait in queues, and face delays at moments when the stakes are highest. Gradient Labs(opens in a new window) is built to handle this complexity. The London-based company is building AI agents that give every bank customer the experience of a dedicated account manager. Founded by a team that previously led AI and data efforts…

Accelerating the next phase of AI

OpenAI raises $122 billion to accelerate the next phase of AI Today, we closed our latest funding round with $122 billion in committed capital at a post money valuation of $852 billion. OpenAI is becoming the core infrastructure for AI, making it possible for people around the world and businesses, big and small, to just build things. The broad consumer reach of ChatGPT creates a powerful distribution channel into the workplace, where demand is rapidly shifting from basic model access to intelligent systems that reshape how businesses operate. Developers build on and expand the platform by leveraging our APIs, and Codex is transforming how developers turn ideas into working software. Durable access to compute is the strategic advantage that compounds across the entire system: it advances research, improves products, expands access, and structurally lowers the cost of delivery at scale.…

Helping disaster response teams turn AI into action across Asia

Helping disaster response teams turn AI into action across Asia First-of-its-kind AI workshop with the Gates Foundation, ADPC, and DataKind. Today in Bangkok, we’re bringing together 50 disaster management leaders from across Southeast and South Asia for our inaugural AI Jam for Disaster Management professionals, in partnership with the Gates Foundation, Asian Disaster Preparedness Center (APDC), and DataKind. The question guiding this initiative is simple, but urgent: How can AI help governments and nonprofits respond faster and more effectively when it matters most? Participants come from 13 countries—Bangladesh, India, Indonesia, Lao PDR, Malaysia, Myanmar, Nepal, Pakistan, Philippines, Sri Lanka, Thailand, Timor Leste, Vietnam—representing government agencies, multilateral organizations and non-profits. Many are directly involved in disaster response on the ground, coordinating information, supporting affected communities, and making time-critical decisions. This effort also builds on the expansion of our OpenAI for Countries…

STADLER reshapes knowledge work at a 230-year-old company

STADLER reshapes knowledge work at a 230-year-old company Embedding ChatGPT across 650 employees to turn hours of knowledge work into minutes—scaling speed, quality, and decision-making company-wide. Results 125+ Custom GPTs created Results 30-40% Time savings on common knowledge tasks Results 2.5x Faster time to first draft on average Results >85% Daily active usage From industrial legacy to digital leverage STADLER is a family-owned company with more than 230 years of history, specializing in automated waste sorting plants for the global recycling industry. With over 650 employees operating worldwide, the company plays a critical role in helping countries advance their sustainability and circular economy goals. Under the leadership of Co-CEO Julia Stadler, the company has taken a forward-looking approach to modernization—embedding AI into everyday work as a core productivity layer. Since 2023, STADLER has pursued a clear principle: every employee working…

Inside our approach to the Model Spec

Inside our approach to the Model Spec As AI systems become more capable and widely used, we need a clear public framework for how they should behave. At OpenAI, we believe AI should be fair, safe, and freely available so that more people can use it to solve hard problems, create opportunities, and benefit in areas like health, science, education, work, and everyday life. We believe that democratized access to AI is the best path forward: not AI whose benefits or control are concentrated in the hands of a few, but AI that more people can access, understand, and help shape. That is a core reason why the OpenAI Model Spec exists. The Model Spec(opens in a new window) is our formal framework for model behavior. It defines how we want models to follow instructions, resolve conflicts, respect user freedom,…

Introducing the OpenAI Safety Bug Bounty program

Today, OpenAI is launching a public Safety Bug Bounty(opens in a new window) program focused on identifying AI abuse and safety risks across our products. As AI technology rapidly evolves, so do the potential ways it can be misused. Our goal is to ensure our systems remain safe and secure against misuse or abuse that could lead to tangible harm. This new program will complement OpenAI’s Security Bug Bounty(opens in a new window) by accepting issues that pose meaningful abuse and safety risks, even if they don’t meet the criteria for a security vulnerability. Through this program, we look forward to continuing to partner with safety and security researchers to help us identify and address issues that fall outside conventional security vulnerabilities but still pose real risks. Submissions will be triaged by OpenAI’s Safety and Security Bug Bounty teams, and…

