Anthropic — Partner Intelligence

Current state (as of 2026-05-17)

The Claude 4 family is the current shipping line — Opus 4.7 at the top (extended thinking + 1M context), Sonnet 4.6 in the middle, Haiku 4.5 at the bottom (to verify exact release dates beyond Frank's Jan 2026 knowledge cutoff). Claude Code is now a first-class CLI with SDK bindings and a stable skill format. The Model Context Protocol (MCP) — owned and stewarded by Anthropic — has graduated from spec to ecosystem standard, with first-party tooling from Vercel, Cursor, and Codex consuming the same wire format. Claude for Work and Claude for Enterprise tiers continue to anchor the commercial lane.

Product map

• Claude (model family) — Opus 4.7 (reasoning + 1M context), Sonnet 4.6 (balanced), Haiku 4.5 (fast). Frank works against Opus 4.7 by default.
• Claude Code (CLI + SDK) — the agentic build harness. Stable skills/agents/commands/hooks format. The harness underneath every shipped FrankX repo.
• Claude API — direct API access via @anthropic-ai/sdk (TS) and anthropic (Python). Prompt caching, tool use, vision, batch, files, citations, memory.
• Claude Agent SDK — managed-agent framework for long-running autonomous loops. Sibling lane to Vercel AI SDK (web) and Google ADK (enterprise) in the Starlight three-lane portfolio.
• Claude for Work — team tier with shared chats, projects, and admin controls.
• Claude for Enterprise — SSO, audit, data residency, expanded context, enterprise procurement.
• Model Context Protocol (MCP) — open spec owned by Anthropic. Servers expose tools/resources/prompts over stdio or HTTP. Frank ships SIS as a 31-tool MCP server.
• Claude Code skills marketplace — community + first-party skills (vercel:*, code-review:*, superpowers:*, agent-sdk-dev:*, etc.).
• Open-source artifacts — @anthropic-ai/sdk (MIT), claude-code (proprietary CLI, MIT skills), MCP reference servers and SDKs (MIT).