Anthropic · Technologies
Claude Code
The coding agent your engineers delegate to.
Claude Code is Anthropic’s coding agent, running in the terminal, the desktop app, your IDE and the cloud. Engineers hand it whole tasks: features, refactors, tests and reviews, and it works across entire repositories with your rules encoded. In our experience it is the strongest coding agent available, and we use it daily on our own work.
CODING TASKS · EXAMPLE SPRINT
TASK
SCOPE
REVIEW
STATUS
Bug-Fix-Batch
Repo wide
PR review
DONE
Test-Coverage
Service layer
PR review
DONE
Docs-Update
Repo
PR review
DONE
Refactor-Auth
Module
In review
RUNNING
direct-push-hotfix
No review
Skipped
RISK
Sample sprint
done · running · risk
In plain terms
Autocomplete suggests. Claude Code delivers.
The shift is from help with lines to delegation of tasks. Here is what changes.
Without it
- Engineers typing every line, assisted or not
- Routine maintenance eating the best hours of the day
- One task at a time, serially
- AI coding happening ad hoc on personal accounts
With it
- Whole tasks delegated and returned as reviewable pull requests
- Mornings that start with finished pieces of routine work
- Parallel sessions working across the codebase
- One governed rollout with rules the team agreed to
What CG TECH can do with Claude Code
The work, broken into the parts that matter.
One agent across every surface
The terminal, the desktop app, IDE extensions and cloud sessions share one account and one configuration, and every Team and Enterprise seat now includes it.
one agent, every surface
Delegation that sticks
Project instruction files teach Claude Code your conventions, skills and plugins package your team’s workflows, and hooks enforce the rules that are not negotiable.
your standards, enforced by default
Built for the hard refactors
A context window of up to 1 million tokens holds large codebases whole, subagents split big jobs into parallel workstreams, and everything lands as a pull request for human review.
large codebases, handled whole
Speed with the brakes fitted
Permissions are explicit, admin controls manage access and spend on Team and Enterprise plans, and we pilot on real tickets and measure before scaling.
speed with the brakes fitted
How an engagement runs
From autocomplete to safe delegation, step by step.
01
Assess
We map your repos, workflows and where delegation pays fastest.
02
Prepare
Instruction files, permissions and review rules set up first.
03
Pilot
A small team runs Claude Code on real tickets, measured honestly.
04
Scale
Rollout grows with the evidence, with costs tracked.
Questions we hear a lot
Common questions about Claude Code
What is Claude Code?
Claude Code is Anthropic’s coding agent. It runs in the terminal, the desktop app, your development environment and the cloud, and engineers hand it whole tasks rather than single lines: features, refactors, tests and reviews. It works across entire repositories with your own rules encoded.
Does Claude Code replace developers?
No. It changes what they spend time on. The routine work gets delegated and the judgement, architecture and review stay human. Teams ship more, not fewer people.
How is Claude Code licensed?
It is included on paid Claude plans, including every Team and Enterprise seat, with heavier users on higher usage tiers. We model expected usage during the pilot so the bill is a decision, not a surprise.
Is our code used to train models?
On Team and Enterprise plans, no, business data is excluded from training by default. We confirm the right plan and settings as part of the rollout.
Claude Code or Codex?
They are the two leading coding agents and we use both. Claude Code is exceptionally thorough on hard refactors and long tasks; Codex is fast and token efficient. We recommend per team and workload, honestly.
What does it do that autocomplete does not?
Autocomplete finishes the line you are typing. Claude Code takes a described outcome, works out which files need to change, makes the changes across the repository and runs the tests. The unit of work is a task, not a keystroke.
How should we review what it writes?
Exactly as you would review a colleague’s work, and no more loosely. Everything through pull request, tests passing, a human approving. The speed gain is in getting to a reviewable change quickly, not in skipping the review.
Does it work with our existing repositories and tooling?
Generally yes, and that is the point of it running in the terminal and your development environment rather than a separate website. It works with the repository, the tests and the review process you already have.
Ready when you are
Putting a coding agent to work? Let us talk.
A discovery session maps your workflows, your risks and your quick wins. You keep the plan either way.
What to expect
- A consultant replies within 4 business hours
- Session booked to understand your requirements
- We will provide you with a fixed price quote