Helping developers build safer AI experiences for teens

Helping developers build safer AI experiences for teens Introducing a set of teen safety policies formatted as prompts for gpt-oss-safeguard Today, we’re releasing prompt-based safety policies(opens in a new window) to help developers create age-appropriate protections for teens. Built to work with our open-weight safety model, gpt-oss-safeguard(opens in a new window), these policies simplify how developers turn safety requirements into usable classifiers for real-world systems. We released open weight models to democratize access to powerful AI and support broad innovation. At the same time, we believe safety and innovation go hand in hand, and that developers should have access to capable models as well as the tools and policies to deploy them safely and responsibly. We developed these policies to support developers in their safety efforts to protect young users, with input from trusted external organizations including Common Sense Media(opens…

Update on the OpenAI Foundation

Update on the OpenAI Foundation A note from Bret Taylor, Chair of the Board of Directors of the OpenAI Foundation Last fall, OpenAI announced its recapitalization, paving the way for the OpenAI Foundation to access significant resources. Today, we’re sharing how the Foundation is starting to put that support to work. Our mission is to ensure artificial general intelligence benefits all of humanity. This is a multi-faceted endeavor. AI is already changing how people work, learn, and access care. It has the potential to unlock extraordinary benefits—faster medical breakthroughs, accelerated scientific discovery, more personalized services in healthcare and education, new tools for creativity and invention, higher productivity and economic growth, improved public services like transportation systems, and so much more. Our belief in this potential has guided OpenAI since its founding. But building powerful systems to benefit humanity is only…

Powering product discovery in ChatGPT

Powering Product Discovery in ChatGPT Launching richer, more visually immersive shopping experiences powered by the Agentic Commerce Protocol More and more, people are starting their shopping in ChatGPT—to explore, compare, and figure out what to buy. Shopping on the web is easy if you already know what you want. But when you’re still deciding, it often means jumping between tabs, reading the same “best of” lists, and trying to piece together the right answer. ChatGPT solves that: figuring out what to buy. You can describe what you’re looking for, refine it in a conversation, and quickly compare options that fit your specific needs. Today, we’re making that experience better with richer and more visual shopping in ChatGPT. You can now browse products visually, compare options side-by-side, and get detailed, up-to-date information—all in one place. What used to take hours of…

Creating with Sora Safely

Loading… The Sora 2 model and the Sora app offer state-of-the-art video generation with a new way to create together, and we’ve made sure safety is built in from the very start. Our approach is anchored in concrete protections: - Distinguishing AI content. Every video generated with Sora includes both visible and invisible provenance signals. All Sora videos also embed C2PA metadata—an industry-standard signature—and we maintain internal reverse-image and audio search tools that can trace videos back to Sora with high accuracy, building on successful systems from ChatGPT image generation and Sora 1. Many outputs also carry visible, dynamically moving watermarks which include the name of the creator. - Image-to-video with real person likeness. As we continue to strengthen Sora’s guardrails, we’re enabling more creative expression and connection, including letting people create videos from photos of family and friends. Users…

How we monitor internal coding agents for misalignment

How we monitor internal coding agents for misalignment Using our most powerful models to detect and study misaligned behavior in real-world deployments. AI systems are beginning to act with greater autonomy in real-world environments at scale. As their capabilities advance, they are able to take on increasingly complex, high-impact tasks and interact with tools, systems, and workflows in ways that resemble human collaborators. A core part of OpenAI’s mission is helping the world navigate this transition to AGI responsibly. That means not only building highly capable systems, but also developing the methods, infrastructure, and approaches needed to deploy and manage them safely as their capabilities continue to grow. Monitoring internally deployed agents is one of the key ways we’re doing this, and it allows us both to learn from real-world usage and to identify and mitigate emerging risks. Over the…

