{"id":24337,"date":"2026-11-19T09:41:36","date_gmt":"2026-11-19T09:41:36","guid":{"rendered":"https:\/\/dianapps.com\/blog\/?p=24337"},"modified":"2026-11-19T09:47:41","modified_gmt":"2026-11-19T09:47:41","slug":"how-to-build-ai-agents-with-openai","status":"publish","type":"post","link":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/","title":{"rendered":"How to build AI agents with OpenAI? Agents SDK and AgentKit"},"content":{"rendered":"<p><b>Key Takeaways<\/b><span style=\"font-weight: 400;\">:\u00a0<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">OpenAI\u2019s Agents SDK supports code-first agent development in Python and TypeScript.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Agent Builder is scheduled to shut down on November 30, 2026, making migration essential for existing users.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Use tools, handoffs and guardrails to build reliable agents with controlled actions.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Deploy agents as regular services with external session storage, queues and observability.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Replace hosted Evals with custom datasets, automated graders and regression testing.<\/span><\/li>\n<\/ul>\n<p><b>Quick Answer<\/b><span style=\"font-weight: 400;\">: Build AI agents with OpenAI using the Agents SDK in Python or TypeScript. Define a focused agent with instructions and tools, add handoffs for specialized tasks, and implement input\/output guardrails before deployment. Run the agent as a regular backend service using containers or serverless infrastructure, with external session storage, background queues and tracing. For existing Agent Builder workflows, export the code and migrate to the SDK before the November 30, 2026 shutdown.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><\/p>\n<p><span style=\"font-weight: 400;\">If you searched for how to build AI agents with OpenAI this month, you\u2019ve landed at an awkward moment, because the answer changed in June and most tutorials haven\u2019t caught up. Agent Builder, the visual canvas inside AgentKit, shuts down on November 30, 2026, and OpenAI is pointing everyone toward the code first Agents SDK instead.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Our AI development services team has shipped agents on the SDK since it appeared and migrated a few off Agent Builder since the announcement, so what follows is grounded in work rather than launch day press. You\u2019ll get an explanation of what an agent is, how the SDK is put together, what\u2019s left of AgentKit, and a deployment path that holds up once real users arrive.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">What Counts As An AI Agent, And What Doesn\u2019t?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Before building anything, it helps to be strict about the word, since \u201cagent\u201d gets attached to everything from an autocomplete feature to a fully autonomous system. An agent, in the sense the Agents SDK means it, is a model given instructions, a set of tools it can call and the freedom to decide which tool to use and when.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">That decision making loop is the difference. A chatbot answers, an agent acts, checks the result and decides what to do next, sometimes handing the task to another agent entirely. The distinction matters for scoping, because a lot of what clients ask us to build turns out to be a very good copilot rather than an agent, and that\u2019s fine, it\u2019s just a different architecture. If you\u2019re unsure which one you actually need,<\/span><a href=\"https:\/\/dianapps.com\/blog\/ai-copilot-vs-ai-agent\/\"> <span style=\"font-weight: 400;\">AI copilot vs AI agent<\/span><\/a><span style=\"font-weight: 400;\"> draws the line in detail, and it\u2019s worth reading before you commit to a framework.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">What Is The OpenAI Agents SDK?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">The OpenAI Agents SDK is a lightweight framework for building agents on top of the Responses API, released in March 2025 and now the centerpiece of how OpenAI expects agents to be built. It\u2019s deliberately small, which we consider a feature rather than a limitation.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Agents:<\/b><span style=\"font-weight: 400;\"> A model, a set of instructions and a list of tools, defined in a few lines of code.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Tools:<\/b><span style=\"font-weight: 400;\"> Any Python or TypeScript function becomes a tool with a decorator, plus hosted tools like file search and web search.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Handoffs:<\/b><span style=\"font-weight: 400;\"> One agent can delegate to another, which is how you build triage flows and specialist agents.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Guardrails:<\/b><span style=\"font-weight: 400;\"> Input and output checks that run alongside the agent and can stop a run before damage is done.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Sessions and tracing:<\/b><span style=\"font-weight: 400;\"> Conversation memory is built in, and every run produces a trace you can inspect.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">That\u2019s nearly the whole conceptual surface, and the small size is why teams who dislike heavy orchestration frameworks tend to settle on it.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">What Is AgentKit, And What\u2019s Left Of It?