
Go from idea to a working agent faster with the Agents API. Build and run cloud agents with the Codex harness, fully managed by OpenAI. We handle orchestration, long-running sessions, and context ma
The Hook
“Getting a long-running agent into production takes a lot of work, even with a capable model. You need to connect tools, track progress, manage context, and secure and maintain the infrastructure around it.”
Product Reveal
“Today, we're launching the Agents API to handle that infrastructure for you.”
Feature Teaser
“The Agents API brings a hosted version of the Codex harness to your applications. OpenAI handles orchestration, sessions, and context management so that you can stay focused on building.”
Feature Teaser
“Let's look at an example. Suppose we want to build an agent that helps investigate incidents in our production stack. It would need access to observability data and recent code changes, along with our team's instructions for how to handle an outage. We can connect all of our necessary tools through MCPs and give the agent our investigation runbook via a skill.”
Feature Teaser
“You control the agent's execution environment and the tools it has access to. That includes connecting a sandbox, whether it's through OpenAI, a third-party provider, or using your own infrastructure.”
Feature Teaser
“In a situation like this, we'd also be working through a ton of logs, likely more than we could fit in the model's context window. With programmatic tool calling, the agent can process those logs and filter the results in code, meaning fewer tokens spent passing around raw data and more spent on the information the agent needs.”
Feature Teaser
“For the largest tasks, independent work can be delegated via multi-agent orchestration. In this case, we might want one sub-agent to examine recent changes, another to check telemetry, and then have the lead agent unify their findings.”
Feature Teaser
“But even in a single agent session, long-running context windows still work really well with compaction. It gives the model a summary of all prior work completed so the agent can continue its investigation. Once the work is complete, the findings should be served as a report that the on-call team can review: a likely root cause, the supporting evidence, and suggested next steps bundled into a single shareable file.”
Call to Action
“And there we have it. With the Agents API, we were able to drive an entire workflow without building or maintaining any of our own agent infrastructure. Infrastructure that will continue to get better alongside new models and new capabilities. We're excited to bring you an ever-improving harness behind one API. Happy building.”
Synthesizable in Remotion · key components of the developer-agent-launch template.
Simulates real-time CLI terminal text and JSON output typing with glowing particle ambient background.
Use Remotion Sequence with interpolated string slicing driven by frame count, wrapped in a styled rounded container.
Presenter aligned to right side while syntax-highlighted code shifts smoothly on the left.
Absolute layout flex container with slide-in CSS transitions controlled via spring() physics on interpolate.
Side-by-side layout contrasting standard API direct calls with PTC tokens (170,126 vs 11).
Dual column card grid with spring-animated numerical counting and opacity reveal.
Purpose. Highlight agent ops complexity.
Execution. Presenter speaking directly to camera.
Purpose. Position API as turnkey infrastructure.
Execution. Minimal 2D schematic diagram.
Purpose. Demonstrate real triage with code and tools.
Execution. Terminal CLI output and code overlays.
Purpose. Quantify token savings via programmatic tool calling.
Execution. Side-by-side token reduction counter.
Purpose. Show polished end deliverable.
Execution. Rendered incident incident PDF report.