AI systems · Product
Claude Code
What is Claude Code?
Claude Code is Anthropic’s agentic development tool for inspecting projects, editing files, using tools, and verifying work under configurable permissions.
Its documented loop gathers context, acts, and verifies. Project instructions, hooks, and subagents extend the workflow.
A tool’s successful execution is not proof that a change meets its specification; independent acceptance evidence remains necessary.
Related entities
- Altitude, depth and rangeAltitude, depth and range are Felix Rieseberg’s three directions beyond speed for AI work: pursue outcomes, use expert instruments and combine disciplinary methods.
- Claude DuetClaude Duet is Anthropic’s proactive personal AI agent for delegated work in connected apps, introduced as an invitation-only research preview in October 2026.
- Data minimizationData minimization limits the personal information collected, used and retained to what is necessary for a specified purpose.
- Editorial operationsEditorial operations is the governed process connecting audience research, content, site architecture, verification, publication, and ongoing maintenance.
- Maker-checker reviewMaker-checker review is a control pattern in which one agent or person produces work and a separate one verifies it against a specification before it ships.
- AI evaluationsAI evaluations are repeatable tests of a model or agent workflow against defined tasks, acceptance criteria, and observable failure categories.
- Model Context ProtocolThe Model Context Protocol (MCP), introduced by Anthropic in November 2024, is an open standard for connecting AI applications to external tools and data sources.
Field notes covering Claude Code
- Altitude, Depth, Range: More Ambitious AI PromptingHow to be more ambitious with AI: Felix Rieseberg’s altitude, depth and range framework, fourteen templates and a practical, bounded Prompt Elevator.
- When Building Gets Cheap, Product Judgment Gets ExpensiveClaude Code expands the space of possible products. The differentiator is no longer a convincing specification—it is choosing, testing and shipping the right experience.
- More Agents. One Person Who Signs Off.Leaders are using AI more often, but adoption is not ability. As execution accelerates, accepted work—not generated output—becomes the real productivity measure.
- Harness²: The Agent Harness That Rewrites ItselfA harness makes an agent reliable. A harness for the harness makes it get better: every correction is captured, promoted, enforced or deleted.
- When Code Is Cheap, What Still Protects a SaaS?AI lets anyone clone a feature over a weekend. The moats that remain are data, workflow, distribution and trust—and you can audit yours in two minutes.
- The AI Subscription Bargain Has a CatchA response to SemiAnalysis’s Anthropic-versus-OpenAI value study: why API-equivalent dollars, usable capacity, and accepted work are three different things.
- From Content Writer to Website OperatorClaude Code changes the boundary of a writing job: from handing over a document to owning a governed website pipeline. The opportunity, the workflow, and the limits.
- AI Development: Evidence Before AutonomyA convincing demo is not a release gate. How to evaluate agent-built software, contain failure, and measure the whole delivery loop instead of the typing speed.
- Loop Engineering: The Definitive Field GuideThe leverage point in software has moved from writing prompts to designing the loops that prompt your agents. The complete field guide — Ralph, maker-checker, worktrees, AGENTS.md, memory, and MCP — from someone who runs these loops across a live portfolio.
- The Agent Harness — Setting Up Claude Code Like You Mean ItAn AI coding model on its own is a brilliant intern with amnesia. The harness — twelve parts of configuration, rules, and checks you wrap around it — turns it into a teammate you'd put on a real codebase.
Sources & identifiers
Search disciplinesSite structureAI systemsLocal searchDistribution & growthAgentic commerceHover to trace relationships · click to open