AI · AI agents and automation
Claude Code
Anthropic's agentic coding tool for terminal, IDE, desktop and web
At a glance
Claude Code is Anthropic's agentic coding tool that reads a codebase, edits files across a project, runs commands and works with git to commit changes and open pull requests. It runs in the terminal, in VS Code and JetBrains IDEs, in the Claude desktop app and in the browser, all sharing the same engine and project settings.
- Category
- AI agents and automation
- Best fit
- SME · Mid-market · Enterprise
- Pricing
- See pricing below
- In Adam’s stack
- No
Who Claude Code is best for
Developers, technical founders and engineering teams who want an AI that completes real coding tasks such as features, bug fixes, tests and refactors rather than only suggesting snippets. It also suits automation-minded operators who script repeatable jobs in CI or on a schedule.
Key features
- Plans and makes multi-file changes, then runs tests and commands to verify them
- Git workflow support: branches, commits and pull requests, plus GitHub Actions and GitLab CI/CD
- MCP connections to tools like Google Drive, Jira and Slack
- Project instructions via CLAUDE.md, reusable skills and hooks
- Parallel sub-agents and the Agent SDK for building custom agents
- Cloud routines and scheduled tasks that run without your computer on
Why it’s worth it
It can take a well-described task from plan to tested pull request, which compresses hours of routine engineering work and lets small teams ship more without extra headcount.
Things to consider
- Large or long-running tasks consume usage quickly; heavy users often need a Max plan or pay-per-token API billing
- Output still needs code review, and results depend heavily on clear instructions and good tests
- It assumes some comfort with code and the terminal, so non-technical users may prefer Claude Cowork
For Australian businesses
Anthropic announced a Sydney office in March 2026 and said it is exploring local compute capacity in Australia, but Australian data hosting is not confirmed. Published plan prices are in US dollars.
Claude Code pricing
Pricing as published by Claude Code
Included with paid Claude plans (not the Free plan). Pro US$20/month, or US$17/month billed annually. Max from US$100/month. Team Standard seat US$25/seat/month, or US$20 billed annually; Premium seat US$125/seat/month, or US$100 billed annually. Enterprise by quote. Can also be used with pay-as-you-go API billing through an Anthropic Console account.
Source: claude.com/pricing. Checked 8 October 2026. Prices change often, so confirm on the vendor’s site before you buy.
Alternatives to Claude Code
Other tools listed under AI agents and automation. Tools from Adam’s stack are marked.
OpenClaw
In Adam’s stackOpen-source, always-on agent you host yourself
SMEMid-marketClaude working through tasks across your files and apps
SMEMid-marketEnterpriseRelevance AI
AustralianBuild teams of AI agents without code
SMEMid-marketEnterpriseAI agents connected to Zapier’s app library
SMEMid-marketOpen-source automation you can self-host
SMEMid-marketEnterpriseAI assistants for email, meetings and admin
SMEBuild agents for Microsoft 365
Mid-marketEnterpriseAI agents inside Salesforce
Enterprise
FAQ
Claude Code: common questions
Is Claude Code free?
No. It needs a paid Claude subscription (Pro and above) or an Anthropic Console account billed per API usage. The lowest-cost entry is Claude Pro at US$20 a month.
Can non-developers use Claude Code?
Some non-developers use it to build simple tools and automations, and there is a desktop app and web version that avoid the terminal. For documents, spreadsheets and research tasks, Claude Cowork is the more natural fit.
Claude Code vs GitHub Copilot?
GitHub Copilot is best known for in-editor suggestions and chat, while Claude Code is built to carry out whole tasks itself: planning, editing many files, running commands and opening pull requests. Many teams use an IDE assistant for line-level help and Claude Code for larger delegated work.
Can’t find a tool that fits?
When every option forces a workaround, our trusted build partners can build it: apps, automations and AI agents designed around how your business actually works.