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">AgentKit arrived at DevDay in October 2025 as a bundle rather than a single product, and understanding the bundle explains the current confusion. It contained Agent Builder, a visual canvas for composing multi agent workflows with nodes, a Connector Registry for admins to manage data sources, ChatKit for embedding chat interfaces, and an expanded Evals platform with trace grading and automated prompt optimization. Guardrails, an open source safety layer, could be dropped into Agent Builder flows as a node.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Then on June 3, 2026, OpenAI announced it was winding down Agent Builder and Evals, with evals going read only at the end of October and both products disappearing on November 30, 2026. ChatKit survives, and so does the Connector Registry for enterprise accounts. So when people say \u201cAgentKit\u201d today they usually mean the pieces that remain, and when they say \u201cAgent Builder\u201d they\u2019re describing something with thirteen days left. We\u2019d rather you learn that from us than from a dead link.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">How To Get Started With Agent Builder, And Why You Shouldn\u2019t Now?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">People still search for how to get started with Agent Builder, and the honest answer in November 2026 is that you shouldn\u2019t start, you should finish. If you already have workflows there, this is the checklist we\u2019ve used on migrations.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Export Every Workflow As Code:<\/b><span style=\"font-weight: 400;\"> Open each one in Agent Builder, select Code and copy the Agents SDK export before the shutdown.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Record The Configuration:<\/b><span style=\"font-weight: 400;\"> Write down each agent\u2019s instructions, model and tools, plus the typed inputs and outputs passing between nodes.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Copy Your Eval Datasets:<\/b><span style=\"font-weight: 400;\"> Evals are already read only, so pull the datasets and grader results out while the dashboard still loads.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Check ChatKit References:<\/b><span style=\"font-weight: 400;\"> A ChatKit interface pointing at an Agent Builder workflow by ID will outlive the workflow it points to.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Pick The Destination:<\/b><span style=\"font-weight: 400;\"> Code heavy logic goes to the Agents SDK, and natural language tasks may fit ChatGPT Workspace Agents instead.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">If you have nothing there yet, skip the canvas entirely and go straight to the SDK, where the rest of this guide lives.<\/span><\/p>\n<div style=\"background: #EEF2FE; border: 1px solid #DBE2FB; border-radius: 14px; padding: 28px 32px; margin: 38px 0;\">\n<p style=\"color: #1b3fae; font-size: 22px; line-height: 1.3; font-weight: bold; margin: 0 0 10px;\"><span style=\"font-weight: 400;\">Still running something in Agent Builder?<\/span><\/p>\n<p style=\"color: #4b5563; font-size: 16px; line-height: 1.6; margin: 0 0 22px;\"><span style=\"font-weight: 400;\">We\u2019ll migrate it to the Agents SDK before the deadline.<\/span><\/p>\n<p><a style=\"display: inline-block; background: #2563EB; color: #ffffff; text-decoration: none; font-size: 15px; font-weight: 600; padding: 13px 26px; border-radius: 8px;\" href=\"https:\/\/dianapps.com\/contact\">Talk To An AI Expert<\/a><\/p>\n<\/div>\n<h2><span style=\"font-weight: 400;\">Building Production Ready AI Agents With OpenAI: The Steps That Matter<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Building production ready AI agents with OpenAI looks very different from building a demo, and most of the difference sits outside the agent code. We\u2019ve found the sequence below holds up across support, operations and sales use cases.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Define The Job Narrowly:<\/b><span style=\"font-weight: 400;\"> One clear outcome per agent, because agents asked to do everything reliably do nothing well.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Write Tools Before Prompts:<\/b><span style=\"font-weight: 400;\"> Tools fix what the agent can actually do, and the instructions then explain when to use them.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Add Handoffs For Specialization:<\/b><span style=\"font-weight: 400;\"> A triage agent routing to specialists beats one giant prompt every time we\u2019ve measured it.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Put Guardrails On Both Ends:<\/b><span style=\"font-weight: 400;\"> Validate inputs for injection and outputs for leakage before anything reaches a user or a database.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Trace From Day One:<\/b><span style=\"font-weight: 400;\"> The SDK traces every run, and reading traces early teaches you where the agent goes wrong.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Build Your Own Eval Loop:<\/b><span style=\"font-weight: 400;\"> Golden datasets and automated graders in your repo, since the hosted version is leaving.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">None of these steps are glamorous, and all of them are what separates the agents still running next year from the ones quietly switched off.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">Which Tools Should Your Agent Actually Have?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Tool selection decides more about an agent\u2019s reliability than model choice does, which surprises people who expect the model to be the hard part. Give an agent too many tools and it dithers or picks wrong, give it too few and it hallucinates the capability it lacks. The SDK makes any function a tool, which is convenient and also dangerous, because a database write tool is one decorator away from an agent that can corrupt records.