OpenAI’s new Agents API and hosted sandboxes give agents a place to operate, files to touch, tools to use, and costs to manage.
Before choosing a model, decide where the agent works, what it can touch, and who owns the result.
OpenAI announced the Agents API and hosted sandboxes on September 10, 2026. The company says developers can now build and run cloud agents with the Codex harness, while OpenAI handles orchestration, long-running sessions, and context management. Agents can run code, work with files, produce artifacts, install packages, and use skills and plugins inside a managed environment.
TL;DR
Agents need a workspace as well as instructions. OpenAI’s hosted sandboxes give teams a managed environment for agent work. Business leaders should define the workspace, permissions, budget, handoff, and review loop before agents start doing real work.
The sandbox gives agent work a home
The developer headline is the Agents API. The business headline is the sandbox.
A sandbox is the working environment around the agent. It is where code runs, files are handled, packages are installed, and artifacts are produced. OpenAI’s announcement says teams can bring their own sandbox, connect a sandbox provider, or use OpenAI-hosted environments. It also names nine first-class integrations: Blaxel AI, Cloudflare Dev, Daytona, DigitalOcean, E2B, Modal, Oracle Cloud, Runloop AI, and Vercel.
That list shows vendors competing on where agent work happens as well as on model quality.
For a normal company, that sounds technical until you translate it into operations. If an agent is helping finance reconcile reports, where are the source files? If it is helping marketing produce campaign assets, where does it store drafts? If it is helping support triage tickets, what customer data can it read? If it is helping operations update records, can it actually change the system or only prepare a recommendation?
Management needs to make those decisions with engineering.
A collaborator needs a workspace
Most companies still talk about AI as if the interaction begins and ends inside a chat box. Ask a question. Get an answer. Copy the answer somewhere else. Maybe paste in a spreadsheet. Maybe ask again.
That mental model breaks down with agents.
An agent that can run code, handle files, and produce artifacts is closer to a junior collaborator than a search box. It needs a workspace. It needs a defined assignment. It needs constraints. It needs someone to review the output before the work moves downstream.
This is where organizations either get leverage or create mess.
A human employee needs a laptop and an understanding of the work, the systems, the approval path, and what a good result looks like. Agents need that context too, while being less forgiving in some places and faster in others.
If the workspace is messy, the agent inherits the mess. If the instructions are vague, the agent produces vague work. If nobody owns review, the handoff fails quietly.
Assign ownership and budget for hosted work
OpenAI’s announcement says there are no additional fees for using the Agents API itself, with teams paying for tokens and tools. In the community discussion, OpenAI also clarified that hosted sandboxes use standard container rates and model usage is billed separately.
That is a small detail with a big operational implication.
Agent work costs include model usage, tool usage, sandbox runtime, storage, integrations, retries, and human review time alongside any software subscription. If leaders do not define the work tightly, they should expect surprise costs and fuzzy accountability.
This is especially true when agents move from demos into recurring workflows. A one-off agent that analyzes ten files is a test. A daily agent that reviews every incoming contract, writes summaries, checks exceptions, and prepares handoffs is an operating expense.
Plan recurring agent work as a recurring expense. Answer the practical questions early:
What does this agent do every day?
Where does it work?
What files can it access?
What can it create?
What can it change?
What happens when it is wrong?
Who reviews the output?
Where does the cost show up?
That is the difference between an agent experiment and an agent workflow.
What leaders should do this week
Start with one workflow where an agent needs a real workspace, then use its requirements to evaluate platforms.
Pick something concrete: preparing a weekly sales brief, reconciling vendor invoices, summarizing support escalations, reviewing documents for missing fields, producing first drafts of client follow-ups, or turning meeting notes into assigned tasks.
Then define five things before anyone builds:
- The workspace: where the agent does the work and where outputs live.
- The inputs: files, systems, records, messages, or data it can read.
- The authority: what it can draft, create, update, submit, or trigger.
- The review loop: who checks the work and what counts as acceptable.
- The cost boundary: when the workflow should stop, ask, or escalate.
These decisions prepare AI for production environments where work actually happens. OpenAI’s hosted sandboxes give teams another way to build those environments.
Once agents have a place to work, leaders have a new responsibility: design the place well enough that the work can be trusted.
Research and structure: Mai. Direction and voice: John Lipe.
Sources: OpenAI Developer Community, “Introducing the Agents API and hosted sandboxes,” published September 10, 2026; The Verge, “Due to GPT-6 Astra demand, OpenAI has paused new subscriptions to its $200 ChatGPT Pro tier,” published September 11, 2026.