Skip to content
Talk to an architect
Agents and automation

An assistant with a terminal and your repositories.

Claude Code is an agentic coding tool that operates in the terminal and against a working repository, taking on multi-step development work rather than completing lines. Our work is branch protection consistency and the credential boundary an agentic coding tool inherits.

Claude Code works in the terminal and against real codebases. What it can reach is decided by the credentials on the machine it runs on, which is a narrower question than it sounds and a more urgent one.

What it is

Claude Code is an agentic coding tool that operates in the terminal and against a working repository, taking on multi-step development work rather than completing lines.

It matters to governance because it inherits whatever the developer's environment already holds: repository access, cloud credentials, and any token sitting in the shell.

source build review deploy run scope check built inside the permission model, not beside it L1 L2 L3 L4

What it does

It acts with local credentials

Which means the developer's environment is the permission boundary.

It works on real repositories

So branch protections and review requirements are the controls that actually apply.

Where it fits

L4, agents and automation, bounded by L1 and L2. It acts with a developer's own reach. In an estate where branch protections are inconsistent and local credentials are broad, it makes both facts operational rather than theoretical.

L4

Agents and Automation

Rovo, Agents in Jira, Forge, MCP with Claude and Copilot, agent lifecycle, usage and cost governance.

Atlassian Anthropic
L3

Governance and Change

Permission architecture, audit and compliance, ITSM and change control, change management, strategic reporting and budgets.

Atlassian Guard Jira Service Management Strategy Collection Jira Align
L2

Platform and Migration

Migration of every kind, tool consolidation, licensing, standardization, the system of work.

Atlassian Miro AWS Azure
L1

Identity and Access

Human and non-human identity, SSO, SCIM, least privilege, access reviews, Guard cleanup, Agent SSO readiness.

Atlassian Guard Okta

load-bearing, bottom to top

What we do with it

Branch and protection consistency

One protection model across repositories, which is what makes agentic development reviewable.

Connecting it to the estate

Where it reaches into Atlassian, the connecting identity is designed rather than borrowed.

Usage policy

What may be run against production paths, and what evidence is kept.

Where it earns its place

An engineering group adopting agentic coding

The tool is easy. Consistent branch protections across repositories are the prerequisite.

An estate with broad local credentials

A developer machine holding wide cloud access is a finding whether or not an assistant is present.

Proof

AI Innovator Finalist, 2026

AI Innovator Finalist, 2026

Atlassian Partner Awards, 2026

Questions we get

Does this need special permissions?
It needs no more than the developer has, which is exactly the point worth examining.
How is this different from Rovo Dev?
Different vendor and surface. Rovo Dev works inside the Atlassian estate. This works in the terminal.

Anthropic's own page for Claude Code, opens in a new tab

Find out what an agent would inherit.

Fixed scope. The assessment reads the three layers an agent lands on, identity, platform and governance, before anything is switched on. You get the findings, the ownership gaps, and the order to close them in.

Get an agent readiness assessment

By sending this you agree to our privacy policy.

Not ready? Talk to an architect