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">We keep tools small, idempotent where possible and named for exactly what they do, and we gate anything destructive behind a human approval step. Hosted tools cover file search, web search and code execution without you building them. The most common mistake we see is treating a content generation workflow as if it needs agentic autonomy when it needs a good writing tool and a review step.<\/span><a href=\"https:\/\/dianapps.com\/blog\/ai-writing-software-vs-autonomous-ai-agent\/\"> <span style=\"font-weight: 400;\">AI writing software vs autonomous AI agent<\/span><\/a><span style=\"font-weight: 400;\"> is where we unpack that confusion, because it costs teams months.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">Guardrails And Security For OpenAI Agents<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Guardrails are the part of OpenAI agent development that everyone agrees matters and most teams implement last, usually after an incident. The SDK runs guardrails as parallel checks on inputs and outputs, and the open source Guardrails library gives you detectors for personal data, jailbreak attempts and hallucination patterns.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Input Guardrails:<\/b><span style=\"font-weight: 400;\"> Catch prompt injection and off topic requests before the agent spends tokens or calls a tool.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Output Guardrails:<\/b><span style=\"font-weight: 400;\"> Scan responses for leaked personal data, policy violations or confident nonsense before they reach anyone.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Tool Level Permissions:<\/b><span style=\"font-weight: 400;\"> Scope credentials per tool so a compromised agent can\u2019t reach systems it was never meant to.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Human Approval Nodes:<\/b><span style=\"font-weight: 400;\"> Any irreversible action, payments, deletions, external emails, waits for a person to confirm.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Rate And Cost Limits:<\/b><span style=\"font-weight: 400;\"> Cap tokens and tool calls per run, because a looping agent is an expensive agent.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Security teams increasingly build their own agents to watch for exactly these failures, and<\/span><a href=\"https:\/\/dianapps.com\/blog\/ai-agents-for-cybersecurity\/\"> <span style=\"font-weight: 400;\">AI agents for cybersecurity<\/span><\/a><span style=\"font-weight: 400;\"> covers how that defensive use is taking shape.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">How Are You Deploying OpenAI Agents SDK To Production?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">This is the question we hear most from engineering leads, phrased almost exactly that way, and the answer is reassuringly boring. The Agents SDK is a library, not a hosted runtime, so your agent is an ordinary service that you deploy wherever you deploy services today.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">A Python agent runs happily inside a FastAPI app on a container, a TypeScript agent sits in a Node service or an edge worker, and the SDK doesn\u2019t care which cloud is underneath. The things you do have to decide are where session state lives, how you handle long running runs that exceed a request timeout, and how traces get shipped to whatever observability stack you already trust.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">We generally put session storage in a managed database, run agents as background jobs with a queue for anything over thirty seconds, and forward traces to the same place as application logs. If you need a chat surface, ChatKit embeds in your frontend and talks to your backend, which saves rebuilding streaming and thread management yourself.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">OpenAI Agent Deployment Options Compared<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">The table below lays out the hosting choices we\u2019ve actually used for deploying OpenAI Agents SDK to production, with the tradeoffs stated plainly. None is universally right, and your existing platform team\u2019s preferences should weigh heavily.<\/span><\/p>\n<table>\n<tbody>\n<tr>\n<td><b>Deployment option<\/b><\/td>\n<td><b>Best for<\/b><\/td>\n<td><b>Session state<\/b><\/td>\n<td><b>Long runs<\/b><\/td>\n<td><b>Main tradeoff<\/b><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Container on Kubernetes or ECS<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Teams with existing platform tooling<\/span><\/td>\n<td><span style=\"font-weight: 400;\">External database<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Background workers with a queue<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Operational overhead you may already carry<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Serverless functions<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Bursty, short agent tasks<\/span><\/td>\n<td><span style=\"font-weight: 400;\">External store, nothing local<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Awkward beyond timeout limits<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Cold starts and run length ceilings<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Edge workers (TypeScript)<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Low latency chat agents near users<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Durable objects or external store<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Limited, offload heavy work<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Restricted runtime and library support<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Managed app platform (Render, Fly, Railway)<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Small teams moving fast<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Managed Postgres or Redis<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Worker processes<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Less control at scale<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Agent Builder hosted endpoint<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Nothing new, shutting down November 30<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Hosted by OpenAI<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Hosted<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Gone in two weeks<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><span style=\"font-weight: 400;\">For most clients with a modest platform team, containers plus a queue is the default, and the serverless option wins only when agent runs are short and spiky.<\/span><\/p>\n<div style=\"background: #EEF2FE; border: 1px solid #DBE2FB; border-radius: 14px; padding: 28px 32px; margin: 38px 0;\">\n<p style=\"color: #1b3fae; font-size: 22px; line-height: 1.3; font-weight: bold; margin: 0 0 10px;\"><span style=\"font-weight: 400;\">Want a production deployment reviewed?<\/span><\/p>\n<p style=\"color: #4b5563; font-size: 16px; line-height: 1.6; margin: 0 0 22px;\"><span style=\"font-weight: 400;\">We\u2019ll check your agent architecture before it meets real traffic.<\/span><\/p>\n<p><a style=\"display: inline-block; background: #2563EB; color: #ffffff; text-decoration: none; font-size: 15px; font-weight: 600; padding: 13px 26px; border-radius: 8px;\" href=\"https:\/\/dianapps.com\/contact\">Talk To An AI Expert<\/a><\/p>\n<\/div>\n<h2><span style=\"font-weight: 400;\">Evaluating Agents After The Evals Shutdown<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">With OpenAI\u2019s hosted Evals platform closing alongside Agent Builder, evaluation becomes your responsibility, and that\u2019s a healthier place for it to live anyway. The pattern we use is simple enough to fit in a repository and run in CI.<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Golden dataset:<\/b><span style=\"font-weight: 400;\"> Fifty to two hundred real or realistic inputs with expected outcomes, grown from production traces over time.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Automated graders:<\/b><span style=\"font-weight: 400;\"> A model based grader scoring correctness and tone, plus deterministic checks for tool calls and formats.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Trace replay:<\/b><span style=\"font-weight: 400;\"> Rerun recorded traces against a new prompt or model version and diff the results before shipping.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Regression gate:<\/b><span style=\"font-weight: 400;\"> A pull request that drops the eval score below a threshold doesn\u2019t merge, same as a failing test.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Human spot checks:<\/b><span style=\"font-weight: 400;\"> A weekly sample reviewed by someone who knows the domain, because graders drift too.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">If you had datasets in the hosted platform, export them now, since read only became permanent in October and deletion follows at month end.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">Where OpenAI Agents Pay Off: Examples From Real Work?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">The agents that justify their cost tend to sit on repetitive, judgment heavy work with clear tools, rather than on anything requiring creativity or deep ambiguity. Support triage is the classic case, where a classifier agent routes tickets and specialist agents resolve the common ones, with a handoff to a person for the rest.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Procurement and back office flows are another, reading requests, checking policy and drafting approvals with a human signing off. Industry specific examples are where the interesting work happens, and<\/span><a href=\"https:\/\/dianapps.com\/blog\/ai-agents-for-real-estate\/\"> <span style=\"font-weight: 400;\">AI agents for real estate<\/span><\/a><span style=\"font-weight: 400;\"> walks through lead qualification and listing operations agents we\u2019ve seen deliver. A question clients ask early is whether they need an agent at all or whether rules based automation would do, and the honest answer is often the latter for stable, high volume processes.<\/span><a href=\"https:\/\/dianapps.com\/blog\/ai-agents-vs-rpa-vs-traditional-automation\/\"> <span style=\"font-weight: 400;\">AI agents vs RPA vs traditional automation<\/span><\/a><span style=\"font-weight: 400;\"> lays out that decision, and reading it first has saved more than one client an unnecessary project.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">Should You Build In House Or Bring In A Partner?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Most engineering teams can build a working OpenAI agent in a week, and that\u2019s the problem, because the working prototype creates confidence the production system hasn\u2019t earned yet. The parts that take experience are guardrail design, eval discipline, cost control and the operational plumbing around long runs, and those are exactly the parts a first project tends to skip. If your team has shipped agents before, keep it in house and use this guide as a checklist.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">If this is the first one and it touches customers or money, a partner who has already made the expensive mistakes shortens the path considerably, and you should be picky about which one.