OpenAI to acquire Astral

OpenAI to acquire Astral Accelerates Codex growth to power the next generation of Python developer tools Today we’re announcing that OpenAI will acquire Astral(opens in a new window), bringing powerful open source developer tools into our Codex ecosystem. Astral has built some of the most widely used open source Python tools, helping developers move faster with modern tooling like uv, Ruff, and ty. These tools power millions of developer workflows and have become part of the foundation of modern Python development. As part of our developer-first philosophy, after closing OpenAI plans to support Astral’s open source products. By bringing Astral’s tooling and engineering expertise to OpenAI, we will accelerate our work on Codex and expand what AI can do across the software development lifecycle. Codex has already seen 3x user growth and 5x usage increase since the start of the…

OpenAI Japan announces Japan Teen Safety Blueprint to put teen safety first

OpenAI Japan announces Japan Teen Safety Blueprint to put teen safety first Strengthening age-appropriate protections, parental support, and well-being-centered design in Japan. OpenAI Japan today announced the Japan Teen Safety Blueprint, a new framework to help teens use generative AI safely and with confidence. In Japan, where a growing number of teens are already using generative AI for learning, creativity, and everyday tasks, this work is especially important. As the first generation grows up alongside AI, it is critical to ensure that these technologies are designed with their safety and well-being in mind from the outset. Generative AI is already supporting people across a wide range of activities from learning and creative expression to everyday tasks that help individuals thrive at school, at work, and in their personal lives. At a broader level, it also has the potential to accelerate…

Introducing GPT-5.4 mini and nano

Today we’re releasing GPT‑5.4 mini and nano, our most capable small models yet. They bring many of the strengths of GPT‑5.4 to faster, more efficient models designed for high-volume workloads. GPT‑5.4 mini significantly improves over GPT‑5 mini across coding, reasoning, multimodal understanding, and tool use, while running more than 2x faster. It also approaches the performance of the larger GPT‑5.4 model on several evaluations, including SWE-Bench Pro and OSWorld-Verified. GPT‑5.4 nano is the smallest, cheapest version of GPT‑5.4 for tasks where speed and cost matter most. It is also a significant upgrade over GPT‑5 nano. We recommend it for classification, data extraction, ranking, and coding subagents that handle simpler supporting tasks. These models are built for the kinds of workloads where latency directly shapes the product experience: coding assistants that need to feel responsive, subagents that quickly complete supporting tasks,…

Equipping workers with insights about compensation

Equipping workers with insights about compensation Americans are sending nearly 3 million messages to ChatGPT each day to help them close the wage information gap. Wage information shapes important decisions: what jobs people apply for, whether they negotiate, and whether a particular career path is worth pursuing. But unlike the price of most goods, the price of labor is often hard to find and difficult to interpret—especially for workers who are early in their careers, switching fields, or moving locations. AI is a new type of labor-market resource. Rather than requiring a worker to search across multiple websites, interpret scattered salary pages, or ask a socially risky question, a model can synthesize wage information and return a benchmark in seconds. Workers are already using ChatGPT this way, sending nearly 3 million messages per day, on average in the US, asking…

Why Codex Security Doesn’t Include a SAST Report

For decades, static application security testing (SAST) has been one of the most effective ways security teams scale code review. But when we built Codex Security, we made a deliberate design choice: we didn’t start by importing a static analysis report and asking the agent to triage it. We designed the system to start with the repository itself—its architecture, trust boundaries, and intended behavior—and to validate what it finds before it asks a human to spend time on it. The reason is simple: the hardest vulnerabilities usually aren’t dataflow problems. They happen when code appears to enforce a security check, but that check doesn’t actually guarantee the property the system relies on. In other words, the challenge isn’t just tracking how data moves through a program—it’s determining whether the defenses in the code really work. SAST is often framed as…

