Guide OpenAI · Reference

    What changed at OpenAI, with date and source.

    Every change comes with its date and OpenAI's own page, from the shutdown of the Assistants API to dots in ChatGPT, filterable by vendor and by chapter of the guide.

    As of: October 2026 · Editor: Marcel Haas

    Chronicle

    Newest first.

    Every entry comes with its status date, the text of the page and the vendor's own source. Filter by vendor and chapter.

    17 entries in this selection

    1. 2026

      As of 12 October 2026

      OpenAI

      Apps and Company Knowledge in Business and Enterprise, the Connector Registry in Enterprise.

      With apps, ChatGPT reads documents from SharePoint and Outlook, issues from GitHub or data from your own systems, and Company Knowledge answers questions across several connected sources; both belong to ChatGPT Business and Enterprise. Which apps are allowed in the workspace is set by the administration, and Enterprise lists them in the Connector Registry. In an app, ChatGPT sees only what the signed-in person may open there.

    2. As of 12 October 2026

      OpenAI

      Codex sandbox modes and approval policy, set centrally.

      Codex has the sandbox modes read-only, workspace-write and danger-full-access, and the approval policy decides when Codex asks. Through requirements.toml or the Agent Security settings the administration sets which profiles, approval policies and MCP servers are allowed; settings from the repository cannot widen these limits.

    3. As of 12 October 2026

      OpenAI

      Zero Data Retention and Modified Abuse Monitoring need an approval.

      Per project you set keys with an expiry date, hard spending limits and the data region when creating it. OpenAI does not use API data for training unless you explicitly opt in. Zero Data Retention or Modified Abuse Monitoring take content out of the abuse monitoring logs after approval by OpenAI.

    4. As of October 2026

      OpenAI

      API data: no training, a Europe region per project.

      OpenAI has not used API data for training since 1 March 2023, and abuse monitoring logs are kept for up to 30 days. The Europe region, which OpenAI labels EEA and Switzerland, stores and processes in the region for the listed endpoints and requires a retention option approved by OpenAI. The Agents API is not listed there.

    5. As of October 2026

      Anthropic

      Claude Enterprise with SCIM, audit logs and the Compliance API.

      The Enterprise plan includes single sign-on, SCIM provisioning, audit logs, the Compliance API, custom retention rules and role-based access; Claude Code is included. Content is not used for training by default. The Team plan offers single sign-on, but neither SCIM nor audit logs.

    6. As of October 2026

      OpenAI

      The data region of the project decides where a model computes.

      You set the data region per project when creating it, together with keys that expire and hard spending limits. The Europe region, which OpenAI labels EEA and Switzerland, stores and processes in the region for the listed endpoints and requires a retention option approved by OpenAI; the Agents API is not listed there.

    7. Since 10 September 2026

      OpenAI

      The Agents API is in public beta, since 29 September 2026 with computer use.

      OpenAI has run the Agents API as a public beta since 10 September 2026: sessions that persist, sandboxes, context compaction and collaboration between several agents on the runtime OpenAI itself runs Codex on. Since 29 September 2026 an agent also operates a browser hosted by OpenAI through it.

    8. Since 26 August 2026

      OpenAI

      OpenAI: Assistants API removed, Agents API in beta.

      The Assistants API was removed on 26 August 2026; agents of your own run on the Responses API, the Agents SDK and the new Agents API, which provides the Codex harness as a managed service. Agent Builder and the Evals platform from AgentKit shut down on 30 November 2026; ChatKit remains.

    9. Since 8 April 2026

      Anthropic

      Claude Managed Agents, harness and operation for autonomous agents.

      Anthropic runs Claude as an autonomous agent in a cloud or self-hosted sandbox, with MCP servers and scheduled runs, as a public beta. The Model Context Protocol, which connects tools and data to agents, went to the Linux Foundation's Agentic AI Foundation on 9 December 2025; Microsoft, OpenAI and Anthropic support it.

    Reference

    Agree on a useful next step

    Tell us about your current workflow, the systems involved and the result you need. In our first conversation we map your needs to the layers of the guide.