<\/span><a href=\"https:\/\/dianapps.com\/blog\/how-to-choose-an-ai-agent-development-company\/\"> <span style=\"font-weight: 400;\">How to choose an AI agent development company<\/span><\/a><span style=\"font-weight: 400;\"> sets out the questions we\u2019d want answered, including a few that make vendors uncomfortable, which is rather the point.<\/span><\/p>\n<div style=\"background: #EEF2FE; border: 1px solid #DBE2FB; border-radius: 14px; padding: 28px 32px; margin: 38px 0;\">\n<p style=\"color: #1b3fae; font-size: 22px; line-height: 1.3; font-weight: bold; margin: 0 0 10px;\"><span style=\"font-weight: 400;\">Ready to build your first production agent?<\/span><\/p>\n<p style=\"color: #4b5563; font-size: 16px; line-height: 1.6; margin: 0 0 22px;\"><span style=\"font-weight: 400;\">Tell us the job it needs to do and we\u2019ll scope it.<\/span><\/p>\n<p><a style=\"display: inline-block; background: #2563EB; color: #ffffff; text-decoration: none; font-size: 15px; font-weight: 600; padding: 13px 26px; border-radius: 8px;\" href=\"https:\/\/dianapps.com\/contact\">Talk To An AI Expert<\/a><\/p>\n<\/div>\n<h2><span style=\"font-weight: 400;\">Final Thoughts<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Learning how to build AI agents with OpenAI in late 2026 means accepting that the visual shortcut is gone and the code path is the path. That\u2019s less of a loss than it sounds, because the Agents SDK is small enough to learn in an afternoon and honest enough to show you, through traces, exactly where your agent is failing.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The hard work was never the canvas, it was the tool design, the guardrails, the evals and the deployment plumbing, and those sit with you either way. If you\u2019re mid migration, export before November 30 and treat the rebuild as a chance to tighten scope. If you\u2019re starting fresh, build narrow, trace everything and keep a human in the loop for anything irreversible. DianApps, a mobile and AI app development company, has done both kinds of projects this year, and the agents still running are the ones built that way.<\/span><\/p>\n<style>.elementor-24349 .elementor-element.elementor-element-2932a52{text-align:left;}.elementor-24349 .elementor-element.elementor-element-2932a52 > .elementor-widget-container{margin:0px 0px 0px 0px;}.elementor-24349 .elementor-element.elementor-element-0b767d1 .elementor-tab-title{border-width:1px;border-color:#00000014;}.elementor-24349 .elementor-element.elementor-element-0b767d1 .elementor-tab-content{border-width:1px;border-bottom-color:#00000014;}.elementor-24349 .elementor-element.elementor-element-0b767d1 > .elementor-widget-container{margin:0px 0px 0px 0px;}<\/style><div class=\"porto-block elementor elementor-24349\">\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-27707ca elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"27707ca\" data-element_type=\"section\">\r\n\t\t\t\r\n\t\t\t\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\r\n\t\t\t\t\t\t\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-0163611\" data-id=\"0163611\" data-element_type=\"column\">\r\n\r\n\t\t\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\r\n\t\t\t\t\t\t\t\t<div class=\"elementor-element elementor-element-03a2969 elementor-widget elementor-widget-text-editor\" data-id=\"03a2969\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.14.0 - 26-06-2023 *\/\n.elementor-widget-text-editor.elementor-drop-cap-view-stacked .elementor-drop-cap{background-color:#69727d;color:#fff}.elementor-widget-text-editor.elementor-drop-cap-view-framed .elementor-drop-cap{color:#69727d;border:3px solid;background-color:transparent}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap{margin-top:8px}.elementor-widget-text-editor:not(.elementor-drop-cap-view-default) .elementor-drop-cap-letter{width:1em;height:1em}.elementor-widget-text-editor .elementor-drop-cap{float:left;text-align:center;line-height:1;font-size:50px}.elementor-widget-text-editor .elementor-drop-cap-letter{display:inline-block}<\/style>\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-2932a52 elementor-widget elementor-widget-heading\" data-id=\"2932a52\" data-element_type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.14.0 - 26-06-2023 *\/\n.elementor-heading-title{padding:0;margin:0;line-height:1}.elementor-widget-heading .elementor-heading-title[class*=elementor-size-]>a{color:inherit;font-size:inherit;line-height:inherit}.elementor-widget-heading .elementor-heading-title.elementor-size-small{font-size:15px}.elementor-widget-heading .elementor-heading-title.elementor-size-medium{font-size:19px}.elementor-widget-heading .elementor-heading-title.elementor-size-large{font-size:29px}.elementor-widget-heading .elementor-heading-title.elementor-size-xl{font-size:39px}.elementor-widget-heading .elementor-heading-title.elementor-size-xxl{font-size:59px}<\/style><h2 class=\"elementor-heading-title elementor-size-large\">FAQs <\/h2>\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-0b767d1 elementor-widget elementor-widget-toggle\" data-id=\"0b767d1\" data-element_type=\"widget\" data-widget_type=\"toggle.