Designing AI agents to resist prompt injection

Designing AI agents to resist prompt injection What social engineering teaches us about securing AI agents. AI agents are increasingly able to browse the web, retrieve information, and take actions on a user’s behalf. Those capabilities are useful, but they also create new ways for attackers to try to manipulate the system. These attacks are often described as prompt injection: instructions placed in external content in an attempt to make the model do something the user did not ask for. In our experience, the most effective real-world versions of these attacks increasingly resemble social engineering more than simple prompt overrides. That shift matters. If the problem is not just identifying a malicious string, but resisting misleading or manipulative content in context, then defending against it cannot rely only on filtering inputs. It also requires designing the system so that the…

From model to agent: Equipping the Responses API with a computer environment

From model to agent: Equipping the Responses API with a computer environment By Bo Xu, Danny Zhang, and Rohit Arunachalam We're currently in a shift from using models, which excel at particular tasks, to using agents capable of handling complex workflows. By prompting models, you can only access trained intelligence. However, giving the model a computer environment can achieve a much wider range of use cases, like running services, requesting data from APIs, or generating more useful artifacts like spreadsheets or reports. A few practical problems emerge when you try to build agents: where to put intermediate files, how to avoid pasting large tables into a prompt, how to give the workflow network access without creating a security headache, and how to handle timeouts and retries without building a workflow system yourself. Instead of putting it on developers to build…

Wayfair boosts catalog accuracy and support speed with OpenAI

Wayfair boosts catalog accuracy and support speed with OpenAI By embedding OpenAI models in supplier and catalog systems, Wayfair improved data accuracy and automated workflows for millions of products. Results 2.5M Product tags corrected Results 41K Supplier support tickets automated per month Results 1,200 ChatGPT Enterprise seats deployed Wayfair, one of the world’s largest home goods retailers, has integrated OpenAI models into critical internal systems to improve supplier support workflows and product catalog quality at scale. What began as value-testing small scale releases in 2024 has evolved into a full production system that reduces manual effort, accelerates decision-making and improves data quality across millions of products. Rather than treat generative AI as an experiment or point solution, Wayfair embedded OpenAI models into core operational workflows. The company focused first where complexity and need for scale were highest: routing and resolving…

Rakuten fixes issues twice as fast with Codex

Results 50% Reduction in MTTR Results 3-4x Faster potential build time for projects - from quarters to weeks Rakuten(opens in a new window) is a global innovation company operating across e-commerce, fintech, and mobile communications, serving both consumers and merchants at massive scale. With 30,000 employees worldwide, its engineering teams ship across a large, complex product ecosystem where both speed and reliability are essential. That’s why Yusuke Kaji, General Manager of AI for Business at Rakuten, has spent the past year pushing agentic workflows deeper into how teams plan, build, and validate software. Codex—the coding agent from OpenAI—has become a core part of Rakuten’s engineering stack, especially where the company needs to move faster without compromising security. Over the past year, Rakuten engineers have used Codex across operations and software delivery to compress incident response (including a ~50% reduction in…

Improving instruction hierarchy in frontier LLMs

Improving instruction hierarchy in frontier LLMs Introducing IH-Challenge, a training dataset that strengthens instruction hierarchy, safety steerability, and prompt injection robustness. AI systems often receive instructions from multiple sources. These can include safety policies from system messages, product guidance from developers, requests from users, and information found online. Training models to reliably prioritize the most trusted instructions among these sources is a key part of safe deployment. Many AI safety and reliability issues can arise when this prioritization breaks down. Models may receive requests for disallowed content, attempts to reveal private information, or prompt‑injection attacks embedded in online data. Failing to behave appropriately in each of these scenarios shares the same root cause: the model may follow the wrong instruction. When these instructions conflict, the model has to decide which ones to prioritize. If it treats an untrusted instruction as…

