Claude Code

A practical, docs-grounded guide to Claude Code's Agent View — the multi-session dashboard Anthropic released on May 11, 2026. Covers parallel dispatch, automatic git-worktree isolation, background sessions, billing implications, and runaway-cost guardrails for serious team use.

Claude Code by Anthropic is an agent-based development tool that autonomously codes by understanding entire codebases. Available via CLI, IDE, Desktop, and Web. Complete 2026 guide covering Opus 4.6, MCP, Agent Teams, and advanced features.

A grounded guide to the Forward Deployed Engineer (FDE) role pioneered by Palantir and now being mass-hired by OpenAI, Anthropic, Cursor, and even Big-4 consulting firms in 2026. Covers origin, scope, skills, compensation, career paths, how FDE differs from SES/SI and from generic consultants, and where this role fits for Japanese enterprises trying to ship AI beyond the PoC stage.

Figma's official MCP catalog connects the Figma MCP server to Claude Code, Codex, Cursor, and Devin, covering setup steps, pricing, and security for each.

A guide to Plaud's official MCP server (@plaud-ai/mcp) and CLI: search recordings, pull transcripts, and read AI summaries directly from Claude, ChatGPT, Cursor, and other AI clients. Covers one-command setup, the 7 MCP tools and 6 skills, terminal commands, meeting-to-follow-up workflows, and privacy considerations — based on the official docs.

**[Mosaic (mosaic.inc)](https://mosaic.inc/) is a desktop tool that runs multiple AI coding agents ([Claude Code](https://claude.com/product/claude-code) / Codex / OpenCode) in parallel from a single UI**, and on top of that offers **"SHARED CONTROL" — a rare feature in 2026 that lets multiple people live-edit a single Claude Code session together**. **The core of SHARED CONTROL**: spin up a session, a teammate joins the same terminal, and **you both see each others cursors, prompts, and output in real time** — genuinely shared control, not screen-share theater. The experience of Google Docs or VS Code Live Share, applied to a Claude Code session. Use cases (see the standing [request in Anthropic issue #60082](https://github.com/anthropics/claude-code/issues/60082)): pair programming, team debugging, onboarding, live review, and division of labor (Ali refactors the auth middleware while Shubham adds the rate-limit test — same session). **Parallel-ops layer**: each agent gets a **Git-worktree-isolated workspace**, and 5-10 agents can develop different branches / features concurrently with zero file collisions or state interference. **Position**: in the rapidly maturing late-2026 parallel-Claude-Code market, Mosaic competes with **[Conductor](https://www.ycombinator.com/companies/conductor) (YC, Mac-native)**, **[Superset](https://superset.sh/) (three ex-YC CTOs, 10+ concurrent)**, **[Herdr](../columns/herdr-terminal-agent-multiplexer-2026-07) (terminal-native, Rust)**, and Product-Hunt entries like [Claudy](https://www.producthunt.com/products/claudy) / [Multi-Claude](https://www.producthunt.com/products/multi-claude) — its distinctive differentiation is **real-time SHARED CONTROL**. Target users: solo developers, startup CTOs, staff engineers, plus **teams that want pair programming and live review with AI agents in the loop**. Combined with [Command Code taste-1 learning](../columns/commandcode-taste-1-personalized-coding-agent-2026-07), [the grill-me skill](../columns/grill-me-agent-skill-2026-07), and [Crit.md HITL review](../columns/crit-md-local-first-agent-review-2026-07), it forms a **"parallel × personalized × thoroughly reviewed × real-time collaborative" late-2026 AI dev stack**.