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t<style>\/*! elementor - v3.14.0 - 26-06-2023 *\/\n.elementor-toggle{text-align:left}.elementor-toggle .elementor-tab-title{font-weight:700;line-height:1;margin:0;padding:15px;border-bottom:1px solid #d5d8dc;cursor:pointer;outline:none}.elementor-toggle .elementor-tab-title .elementor-toggle-icon{display:inline-block;width:1em}.elementor-toggle .elementor-tab-title .elementor-toggle-icon svg{-webkit-margin-start:-5px;margin-inline-start:-5px;width:1em;height:1em}.elementor-toggle .elementor-tab-title .elementor-toggle-icon.elementor-toggle-icon-right{float:right;text-align:right}.elementor-toggle .elementor-tab-title .elementor-toggle-icon.elementor-toggle-icon-left{float:left;text-align:left}.elementor-toggle .elementor-tab-title .elementor-toggle-icon .elementor-toggle-icon-closed{display:block}.elementor-toggle .elementor-tab-title .elementor-toggle-icon .elementor-toggle-icon-opened{display:none}.elementor-toggle .elementor-tab-title.elementor-active{border-bottom:none}.elementor-toggle .elementor-tab-title.elementor-active .elementor-toggle-icon-closed{display:none}.elementor-toggle .elementor-tab-title.elementor-active .elementor-toggle-icon-opened{display:block}.elementor-toggle .elementor-tab-content{padding:15px;border-bottom:1px solid #d5d8dc;display:none}@media (max-width:767px){.elementor-toggle .elementor-tab-title{padding:12px}.elementor-toggle .elementor-tab-content{padding:12px 10px}}.e-con-inner>.elementor-widget-toggle,.e-con>.elementor-widget-toggle{width:var(--container-widget-width);--flex-grow:var(--container-widget-flex-grow)}<\/style>\t\t<div class=\"elementor-toggle\">\n\t\t\t\t\t\t\t<div class=\"elementor-toggle-item\">\n\t\t\t\t\t<h3 id=\"elementor-tab-title-1201\" class=\"elementor-tab-title\" data-tab=\"1\" role=\"button\" aria-controls=\"elementor-tab-content-1201\" aria-expanded=\"false\">\n\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon elementor-toggle-icon-left\" aria-hidden=\"true\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-closed\"><i class=\"fas fa-caret-right\"><\/i><\/span>\n\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-opened\"><i class=\"elementor-toggle-icon-opened fas fa-caret-up\"><\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-toggle-title\" tabindex=\"0\">What is the best way to build AI agents with OpenAI right now?<\/a>\n\t\t\t\t\t<\/h3>\n\n\t\t\t\t\t<div id=\"elementor-tab-content-1201\" class=\"elementor-tab-content elementor-clearfix\" data-tab=\"1\" role=\"region\" aria-labelledby=\"elementor-tab-title-1201\"><p>Use the open source Agents SDK in Python or TypeScript, with ChatKit for the chat interface if you need one.<\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<div class=\"elementor-toggle-item\">\n\t\t\t\t\t<h3 id=\"elementor-tab-title-1202\" class=\"elementor-tab-title\" data-tab=\"2\" role=\"button\" aria-controls=\"elementor-tab-content-1202\" aria-expanded=\"false\">\n\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon elementor-toggle-icon-left\" aria-hidden=\"true\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-closed\"><i class=\"fas fa-caret-right\"><\/i><\/span>\n\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-opened\"><i class=\"elementor-toggle-icon-opened fas fa-caret-up\"><\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-toggle-title\" tabindex=\"0\">Is OpenAI Agent Builder still available?<\/a>\n\t\t\t\t\t<\/h3>\n\n\t\t\t\t\t<div id=\"elementor-tab-content-1202\" class=\"elementor-tab-content elementor-clearfix\" data-tab=\"2\" role=\"region\" aria-labelledby=\"elementor-tab-title-1202\"><p>It shuts down on November 30, 2026, so export existing workflows as Agents SDK code before that date.<\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<div class=\"elementor-toggle-item\">\n\t\t\t\t\t<h3 id=\"elementor-tab-title-1203\" class=\"elementor-tab-title\" data-tab=\"3\" role=\"button\" aria-controls=\"elementor-tab-content-1203\" aria-expanded=\"false\">\n\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon elementor-toggle-icon-left\" aria-hidden=\"true\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-closed\"><i class=\"fas fa-caret-right\"><\/i><\/span>\n\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-opened\"><i class=\"elementor-toggle-icon-opened fas fa-caret-up\"><\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-toggle-title\" tabindex=\"0\">How do you deploy the OpenAI Agents SDK to production?<\/a>\n\t\t\t\t\t<\/h3>\n\n\t\t\t\t\t<div id=\"elementor-tab-content-1203\" class=\"elementor-tab-content elementor-clearfix\" data-tab=\"3\" role=\"region\" aria-labelledby=\"elementor-tab-title-1203\"><p>Run it as a normal service in a container or serverless function, with external session storage and a queue for long runs.<\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<div class=\"elementor-toggle-item\">\n\t\t\t\t\t<h3 id=\"elementor-tab-title-1204\" class=\"elementor-tab-title\" data-tab=\"4\" role=\"button\" aria-controls=\"elementor-tab-content-1204\" aria-expanded=\"false\">\n\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon elementor-toggle-icon-left\" aria-hidden=\"true\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-closed\"><i class=\"fas fa-caret-right\"><\/i><\/span>\n\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-opened\"><i class=\"elementor-toggle-icon-opened fas fa-caret-up\"><\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-toggle-title\" tabindex=\"0\">What replaces OpenAI Evals for testing agents?<\/a>\n\t\t\t\t\t<\/h3>\n\n\t\t\t\t\t<div id=\"elementor-tab-content-1204\" class=\"elementor-tab-content elementor-clearfix\" data-tab=\"4\" role=\"region\" aria-labelledby=\"elementor-tab-title-1204\"><p>A golden dataset and automated graders in your own repository, run as a regression gate in CI.<\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<div class=\"elementor-toggle-item\">\n\t\t\t\t\t<h3 id=\"elementor-tab-title-1205\" class=\"elementor-tab-title\" data-tab=\"5\" role=\"button\" aria-controls=\"elementor-tab-content-1205\" aria-expanded=\"false\">\n\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon elementor-toggle-icon-left\" aria-hidden=\"true\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-closed\"><i class=\"fas fa-caret-right\"><\/i><\/span>\n\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-opened\"><i class=\"elementor-toggle-icon-opened fas fa-caret-up\"><\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-toggle-title\" tabindex=\"0\">Does ChatKit still work after the AgentKit changes?