The Anthropic Stack On One Page

Anthropic ships into so many surfaces now — three model tiers, ten API primitives, a half-dozen builder tools, a handful of end-user apps, the enterprise controls, the cloud distribution — that nobody who isn't paid to track it can hold the whole shape in their head. This post is one map of that surface area, grouped by who actually uses each piece. The point is not the categories; the point is being able to see what exists, all at once, on one page.

Six domains. They are not Anthropic's official taxonomy — they are how the product looks to a buyer trying to decide which layer they need to touch.

How to read it

Each card answers a different question for a different audience. Treat the diagram as six conversations stacked on one page.

Engine — which model, on what. Opus when judgment quality is the actual differentiator and the cost per call doesn't matter. Sonnet as the default workhorse for almost everything else. Haiku when latency or unit economics win. Extended thinking, vision, 200K context, and Constitutional AI sit on top of all three.

API primitives — the building blocks an engineer composes. Tool use, prompt caching, the batch discount, files, citations, memory, computer use, streaming, structured outputs. Each one removes a class of glue code that teams used to write themselves; the more of these you adopt, the less of your own infrastructure is doing work the platform now does for free.

Developer platforms — the surfaces you'd hand a builder. Claude Code is the CLI most developers actually live in day-to-day. MCP is the protocol that makes any tool you wire up reusable across clients (covered in API vs. MCP). Skills, hooks, subagents, and slash commands are the customization layer on top of Claude Code. Managed Agents and the Agent SDK are how you run longer, more autonomous jobs.

Surfaces — where non-engineers actually use Claude. claude.ai in the browser, the desktop apps on Mac and Windows, the iOS and Android apps, the Chrome extension, the IDE plugins, Projects (for persistent context per workspace), Artifacts (for inline outputs you can keep), and Cowork (for operator-style assistance). This is the column most knowledge workers ever see.

Enterprise & governance — the controls that matter once a workflow leaves experimentation. Free and Pro for individuals. Teams and Enterprise for the org. SSO/SAML and SCIM for identity. Audit logs, usage analytics, custom retention, and zero data retention for the compliance team. Fine-tuning is available, but it goes through Bedrock.

Distribution & trust — the deployment-and-compliance answer. Three places to run Claude (Anthropic API direct, Amazon Bedrock, Google Vertex AI) and four certifications that determine which regulated workloads can sit on top (SOC 2, ISO 42001, HIPAA BAA, GDPR/CCPA). The choice between direct API and a hyperscaler is usually about which paper trail the buyer's procurement team already accepts.

Why the map helps

Most product conversations only happen one card at a time. Engineers compare API primitives. CTOs compare Bedrock vs. Vertex. Compliance teams compare SOC 2 footprints. Operators compare what's inside the desktop app. Each of those conversations makes more sense when you can also see the other five — because the answer in one card often constrains the choices in another. Picking Bedrock changes which fine-tuning is available. Adopting Skills changes how Claude Code fits into your stack. Standardizing on Projects changes what "memory" means for your team.

Print the diagram. Mark the four or five chips you actually use. The empty space is the menu of things that are already built and waiting — most of them you can turn on without writing code.