New ways to learn math and science in ChatGPT

New ways to learn math and science in ChatGPT Explore concepts with interactive visual explanations. ChatGPT has quickly become one of the most widely used tools for learning. Each week, 140 million people use ChatGPT to help them understand math and science concepts alone. People also come to ChatGPT to explore new topics, work through homework problems, prepare for exams, and break down concepts they’ve always found difficult. For many learners, math and science concepts feel abstract and hard to understand. In a recent Gallup(opens in a new window) survey, more than half of U.S. adults said they struggle with math, and many parents reported they don’t feel confident helping their children learn it. Today, we’re making learning these concepts in ChatGPT even more interactive with new dynamic visual explanations. Starting with more than 70 core math and science concepts,…

OpenAI to acquire Promptfoo

OpenAI to acquire Promptfoo Accelerating agentic security testing and evaluation capabilities in OpenAI Frontier We’re acquiring Promptfoo, an AI security platform that helps enterprises identify and remediate vulnerabilities in AI systems during development. Once the acquisition is finalized we will integrate Promptfoo’s technology directly into OpenAI Frontier, our platform for building and operating AI coworkers. As enterprises deploy AI coworkers into real workflows, evaluation, security, and compliance become foundational requirements. Enterprises need systematic ways to test agent behavior, detect risks before deployment, and maintain clear records to support oversight, governance, and accountability over time. The Promptfoo team, led by Ian Webster and Michael D’Angelo, has built a powerful suite of tools trusted by over 25 percent of Fortune 500 companies, along with a widely used open-source(opens in a new window) CLI and library for evaluating and red-teaming LLM applications. Together,…

Codex Security: now in research preview

Today we’re introducing Codex Security, our application security agent. It builds deep context about your project to identify complex vulnerabilities that other agentic tools miss, surfacing higher-confidence findings with fixes that meaningfully improve the security of your system while sparing you from the noise of insignificant bugs. Context is essential when evaluating real security risks, but most AI security tools simply flag low-impact findings and false positives, forcing security teams to spend significant time on triage. At the same time, agents are accelerating software development, making security review an increasingly critical bottleneck. Codex Security addresses both challenges. By combining agentic reasoning from our frontier models with automated validation, it delivers high-confidence findings and actionable fixes so teams can focus on the vulnerabilities that matter and ship secure code faster. Formerly known as Aardvark, Codex Security began last year as a…

How Balyasny Asset Management built an AI research engine

How Balyasny Asset Management built an AI research engine By combining rigorous model evaluation, full-platform use of OpenAI, and agent workflows, Balyasny is reinventing investment research. Results 95% Portion of investment team using the AI research system Results Days to hours With agents powered by OpenAI models, deep research tasks that once required days are now completed in hours Balyasny Asset Management(opens in a new window) (Balyasny) is a global, multi-strategy investment firm with approximately 180 investment teams across diverse asset classes and geographies. The firm operates in a highly competitive and dynamic industry where conviction, precision, and speed are all critical to success. Facing an increasingly complex market environment with surging volumes of financial data, Balyasny saw an opportunity to reimagine the investment research process using AI. In late 2022, Balyasny established an Applied AI team: a centralized group…

How Descript engineers multilingual video dubbing at scale

How Descript engineers multilingual video dubbing at scale Using OpenAI reasoning models, Descript unlocked automatic localization of large content libraries without losing timing or meaning. Results 43 Percentage point improvement in duration adherence with OpenAI Results 15% Increase in dubbed exports post-rollout Descript(opens in a new window) is an AI-native video editor built around a simple idea: if you can edit text, you should be able to edit video. Since Descript’s early days, AI has powered every aspect of the product: transcription, editing, audio cleanup, and increasingly complex creative workflows. They’ve built on OpenAI for years, using Whisper for transcription and GPT series models inside their co-editor Underlord. Translation quickly emerged as a high-impact use case. Traditionally, translating video has been slow and expensive, requiring language experts to manage projects, produce rote translations, handle quality control, and generate corresponding audio.…

