Playbooks · Coding tasks
OpenAI shuts Agent Builder, Evals, and prompts November 30
Written November 4, 2026
Three OpenAI surfaces close November 30, 2026. Where each workload moves — Agents SDK, Workspace Agents, Promptfoo, or your own code — and the export catch.
What shuts down, and when
On 3 June 2026, OpenAI notified developers that three products were being deprecated. All three are scheduled to shut down on 30 November 2026:
- Agent Builder, the visual canvas for building agent workflows. ChatKit remains available.
- The Evals platform, dashboard and API. Existing evals became read-only on 31 October 2026, so nothing in an existing eval can be changed after that date — only moved.
- Reusable prompts: the
v1/promptsAPI and reusable prompt objects.
At shutdown, each surface stops being accessible. The migration for each one is different, and none of them is automatic — plan per surface, not as one move.
Agent Builder: export the workflow as code, then rebuild it
OpenAI's migration guide exports an existing workflow as Agents SDK code. Open the workflow in Agent Builder, select Code, select Agents SDK, pick TypeScript or Python, and copy the complete export. From there, two destinations are named:
- Agents SDK, for building agents through code. Copy the export into your application, install and configure the matching Agents SDK, and test the workflow in your runtime. You now own hosting, authentication, the interface, and uptime.
- ChatGPT Workspace Agents, for building agents through natural language and sharing them with teams. This needs a ChatGPT Business, Enterprise, or Edu workspace with access to workspace agents and permission to create them. Create a workspace agent, paste the exported code with the prompt asking for the workflow to be converted into an agent, review what the builder flags as needing changes, and create the agent only after previewing representative inputs against the original workflow's expected behaviour.
The catch is stated in the guide itself: the export process does not convert your workflow graph and does not guarantee that every behaviour transfers unchanged. Review control flow, triggers, tools, and permissions as you test the migrated agent, and validate the application's configuration and behaviour before deploying it. Workflows with strong determinism at their core may not migrate faithfully to a workspace agent, and connected apps, authentication, publishing, and permission configuration need separate review in ChatGPT. A workflow that has not been tested end to end in its new home has not been migrated — it has only been copied.
Evals: recreate each eval by hand in Promptfoo
OpenAI recommends Promptfoo for continuing evaluation workflows, and its guide covers manually recreating an evaluation — it does not rely on an export feature. Recreate the evaluation's prompts, provider, test cases, and assertions in a promptfooconfig.yaml file, mapping graders configured as testing criteria in the eval to grading behaviour configured as assertions and metrics in Promptfoo. Then run a fresh evaluation and open the results viewer:
promptfoo eval -c promptfooconfig.yaml --no-cachepromptfoo viewpromptfoo validate config -c promptfooconfig.yaml
The new run is separate from any previously completed OpenAI Evals runs: past results do not carry over. After the first run, compare the recreated prompts, assertions, and outputs before using the eval in an ongoing workflow. Similarity-based scoring may not produce identical numerical results across systems, and any manually recreated grader — especially an LLM-as-a-judge grader — should be validated before you rely on it for regression decisions. A grader that has not been re-validated in Promptfoo is a new grader, not a moved one.
Reusable prompts: move the content into your application code
For reusable prompts, OpenAI's instruction is short: move reusable prompt content into your application code. There is no replacement prompt-object service named on the deprecations page. Copy each prompt's content out of the dashboard or API while it is still accessible, store it with the code that uses it, and change the code that read the prompt object to read the stored copy instead. Check every call site that referenced a prompt object by ID — a prompt stored in code but still read from v1/prompts will fail at shutdown exactly like one that was never moved.
Do not confuse this with the model removals
Two further dates on the same deprecations page are model removals, not product shutdowns, and they need separate migration work:
- 11 December 2026:
gpt-5,gpt-5-mini,gpt-5-nano,gpt-5-pro,o3, ando3-proleave the API, withgpt-5.6-sol,gpt-5.6-terra, andgpt-5.6-lunanamed as replacements. - 14 January 2027: specified GPT-4o, GPT-4o mini, GPT-4.1, and GPT-4.1 mini snapshots leave the API, with
gpt-6-lunanamed as the replacement.
Moving a model and moving a workflow are different jobs. Finishing one does not finish the other.
Order of work
- Inventory all three surfaces now. List every Agent Builder workflow, every eval, and every reusable prompt object in use, including ones owned by former team members or embedded in scheduled jobs.
- Move Agent Builder workflows first. They need the most testing: export, rebuild, and run representative inputs in the new home before the canvas disappears.
- Recreate evals next, and re-validate graders. An eval moved without its graders re-validated will pass or fail for reasons nobody has checked.
- Move prompt content into code last, and grep for prompt IDs. The change is small per prompt, but a single missed call site fails at shutdown.
- Cut over before 30 November. The Evals read-only date has already passed; nothing in an existing eval can be edited now, only recreated elsewhere.
Limits
- OpenAI's migration guides describe the paths above. They do not promise that a migrated workflow or eval behaves identically to the original — the Agent Builder guide says so explicitly, and the Promptfoo guide requires re-validation of recreated graders.
- Workspace Agents need a Business, Enterprise, or Edu workspace. A personal ChatGPT plan does not provide that destination.
Related playbooks
- OpenAI's training ban lands November 20
- Agent Builder shuts down Nov 30: export now
- November shutdowns: Runloop, Conductor, Moondream
- Anthropic's no-distillation rule lands November 12
Sources
- https://developers.openai.com/api/docs/deprecations
- https://developers.openai.com/api/docs/guides/agent-builder/migrate-from-agent-builder
- https://developers.openai.com/cookbook/examples/evaluation/moving-from-openai-evals-to-promptfoo
Back to: Coding playbooks hub · Also: Move off Claude Sonnet 4.5 before it retires · GPT-6.1 Sol, Ultrafast, and the new Pro tiers