<\/a>\n\t\t\t\t\t<\/h3>\n\n\t\t\t\t\t<div id=\"elementor-tab-content-1205\" class=\"elementor-tab-content elementor-clearfix\" data-tab=\"5\" role=\"region\" aria-labelledby=\"elementor-tab-title-1205\"><p>Yes, ChatKit isn\u2019t part of the shutdown and still embeds chat agents into your product.<\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<div class=\"elementor-toggle-item\">\n\t\t\t\t\t<h3 id=\"elementor-tab-title-1206\" class=\"elementor-tab-title\" data-tab=\"6\" role=\"button\" aria-controls=\"elementor-tab-content-1206\" aria-expanded=\"false\">\n\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon elementor-toggle-icon-left\" aria-hidden=\"true\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-closed\"><i class=\"fas fa-caret-right\"><\/i><\/span>\n\t\t\t\t\t\t\t\t<span class=\"elementor-toggle-icon-opened\"><i class=\"elementor-toggle-icon-opened fas fa-caret-up\"><\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t<a class=\"elementor-toggle-title\" tabindex=\"0\">How long does building a production ready AI agent with OpenAI take?<\/a>\n\t\t\t\t\t<\/h3>\n\n\t\t\t\t\t<div id=\"elementor-tab-content-1206\" class=\"elementor-tab-content elementor-clearfix\" data-tab=\"6\" role=\"region\" aria-labelledby=\"elementor-tab-title-1206\"><p>A prototype takes days, while a guarded, evaluated, deployed agent usually takes six to twelve weeks.<\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t\t\t\t<script type=\"application\/ld+json\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@type\":\"FAQPage\",\"mainEntity\":[{\"@type\":\"Question\",\"name\":\"What is the best way to build AI agents with OpenAI right now?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"<p>Use the open source Agents SDK in Python or TypeScript, with ChatKit for the chat interface if you need one.<\\\/p>\"}},{\"@type\":\"Question\",\"name\":\"Is OpenAI Agent Builder still available?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"<p>It shuts down on November 30, 2026, so export existing workflows as Agents SDK code before that date.<\\\/p>\"}},{\"@type\":\"Question\",\"name\":\"How do you deploy the OpenAI Agents SDK to production?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"<p>Run it as a normal service in a container or serverless function, with external session storage and a queue for long runs.<\\\/p>\"}},{\"@type\":\"Question\",\"name\":\"What replaces OpenAI Evals for testing agents?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"<p>A golden dataset and automated graders in your own repository, run as a regression gate in CI.<\\\/p>\"}},{\"@type\":\"Question\",\"name\":\"Does ChatKit still work after the AgentKit changes?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"<p>Yes, ChatKit isn\\u2019t part of the shutdown and still embeds chat agents into your product.<\\\/p>\"}},{\"@type\":\"Question\",\"name\":\"How long does building a production ready AI agent with OpenAI take?\",\"acceptedAnswer\":{\"@type\":\"Answer\",\"text\":\"<p>A prototype takes days, while a guarded, evaluated, deployed agent usually takes six to twelve weeks.<\\\/p>\"}}]}<\/script>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/section>\r\n\t\t<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Key Takeaways:\u00a0 OpenAI\u2019s Agents SDK supports code-first agent development in Python and TypeScript. Agent Builder is scheduled to shut down on November 30, 2026, making migration essential for existing users. Use tools, handoffs and guardrails to build reliable agents with controlled actions. Deploy agents as regular services with external session storage, queues and observability. Replace [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":24342,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_yoast_wpseo_meta-robots-noindex":"","_yoast_wpseo_meta-robots-nofollow":"","_yoast_wpseo_canonical":"","_yoast_wpseo_opengraph-title":"","_yoast_wpseo_opengraph-description":"","_yoast_wpseo_opengraph-image":"","_yoast_wpseo_twitter-title":"","_yoast_wpseo_twitter-description":"","_yoast_wpseo_twitter-image":"","_wp_applaud_exclude":false,"footnotes":""},"categories":[1622],"tags":[2941],"class_list":["post-24337","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","tag-how-to-build-ai-agents-with-openai"],"featured_image_src":{"landsacpe":["https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai--1140x445.webp",1140,445,true],"list":["https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai--463x348.webp",463,348,true],"medium":["https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai--300x169.webp",300,169,true],"full":["https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai-.webp",1536,864,false]},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.7 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>How to build AI agents with OpenAI: Agents SDK and AgentKit<\/title>\n<meta name=\"description\" content=\"Learn how to build AI agents with OpenAI using the Agents SDK and what remains of AgentKit, with production deployment steps, guardrails and evals.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How to build AI agents with OpenAI: Agents SDK and AgentKit\" \/>\n<meta property=\"og:description\" content=\"Learn how to build AI agents with OpenAI using the Agents SDK and what remains of AgentKit, with production deployment steps, guardrails and evals.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/\" \/>\n<meta property=\"og:site_name\" content=\"Learn About Digital Transformation &amp; Development | DianApps Blog\" \/>\n<meta property=\"article:published_time\" content=\"2026-11-19T09:41:36+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-11-19T09:47:41+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai-.