Reasoning models struggle to control their chains of thought, and that’s good

Reasoning models struggle to control their chains of thought, and that’s good Why a limitation of frontier models is reassuring for AI safety. As AI agents become capable of carrying out increasingly complex and autonomous tasks, maintaining reliable oversight of their behavior becomes more important. Consistent with our principle of iterative deployment, we study how systems behave in real-world settings and continuously refine safeguards as capabilities advance. To support this, our safety approach uses defense-in-depth, with multiple complementary layers of defense such as safety training, behavioral testing, agentic code review(opens in a new window), and chain-of-thought (CoT) monitoring. CoT monitoring analyzes the reasoning steps agents generate while pursuing tasks. These reasoning traces can provide valuable signals during both training and deployment, helping monitoring systems identify when an agent’s behavior may be unsafe or inconsistent with the user’s intended goals. Today,…

GPT-5.4 Thinking System Card

GPT‑5.4 Thinking is the latest reasoning model in the GPT‑5 series, and explained in our blog. The comprehensive safety mitigation approach for this model is similar to previous models in this series, but 5.4 Thinking is the first general purpose model to have implemented mitigations for High capability in Cybersecurity. The approach to cyber safety builds on the latest approaches implemented for GPT‑5.3 Codex, in ChatGPT and the API. In this card we also refer to GPT‑5.4 Thinking as gpt-5.4-thinking. Note that there is not a model named GPT‑5.3 Thinking, so the main model to baseline against is GPT‑5.2 Thinking. Author OpenAI

Introducing GPT-5.4

Today, we’re releasing GPT‑5.4 in ChatGPT (as GPT‑5.4 Thinking), the API, and Codex. It’s our most capable and efficient frontier model for professional work. We’re also releasing GPT‑5.4 Pro in ChatGPT and the API, for people who want maximum performance on complex tasks. GPT‑5.4 brings together the best of our recent advances in reasoning, coding, and agentic workflows into a single frontier model. It incorporates the industry-leading coding capabilities of GPT‑5.3‑Codex while improving how the model works across tools, software environments, and professional tasks involving spreadsheets, presentations, and documents. The result is a model that gets complex real work done accurately, effectively, and efficiently—delivering what you asked for with less back and forth. In ChatGPT, GPT‑5.4 Thinking can now provide an upfront plan of its thinking, so you can adjust course mid-response while it’s working, and arrive at a final…

Ensuring AI use in education leads to opportunity

Ensuring AI use in education leads to opportunity Our latest tools and resources can help educational institutions close AI capability gaps. Of the 900 million people who use ChatGPT each week, college-age adults are the biggest adopters among age groups. How they learn to use AI will increasingly shape their future opportunities, and education systems are uniquely positioned to help. Much of modern education was built to help students get ready for existing systems of work. But those systems are changing fast. Studies(opens in a new window) predict nearly 40% of the core skills workers rely on will change, largely because of AI. To thrive in this Intelligence Age, students need to build agency: the ability to learn continuously, solve hard problems, and create new economic opportunities for themselves with AI. Agency does not emerge from basic AI use alone.…

Introducing ChatGPT for Excel and new financial data integrations

Introducing ChatGPT for Excel and new financial data integrations Use ChatGPT in Excel to build, update, and analyze spreadsheets faster, and new integrations in ChatGPT for financial workflows. Update on April 22, 2026: ChatGPT for Google Sheets is now available in beta, bringing ChatGPT into Google Sheets so users can build, analyze, and update spreadsheets using natural language. We've also added support for app integrations and skills for both ChatGPT for Excel and ChatGPT for Google Sheets. Learn more(opens in a new window). Today, we’re introducing ChatGPT for Excel(opens in a new window) in beta, an Excel add-in that brings ChatGPT directly into workbooks to help build and update models, run scenarios, and generate outputs based on cells and formulas. Powered by GPT‑5.4, it helps users do more in Excel, supports power users in moving faster, and can improve consistency…

The five AI value models driving business reinvention

The five AI value models driving business reinvention Most organizations still manage AI as a series of use cases: a pilot here, a workflow there, a promising tool inside one function. That approach can generate local wins but it rarely transforms how a business creates value. It is akin to creating interactive banners and drip email campaigns with the arrival of the internet, and missing the point of the eCommerce revolution. The organizations pulling ahead use a different, and more ambitious logic. They treat AI not as a collection of disconnected experiments, but as a portfolio of value models. Each has its own economics, time-to-value, and governance requirements, and each makes the next one easier to scale. This is why the companies that get the most from AI will not be the ones running the most pilots. They will be…

