Agentic AI with Claude Code: a guide for EU teams

A coding assistant suggests the next line and leaves the rest to you. Agentic AI with Claude Code takes the whole ticket, reads the codebase, changes the files that need changing, runs the tests and writes the commit. That difference decides how much of a developer's day actually moves, which is why engineering leads across Europe are asking about it now.

The guide below covers what agentic AI means, what Claude Code does inside a repository, what it costs per seat and what a European company has to settle about GDPR before the first session. Teams that want help moving agents from a trial to production can see the fixed prices for a Claude consultant.

What is agentic AI with Claude Code?

Agentic AI is software that is handed a goal and works through the steps on its own, meaning it plans, acts, checks the result and tries again without anyone typing each instruction. A chat window answers a question about code, whereas an agent opens the files, makes the change and runs the check that tells it whether the change worked.

Claude Code is Anthropic's agent for software work, and it runs in the terminal, in VS Code and JetBrains, in the Claude desktop app and in a browser.¹ You describe the task in plain language, for example to write tests for the auth module and fix any failures. Claude Code then plans the approach, edits across several files and verifies the result.

Adoption among developers moved faster than almost anyone predicted. The Pragmatic Engineer surveyed 906 engineers in early 2026, and 46 per cent named Claude Code their most loved tool, against 19 per cent for Cursor and 9 per cent for GitHub Copilot.²

Gartner expects 40 per cent of enterprise applications to include task-specific AI agents by the end of 2026, up from under 5 per cent in 2025.³ The same firm also predicts that over 40 per cent of agentic AI projects will be cancelled by the end of 2027, because of rising costs, unclear business value or weak risk controls. That second number is the more useful one for anyone planning a budget.⁴

What does Claude Code do in a real codebase?

The work falls into four jobs that most teams recognise from their own backlog, and each one still needs a person who reads the diff before it merges.

The module nobody dares to touch

Every company has a module written years ago by someone who has since left, with no documentation and a test coverage figure nobody says out loud. Claude Code reads the module and its callers, writes tests that pin the current behaviour, and then refactors step by step with the tests running after each change. A human still decides whether the new structure is the one the team wants to maintain, since the agent has no view of where the product is heading.

Tests, lint and dependency updates

Writing tests for untested code, fixing lint errors across a project, resolving merge conflicts and updating dependencies are the chores Anthropic lists first in its documentation.¹ Those tasks are dull enough that nobody schedules them, which is exactly why handing them to an agent for an afternoon clears weeks of backlog.

Commits and pull requests

Claude Code works directly with git, meaning it stages changes, writes commit messages, creates branches and opens pull requests.¹ In a CI pipeline, meaning the automated build that runs on every push, it can review code and triage issues through GitHub Actions or GitLab. The review still belongs to a person, because an agent that approves its own pull request has removed the one check that catches its mistakes.

Connections to your other systems through MCP

MCP, the Model Context Protocol, is an open standard for connecting AI tools to other systems, so Claude Code can read design documents in Google Drive, update tickets in Jira or pull data from Slack.¹⁵ Each connection is a small server you add and approve, and it reaches only what you give it access to.

How do you steer an agent that edits your code?

A file called CLAUDE.md in the project root is the steering wheel, meaning a plain text file with coding standards, architecture decisions and review rules that Claude Code reads at the start of every session.⁶ Writing ten lines in that file, for example which test command to run and which folders never to touch, changes the agent's behaviour more than any prompt typed during the session.

Skills package repeatable work for the whole team, such as a /review-pr command that follows your own checklist. Hooks run a shell command before or after an action, for example a formatter after every file edit.¹ Permission settings decide which commands Claude Code may run without asking, and a new team should start strict, since loosening a rule takes one line while undoing a bad deploy takes an evening.

Where does your code go under GDPR?

