Everything Claude, for GTM & marketing teams
Clear, current, hands-on guides to Claude, Claude Code, the API, Dispatch, Routines, MCP, and Skills - written by an operator who runs them daily. No hype, just what works and how to do it.
Two ways in
Land on the guides through the lens that fits you: the role you sit in, or the funnel stage you are trying to move.
Start with your seat
Every use case, skill, prompt, and guide, organized by the role you actually sit in.
Follow the funnel
The whole GTM motion mapped to Claude plays, one stage at a time.
Prefer a guided route?
Curated, in-order tracks through the library. Follow one start-to-finish, or jump straight to any guide below.
New to Claude
Never used Claude seriously? Get oriented, pick the right model, and learn to prompt it well.
Master Claude Code
Go from install to running multi-agent coding workflows you can trust.
Automate your GTM with Claude
Put Claude on a schedule and run go-to-market work unattended.
Build on the Claude API
Ship production features on the Developer Platform, from first call to agents.
Browse every guide
Start Here
5 guidesWhat is Claude? The whole ecosystem, mapped
Claude is the family of AI models built by Anthropic, plus the products built on top of them: the Claude apps (claude.ai...
Claude models compared: Fable 5, Opus, Sonnet, Haiku
Fable 5 was briefly the most capable Claude model, but as of June 2026 Anthropic has withdrawn it from general availability...
Claude plans and pricing: which one is worth it
As of June 2026, most casual users should be on Free, most people who use Claude every workday should pay $20 for Pro, and...
Which Claude should I use? App vs Claude Code vs API
If you are thinking, drafting, or doing a one-off, use the Claude app. If you want Claude to do multi-step work against your...
Getting started with Claude: your first hour, done right
Sign up free at claude.ai (or install the desktop and mobile apps), then spend your first hour on a real task instead of a toy...
Claude apps
9 guidesClaude Projects: persistent, context-rich workspaces
A Claude Project is a workspace that holds custom instructions and a set of knowledge files, so every chat you start inside it...
Claude Artifacts: interactive outputs you can ship
A Claude Artifact is a standalone output, a document, a chunk of code, an interactive page, a diagram, that Claude renders in...
Claude Memory: how it works and how to steer it
Claude Memory lets Claude keep facts about you and your work across separate conversations, so it does not start from zero...
Web search in Claude: answers beyond the cutoff
Web search lets Claude pull current information from the live web and cite the sources it used, instead of relying only on...
Claude voice mode: talk to Claude with /voice
Voice mode lets you talk to Claude out loud and hear its responses instead of typing. It turns Claude into something you use...
Files & vision in Claude: PDFs, images, and docs
Claude can read the files and images you give it: PDFs, slide decks, spreadsheets, documents, and screenshots or photos....
The Claude desktop app: multi-session and diffs
The Claude desktop app is the Mac and Windows client for Claude. Beyond the web app it can connect to MCP connectors and work...
Claude on mobile: the app, Claude Code, remote control
The Claude mobile app (iOS and Android) is the full Claude assistant on your phone, including voice. It can also reach back to...
Claude Connectors: link Slack, Drive, Calendar & more
Connectors link Claude to the tools you already use, Slack, Google Drive, Google Calendar, your CRM, and more, so it can read...
Claude Code
13 guidesClaude Code: install and your first agent run
Claude Code is an agentic tool that runs in your terminal, your editor, a desktop app, or the web, and does multi-step work...
Claude Code everywhere: CLI, IDE, desktop, web
Claude Code is the same agent across four surfaces: the CLI (terminal), IDE extensions (VS Code and JetBrains), the desktop...
Context & CLAUDE.md: keeping Claude Code on track
CLAUDE.md is a file Claude Code reads at the start of every session. It holds the standing context and rules for the work: how...
Plan mode & permissions in Claude Code
Plan mode makes Claude Code read and propose a plan without changing anything, so you approve the approach before it acts....
Checkpoints in Claude Code: rewind without git
Checkpoints are automatic save points Claude Code creates as it works, so you can rewind to a known-good state if a change...
Claude Code slash commands: the reference
Slash commands are the controls you type inside Claude Code to steer a session: clear or compact the context, rewind a bad...
Subagents in Claude Code: agent teams that scale
A subagent is a worker Claude Code spins up with its own clean context to handle one bounded piece of a larger job, then...
Claude Code hooks: automate format, lint, and alerts
A hook is a shell command Claude Code runs automatically on an event, before or after it uses a tool, or when it finishes. You...
MCP in Claude Code: connect your tools
MCP is the standard Claude Code uses to reach the tools your data lives in, your CRM, your warehouse, an enrichment service,...
Skills in Claude Code: expert knowledge on tap
A skill in Claude Code is a small folder with a SKILL.md file that teaches Claude how to do one task well. Claude loads it on...
Claude Code settings & permissions
Claude Code settings live in settings.json and tune how the agent behaves: which model, which tools, and, most importantly,...
Claude Code + git & GitHub: commits, PRs, CI
Claude Code works the full git and GitHub workflow: it writes changes, commits them with a real message, opens pull requests...
Claude Code: cloud vs local execution
Claude Code is the same agent whether it runs locally on your machine or in the cloud. Run it locally for hands-on work where...
Build with Claude
12 guidesThe Claude API: a quickstart
The Claude API lets your own software call Claude, instead of you typing in the app. You get a key from the console, install...
Tool use with the Claude API
Tool use lets Claude call functions you define instead of only writing text. You describe each tool with a name, a...
Streaming responses from Claude
Streaming sends Claude's response token by token as it is generated, instead of making you wait for the whole thing. It...