Introducing the Adoption news channel

Introducing the Adoption news channel Practical insights and frameworks to turn AI progress into business advantage A new phase of enterprise AI is underway. For the past two years, the story was largely about the pace of the technology: new models, new capabilities, new breakthroughs and demonstrations of what AI could do. That phase mattered. But it also created an information environment dominated by technical updates, product news, and benchmark performances which are not the bottleneck to adoption and value anymore. The defining question for leaders is no longer what AI can do but how to turn that capability into concrete operational change: better decisions, faster workflows, stronger execution, new forms of leverage, and ultimately new business models. That shift calls for a different kind of channel. That is why we are launching the Adoption channel, a new OpenAI business…

VfL Wolfsburg turns ChatGPT into a club-wide capability

VfL Wolfsburg turns ChatGPT into a club-wide capability By focusing on people, not pilots, the Bundesliga club is scaling efficiency, creativity, and knowledge—without losing its football identity. Results 50+ Custom GPTs in active daily use Results 1M+ Annual cost savings through reduced reliance on external agencies At VfL Wolfsburg, football is built on discipline, continuity, and trust. For nearly three decades, the club has been a constant presence in the Bundesliga—backed by strong men’s and women’s teams, a future-oriented academy, and a fast-evolving digital and commercial ecosystem. But modern football is no longer defined by performance on the pitch alone. Expectations from fans, partners, and internal stakeholders continue to rise—while budgets and headcount cannot scale indefinitely. This tension between growing expectations and limited scalability created a clear need for new ways of working. The question was how to apply it…

Extending single-minus amplitudes to gravitons

Extending single-minus amplitudes to gravitons Researchers used GPT‑5.2 Pro to help find a new mathematical result describing how particles can interact in quantum gravity. We’ve published a new preprint studying scattering amplitudes in quantum gravity, extending recent results obtained for gluons to the gravitational setting. The work shows that a class of graviton interactions long assumed to vanish can in fact arise under well-defined kinematic conditions. The preprint is available here(opens in a new window). We welcome feedback from the community. The paper, “Single-minus graviton tree amplitudes are nonzero,” is authored by Alfredo Guevara (Institute for Advanced Study), Alexandru Lupsasca (Vanderbilt University and OpenAI), David Skinner (University of Cambridge), Andrew Strominger (Harvard University), and Kevin Weil (OpenAI) on behalf of OpenAI. Scattering amplitudes are mathematical quantities physicists use to calculate the probability that particles interact in particular ways. Rather than…

Understanding AI and learning outcomes

New tools for understanding AI and learning outcomes Advancing how AI’s impact is measured across learning environments Education is one of AI’s most promising frontiers. With tools like ChatGPT, personalized learning support can be available to any student, anywhere, at any time. But the education sector is still early in its understanding of the impact of AI on learning outcomes. Last year, our team set out to study the use of tools like study mode and found promising gains in student performance. But our research also raised an important question: how can we assess how AI influences a learner's progress over time, not just on a final exam? This is a broader ecosystem challenge. To-date, most research methods focus on narrow performance signals—such as test scores—and lack the ability to assess how students actually learn with AI in real-world settings,…

How Axios uses AI to help deliver high-impact local journalism

How Axios uses AI to help deliver high-impact local journalism A conversation with Allison Murphy, Chief Operating Officer, Axios. Axios is a media company delivering vital, trustworthy news and analysis in the most efficient, illuminating and shareable ways possible. It offers a mix of original and smartly narrated coverage of media trends, tech, business and politics with expertise, voice and smart brevity. We spoke with Allison Murphy, Chief Operating Officer at Axios, about AI supporting high-impact local journalism and serving communities better. AI is already a huge part of how Axios Local works. At the core, what we’re trying to do is prove that you can run a sustainable, profitable local news model that delivers high-quality journalism to every community in America. That means solving for scale and efficiency—and that’s exactly what AI is good at. So there’s a really…