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1536\" \/>\n\t<meta property=\"og:image:height\" content=\"864\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Vikash Soni\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Vikash Soni\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"13 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"How to build AI agents with OpenAI: Agents SDK and AgentKit","description":"Learn how to build AI agents with OpenAI using the Agents SDK and what remains of AgentKit, with production deployment steps, guardrails and evals.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/","og_locale":"en_US","og_type":"article","og_title":"How to build AI agents with OpenAI: Agents SDK and AgentKit","og_description":"Learn how to build AI agents with OpenAI using the Agents SDK and what remains of AgentKit, with production deployment steps, guardrails and evals.","og_url":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/","og_site_name":"Learn About Digital Transformation &amp; Development | DianApps Blog","article_published_time":"2026-11-19T09:41:36+00:00","article_modified_time":"2026-11-19T09:47:41+00:00","og_image":[{"width":1536,"height":864,"url":"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai-.webp","type":"image\/webp"}],"author":"Vikash Soni","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Vikash Soni","Est. reading time":"13 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/#article","isPartOf":{"@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/"},"author":{"name":"Vikash Soni","@id":"https:\/\/dianapps.com\/blog\/#\/schema\/person\/0126fafc83e42bece2acbfe92f7d0f4f"},"headline":"How to build AI agents with OpenAI? Agents SDK and AgentKit","datePublished":"2026-11-19T09:41:36+00:00","dateModified":"2026-11-19T09:47:41+00:00","mainEntityOfPage":{"@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/"},"wordCount":2560,"commentCount":0,"image":{"@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/#primaryimage"},"thumbnailUrl":"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai-.webp","keywords":["How to build AI agents with OpenAI"],"articleSection":["Artificial Intelligence"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/","url":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/","name":"How to build AI agents with OpenAI: Agents SDK and AgentKit","isPartOf":{"@id":"https:\/\/dianapps.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/#primaryimage"},"image":{"@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/#primaryimage"},"thumbnailUrl":"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai-.webp","datePublished":"2026-11-19T09:41:36+00:00","dateModified":"2026-11-19T09:47:41+00:00","author":{"@id":"https:\/\/dianapps.com\/blog\/#\/schema\/person\/0126fafc83e42bece2acbfe92f7d0f4f"},"description":"Learn how to build AI agents with OpenAI using the Agents SDK and what remains of AgentKit, with production deployment steps, guardrails and evals.","breadcrumb":{"@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/#primaryimage","url":"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai-.webp","contentUrl":"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/11\/How-to-build-ai-agents-with-open-ai-.webp","width":1536,"height":864,"caption":"How to build ai agents with open ai"},{"@type":"BreadcrumbList","@id":"https:\/\/dianapps.com\/blog\/how-to-build-ai-agents-with-openai\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dianapps.com\/blog\/"},{"@type":"ListItem","position":2,"name":"How to build AI agents with OpenAI? Agents SDK and AgentKit"}]},{"@type":"WebSite","@id":"https:\/\/dianapps.com\/blog\/#website","url":"https:\/\/dianapps.com\/blog\/","name":"Learn About Digital Transformation &amp; Development | DianApps Blog","description":"Dianapps","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dianapps.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/dianapps.com\/blog\/#\/schema\/person\/0126fafc83e42bece2acbfe92f7d0f4f","name":"Vikash Soni","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/08\/vikash-soni-400-96x96.jpg","url":"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/08\/vikash-soni-400-96x96.jpg","contentUrl":"https:\/\/dianapps.com\/blog\/wp-content\/uploads\/2026\/08\/vikash-soni-400-96x96.jpg","caption":"Vikash Soni"},"description":"Vikash Soni (CTO &amp; Co-founder, DianApps) leads engineering at DianApps, where he has spent over 10 years building AI and machine learning systems, alongside earlier work in AR\/VR and blockchain. He has delivered 250+ AI and machine learning systems across various industries, e.g. healthcare, fintech, and retail. His work centers on the parts of AI development that decide whether a project ships: retrieval architecture, evaluation design, and the data preparation most teams underestimate. He advises founders and enterprise technology leaders on where AI genuinely fits a problem, and where a simpler system would serve better.","sameAs":["https:\/\/dianapps.com\/","https:\/\/www.instagram.com\/_ai_4everyone","https:\/\/www.linkedin.com\/in\/reachvikashsoni\/"],"url":"https:\/\/dianapps.com\/blog\/author\/infodianapps-com\/"}]}},"_links":{"self":[{"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/posts\/24337","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/comments?post=24337"}],"version-history":[{"count":3,"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/posts\/24337\/revisions"}],"predecessor-version":[{"id":24354,"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/posts\/24337\/revisions\/24354"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/media\/24342"}],"wp:attachment":[{"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/media?parent=24337"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/categories?post=24337"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dianapps.com\/blog\/wp-json\/wp\/v2\/tags?post=24337"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}