Prompt caching: cut Claude API cost and latency
Prompt caching lets Claude reuse a stable chunk at the front of your prompt, the system prompt, tool definitions, or a long...
Structured outputs: get clean JSON from Claude
Structured outputs make Claude return data in a shape you define, a JSON schema, instead of prose you have to parse. You...
Adaptive thinking & effort on the Claude API
Extended thinking lets Claude reason more before it answers, and effort controls how much of that reasoning it does. More...
Files, vision, PDFs & citations on the API
The Claude API can take real files and images directly, PDFs, spreadsheets, screenshots, charts, instead of you scraping text...
Batch API & token counting for cost control
The Batch API processes large volumes of requests asynchronously at roughly half the cost of real-time calls, in exchange for...
The Claude Agent SDK: build your own agents
The Claude Agent SDK is Claude Code's engine, exposed for you to build on: the same agentic loop, tool handling, subagents,...
Managed Agents: server-run, stateful Claude agents
Managed Agents let Anthropic run the agentic loop for you and host the tool sandbox and the agent's state on the server side,...
Server-side tools: code execution, computer use, web
Server-side tools are capabilities Anthropic hosts and runs for you: code execution, web search and fetch, and computer use,...
Claude on Bedrock, Vertex, Foundry & AWS
Claude runs on the major cloud platforms, Amazon Bedrock, Google Vertex AI, and Microsoft Foundry, in addition to the direct...
Automate & Schedule
5 guidesClaude Routines: scheduled cloud agents, explained
Claude Routines are scheduled jobs that run in the cloud on a cadence you set, without you or your machine involved. You...
Claude Dispatch: run desktop tasks from your phone
Claude Dispatch lets you send a task from your phone to the Claude running on your own computer, which does the work locally...
Background agents: run many Claude agents at once
Background agents let you run several Claude jobs at the same time, each on its own task, and watch and steer them from one...
/loop vs Routines vs scheduled tasks: which to use
There are three ways to repeat work in Claude, and they are for different kinds of repeat. Use /loop when you are iterating on...
Remote control: drive local Claude Code from anywhere
Remote control lets you run a Claude Code session on your own machine while driving it from a browser or your phone. The work...
Core Concepts
6 guidesPrompting Claude: what actually moves the needle
The things that reliably improve Claude's output are mostly structural: paste the real source material instead of describing...
Context & memory in Claude, explained
Context is everything Claude can see right now, the conversation, the files you shared, the tool outputs, inside a fixed-size...
What is MCP? The Model Context Protocol, explained
MCP, the Model Context Protocol, is an open standard for connecting an AI model to external tools and data through one...
What are Claude Skills? And when to use them
A Claude Skill is a small folder, a SKILL.md file plus any supporting files, that teaches Claude how to do one task well....
What is an AI agent? The agentic loop, explained
An AI agent is a model you give a goal, a set of tools, and permission to loop: it looks at the situation, picks a next...
Claude's tools: client-side vs server-side
Claude's tools are the actions it can take beyond generating text. Client-side tools run in your environment, your code or...
Govern
5 guidesClaude data & privacy: training, retention, ZDR
Whether Claude uses your data to train depends on your tier: business and API usage is not used to train models by default,...
Running Claude agents safely
Running a Claude agent safely is about the actions, not the reasoning: reading and thinking are low risk, but anything that...
Claude compliance: SOC 2, ISO, HIPAA, enterprise
For a regulated team, compliance is the gate before capability: the model does not matter until the paperwork clears....
Controlling Claude cost across app, Code & API
Claude cost is a design choice, not a surprise. The biggest lever is model choice, using a cheaper model where a stronger one...
Claude for teams: admin, SSO & governance
Running Claude across a team needs an admin layer that a single user does not: seats and roles to control who has access,...
GTM Governance
5 guidesRolling Claude out to a sales team: the adoption playbook
AI adoption on a sales team is a rollout problem, not a tooling problem. The sequence that works: stand up the admin layer...
How to measure the ROI of Claude in GTM (a model you can defend)
To measure AI ROI in a GTM org, keep three separate ledgers instead of one blended number: a time ledger (minutes per play...
The AI security review a RevOps lead runs before an agent touches the CRM
An AI security review for a GTM agent answers five questions before the agent gets anywhere near the CRM: what data it can see...
Build a shared prompt and skill library your GTM team actually uses
A team prompt library works when it is organized around plays, each with one owner, and split across the two containers Claude...
Claude cost control for a GTM org: seats, Code, and routines on one ledger
AI cost control for a GTM org means putting three different bills on one ledger: app seats (a fixed price per person, standard...
Compare
6 guidesClaude vs ChatGPT for sales: which one actually helps a rep sell
For the daily work of selling, account research, call prep, follow-ups grounded in your CRM, and pipeline questions, Claude is...
Claude vs Gemini for GTM: home-field advantage vs the away game
If your GTM runs inside Google Workspace, Gmail, Sheets, Docs, Meet, Gemini has a real home-field advantage: it is already in...
The best AI for cold email: the model writes, the sender sends
The best AI for cold email is two tools, because cold email is two jobs. The writing job goes to a frontier model, and Claude...
The best AI for sales research: the model reasons, the data provider verifies
The best AI for sales research is two tools, because account research produces two kinds of facts. Verified fields (headcount,...
The best AI for RevOps: whoever owns the loop
RevOps buys systems, so the best AI for RevOps is the one that should own the loop you are automating. If the loop lives...
Claude vs AI SDR tools: build the agent or rent the rep
Buy an AI SDR tool (11x, Artisan, AiSDR) when you have no builder on staff and need outbound volume running in weeks: you get...