GPT-5.3 Instant: Smoother, more useful everyday conversations

Today, we’re releasing an update to ChatGPT’s most-used model that makes everyday conversations more consistently helpful and fluid. GPT‑5.3 Instant delivers more accurate answers, richer and better-contextualized results when searching the web, and reduces unnecessary dead ends, caveats, and overly declarative phrasing that can interrupt the flow of conversation. This update focuses on the parts of the ChatGPT experience people feel every day: tone, relevance, and conversational flow. These are nuanced problems that don’t always show up in benchmarks, but shape whether ChatGPT feels helpful or frustrating. GPT‑5.3 Instant directly reflects user feedback in these areas. We heard feedback that GPT‑5.2 Instant would sometimes refuse questions it should be able to answer safely, or respond in ways that feel overly cautious or preachy, particularly around sensitive topics. GPT‑5.3 Instant significantly reduces unnecessary refusals, while toning down overly defensive or moralizing…

GPT-5.3 Instant System Card

GPT‑5.3 Instant is the newest addition to the GPT‑5 series. As described in our blog, GPT‑5.3 Instant responds faster, delivers richer and better-contextualized answers when searching the web, and reduces unnecessary dead ends, caveats, and overly declarative phrasing that can interrupt the flow of conversation. The comprehensive safety mitigation approach for this model is largely the same as that described for GPT‑5.2 Instant in the GPT‑5.2 System Card. In this card we also refer to GPT‑5.3 Instant as gpt-5.3-instant. Author OpenAI

Our agreement with the Department of War

Our agreement with the Department of War Update on March 2, 2026 Throughout our discussions, the Department made clear it shares our commitment to ensuring our tools will not be used for domestic surveillance. To make our principles as clear as possible, we worked together to add additional language to our agreement. This language makes explicit that our tools will not be used to conduct domestic surveillance of U.S. persons, including through the procurement or use of commercially acquired personal or identifiable information. The Department also affirmed that our services will not be used by Department of War intelligence agencies like the NSA. Any services to those agencies would require a new agreement. The new language reads: - Consistent with applicable laws, including the Fourth Amendment to the United States Constitution, National Security Act of 1947, FISA Act of 1978,…

Joint Statement from OpenAI and Microsoft

Joint Statement from OpenAI and Microsoft Since 2019, Microsoft and OpenAI have worked together to advance artificial intelligence responsibly and make its benefits broadly accessible. What began as a research partnership has grown into one of the most consequential collaborations in technology—grounded in mutual trust, deep technical integration, and a long‑term commitment to innovation. As conversations around AI investments and partnerships grow and as OpenAI announces new funding and new partners as they did today, we want to ensure these announcements are understood within the existing construct of our partnership. Nothing about today’s announcements in any way changes the terms of the Microsoft and OpenAI relationship that have been previously shared in our joint blog in October 2025. The partnership remains strong and central. Microsoft and OpenAI continue to work closely across research, engineering, and product development, building on years…

Introducing the Stateful Runtime Environment for Agents in Amazon Bedrock

Introducing the Stateful Runtime Environment for Agents in Amazon Bedrock AI agents excel at reasoning. The harder part is operational: running multi-step work reliably over time, across real tools and real systems, with the right controls. Today, we’re making this easier for customers through a partnership and joint collaboration with Amazon to deliver the new Stateful Runtime Environment that runs natively in Amazon Bedrock. AWS customers will have access to the Runtime Environment, powered by OpenAI models, optimized for AWS infrastructure and tailored for agentic workflows, with the state, reliability, and governance needed for production work. A lot of agent prototypes based on stateless APIs tackle simple use cases: one prompt, one answer, maybe one tool call. Production work is different. Real workflows unfold across many steps, require context from previous actions, depend on multiple tool outputs, approvals, and system…