# The Architecture (/claude-and-chatgpt-2/architecture/overview) --- type: Document title: "The Architecture" description: "The technical edition of Claude and ChatGPT 2.0. It shows what was seen inside a real Claude session, what each vendor documents, why both chose the same design, and what a business must add. Optional reading." status: stable order: 0.4 ksor: owner: team:panaversity audience: [ public ] approval: by: process:panaversity at: 2026-11-09T20:42:36Z chapter: "F00A" part: Front expert_status: required objectives: [] word_budget: null prerequisites: [] build_step: null artifact: null field_guides: [] delta_entries: [] concepts: [ "The architecture", "Request flow", "Why the same design", "Sandbox and state", "Cloud environments", "Scheduled tasks", "Projects", "Where to run work", "Security boundaries", "Worked example", "ChatGPT and Codex", "AI Worker platforms", "Business worker", "What comes next" ] last_verified: 2026-11-09 review_by: 2026-12-09 sources: - id: cowork-architecture title: "Claude Cowork architecture overview (Anthropic, verified 2026-11-09)" resource: https://support.claude.com/en/articles/14479288-claude-cowork-architecture-overview - id: cloud-scheduled-tasks title: "Automate work with scheduled tasks (Anthropic, verified 2026-11-09)" resource: https://code.claude.com/docs/en/routines - id: desktop-scheduled-tasks title: "Schedule recurring tasks in Claude Code Desktop (Anthropic, verified 2026-11-09)" resource: https://code.claude.com/docs/en/desktop-scheduled-tasks - id: author-inspection title: "Panaversity's inspection of a cloud Claude session: a Python test run on November 8, 2026, and a process and environment inspection on November 9, 2026" resource: "appendix-reproducing-the-observations.md" - id: chatgpt-inspection title: "ChatGPT's inspection of its own Python and terminal environment, November 9, 2026, as reported to Panaversity" resource: "Reported to Panaversity by ChatGPT, November 9, 2026" - id: claude-and-chatgpt-2-tour title: "Tour of the Apps, for every product feature and its source" resource: "../tour/overview.md" generated: at: 2026-11-09T20:42:36Z by: process:panaversity trust_tier: unverified build_id: sha256:46fd53c5d7ab1c14f6347908d45c9fdaecda4d914439923ee878bdcecd57803e dirty: true ksor_version: 0.0.60 --- *How the new apps work behind the screen, with the evidence* ## Where this section fits This is the fourth section of Claude and ChatGPT 2.0: the technical edition. It is optional. Read it for the evidence and the engineering, or come back when you build AI Workers for a business. The [first section](../new-way-of-working/overview.md) introduced AI Workers, the [borrowed desk](../new-way-of-working/where-the-work-happens.md) and Brightline's [Friday payment run](../new-way-of-working/one-job.md). [Tour of the Apps](../tour/overview.md) documented each feature. [Behind the Screen](../behind-the-screen/overview.md) explained the same ideas with one analogy: the model is a consultant, the harness is a project manager, and the sandbox is the borrowed desk. This section adds the evidence: what was observed in a real Claude session, what each vendor documents, why both chose the same design, and what a business must add. It does not repeat the Tour's feature lists. ## What the architecture is In the desktop app or on the web, a Claude session runs in the cloud by default. A **session** is one running conversation or task. A request travels this path: UI → Anthropic backend → harness → model on Anthropic's inference servers. The **UI** is the app or web page you type into. The **backend** is the servers behind the app. **Inference servers** run the model. This section calls the UI, the backend, the harness and the model its **four layers**. The firsthand observations come from one cloud Claude session that the Panaversity team inspected on November 8 and 9, 2026. The [appendix](appendix-reproducing-the-observations.md) gives the method.[^author-inspection] ChatGPT also reported an inspection of its own code environment. It did not show ChatGPT's harness or inference.[^chatgpt-inspection] The rest of the OpenAI side rests on OpenAI's documentation. - **[Vendor-documented]** Cloud sessions are the default. The agent loop and code execution run on Anthropic's servers. Each session gets its own sandbox, "created when the session starts and destroyed when it ends".[^cowork-architecture] - **[Observed]** In the session examined, the harness was Claude Code. It ran inside a Firecracker microVM, a small virtual machine that starts very quickly. The session had been started from a claude.ai chat. - **[Inferred]** The model does not run inside the sandbox. The sandbox is where the model's tool calls run and where its files are kept. - **[Vendor-documented]** Each scheduled task run starts a new session. The exception is a run inside a project, which can continue an existing thread.