Claude Code runs locally, and to reach the model it sends your prompts and the model's outputs over an encrypted connection, including the contents of any file it reads during the session.⁷ The repository itself stays on your machine or your git server, while anything Claude opens travels as part of that conversation.

The account type decides the rest, and European teams get this wrong more often than anything else. Under commercial terms, meaning Team, Enterprise, the API and cloud platforms such as Amazon Bedrock, Anthropic does not train models on code or prompts sent to Claude Code. Commercial data is kept for 30 days as standard.⁷ Consumer Pro and Max accounts follow a training setting each user controls, so company code belongs on a commercial account and not on a developer's private subscription.

A company that must keep processing inside Europe can point Claude Code at Amazon Bedrock, where Claude models run through an EU cross-region inference profile covering regions such as Frankfurt, Ireland and Stockholm.⁸ On Bedrock, telemetry and bug reporting to Anthropic are switched off by default, which makes the data flow easier to explain to a data protection officer.⁷

What does Claude Code cost for a team?

Claude Code comes with the paid Claude plans, starting with Pro at $20 a month, and Max at $100 or $200 a month suits a developer who runs it all day.⁹ On the Team plan the Premium seat, at $100 per user per month billed annually, is the one sized for heavy agent work. The API route bills per token instead, through the Claude Developer Platform or through Bedrock.

A ten-person engineering team on Team Premium pays $12,000 a year, roughly €10,200, which pays back if each developer saves half an hour a week at a loaded cost of €50 an hour. Whether that pays back depends on one measurement, so count the tickets closed per week for four weeks before the seats arrive and four weeks after.

Through satori-claude the licences arrive on one invoice in euros, at €110 per user per month for a Premium licence plus €14 per user per month for support, after a one-time €490 setup. Teams that want MCP connections built into their own systems can see how we price that work on the managed services page, where every build is quoted as a fixed price after a scoping call. All satori. prices are fixed and exclude VAT.

Where to start this week

Agentic AI with Claude Code pays off on dull, well-tested work first and on risky, poorly-tested work last, so the first week should go to chores and not to the payment module.

Open your issue tracker, pick the three oldest tickets labelled as chores or tech debt, and write a CLAUDE.md of ten lines naming your test command and the folders Claude Code may not touch. In thirty minutes you have a file and a short list, which is everything the first session needs.

---

Sources

Footnotes

1. Anthropic (2026). Claude Code overview. Claude Code Docs. https://code.claude.com/docs/en/overview ↩ ↩² ↩³ ↩⁴ ↩⁵

2. The Pragmatic Engineer (2026). AI tooling for software engineers in 2026. https://newsletter.pragmaticengineer.com/p/ai-tooling-2026 ↩

3. Gartner (2025). Gartner predicts 40% of enterprise apps will feature task-specific AI agents by 2026. https://www.gartner.com/en/newsroom/press-releases/2025-08-26-gartner-predicts-40-percent-of-enterprise-apps-will-feature-task-specific-ai-agents-by-2026-up-from-less-than-5-percent-in-2025 ↩

4. Gartner (2025). Gartner predicts over 40% of agentic AI projects will be canceled by end of 2027. https://www.gartner.com/en/newsroom/press-releases/2025-06-25-gartner-predicts-over-40-percent-of-agentic-ai-projects-will-be-canceled-by-end-of-2027 ↩

5. Model Context Protocol (2026). Introduction. https://modelcontextprotocol.io ↩

6. Anthropic (2026). Store instructions and memories. Claude Code Docs. https://code.claude.com/docs/en/memory ↩

7. Anthropic (2026). Data usage. Claude Code Docs. https://code.claude.com/docs/en/data-usage ↩ ↩² ↩³

8. Amazon Web Services (2026). Regional availability of models in Amazon Bedrock. https://docs.aws.amazon.com/bedrock/latest/userguide/models-region-compatibility.html ↩

9. Anthropic (2026). Plans and Pricing. https://claude.com/pricing ↩