[^cloud-scheduled-tasks],[^desktop-scheduled-tasks] - **[Inferred]** No VM runs permanently for an account. None is documented, and none was observed. - **[Inferred]** What changes from one **surface** (the web, the desktop app or a terminal) to another is where the harness runs: in a cloud sandbox, on your own device, or on a server you manage. In Claude's own apps, on Anthropic-hosted environments, the model runs on Anthropic's servers by default. ## How this section is organized [Why both vendors chose the same design](why-both-vendors-chose-the-same-design.md) comes first. It explains the goals. The first half shows how the runtime works, with Claude as the observed example: [request flow](how-a-request-flows.md), [the sandbox and its state](the-sandbox-and-its-state.md), [cloud environments](cloud-environments-and-self-hosted-runners.md), [scheduled tasks](scheduled-tasks.md), [projects](projects-coordination-on-top-of-sessions.md), [where to run work](choosing-where-to-run-work.md) and [security](security-boundaries.md). It ends with a [worked example](worked-example-brightlines-payment-run-as-a-business-ai-worker.md) and [ChatGPT and Codex](chatgpt-and-codex.md). The second half shows how these runtimes become AI Workers: [are they AI Worker platforms?](are-claude-and-chatgpt-now-ai-worker-platforms.md), [from personal to business worker](from-personal-worker-to-business-worker.md) and [what comes next](what-comes-next.md). Three appendices hold the [reproduction steps](appendix-reproducing-the-observations.md), [business-layer details](appendix-business-layer-details.md) and [runtime details](appendix-runtime-details.md). > [!NOTE] > **Words used in this section** > > - **Model:** the stateless inference service that reads a context and returns text or a tool call. *Stateless* means it keeps nothing from one call to the next. *Inference* means running the model to produce an answer. *Context* is everything the model reads in one call. > - **Harness:** the agent loop around the model. It builds the context, runs tools and tracks progress. Claude Code and Codex are harnesses. It can run inside the sandbox, as observed here, or apart from it. > - **Sandbox:** the isolated place where tool calls run, the borrowed desk. It can be a cloud VM or container, or a limited space on your own computer. > - **Virtual machine (VM):** a complete computer, simulated in software. A **container** is a lighter isolated space that shares the operating system of the computer it runs on. > - **Session:** one running conversation or task, with its own sandbox and history. > - **Runtime:** the harness plus the sandbox, as a product you run work on. For Claude, it is the Claude app, Claude Tag, Managed Agents or the Agent SDK (with the Agent SDK, you host both). For OpenAI, it is ChatGPT Work and Codex. > - **Scheduled task:** a saved prompt that starts a new session on a schedule or when something happens (a trigger). Both vendors offer them. > - **Worker principal:** the identity a worker acts under. It is separate from the people who sponsor or approve the worker. > - **Business layer:** what an organization adds around the runtime: identity, durable records, enforced authority and audit. > [!NOTE] > **How to read the evidence labels** > > Each claim in this section carries a label in square brackets. The label says how we know it. > > - **Observed:** seen directly in the Claude session examined: command output, running programs, the environment and behavior. > - **Reported by ChatGPT:** results that ChatGPT reported from commands it ran in its own tools, at our request. Nobody else has reviewed the raw output. > - **Tool-documented:** stated in the descriptions of the tools available inside the session, but not seen in action. > - **Vendor-documented:** stated in Anthropic's or OpenAI's public documentation, with the source in a footnote. > - **Inferred:** our conclusion from the observations and documents. The vendor does not state it. > - **Unknown:** not visible from inside a session, and not documented. > > Products change often, and features differ by plan. This section describes them as of November 9, 2026. If your app looks different, trust the vendor's help page. The architecture still holds. [^author-inspection]: The observations come from one cloud Claude chat session on November 8 and 9, 2026, and may not hold for every plan, account or surface. The commands and their limits are in the appendix. [^chatgpt-inspection]: At our request, ChatGPT ran commands in its own Python and terminal tools, in a separate ChatGPT conversation, and reported the results. The raw output was not independently reviewed. [^cowork-architecture]: As verified on November 9, 2026. Claude Cowork architecture overview, Anthropic. [^cloud-scheduled-tasks]: Automate work with scheduled tasks, Anthropic. [^desktop-scheduled-tasks]: Schedule recurring tasks in Claude Code Desktop, Anthropic.