Skip to content
Talk to an architect
Agents and automation

Where an application gets its own agent, and its own credentials.

The Claude Developer Platform provides API access for building applications and agents on Anthropic's models, including the tooling around agent behaviour. Our work is scoping integration identities and building inside the permission model.

The developer platform is how custom applications call models directly. Each integration becomes a machine caller, which is an identity to scope rather than a key to paste.

What it is

The Claude Developer Platform provides API access for building applications and agents on Anthropic's models, including the tooling around agent behaviour.

It is for organizations building something bespoke, at the point where the integration acquires credentials and starts acting on internal systems.

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

What it does

Applications act as machine callers

Which brings them under the same discipline as every other non-human identity.

Agent behaviour is defined in the build

So guardrails belong in the design rather than in a policy document afterwards.

Where it fits

L4, agents and automation, governed at L1. An application calling a model is straightforward. The same application reaching into your systems of record is a machine caller, and that is where scope, ownership, and rotation apply.

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

Scoping the integration identity

What the application may reach in your estate, designed rather than granted broadly to get it working.

Building it inside the permission model

Where it touches Atlassian, we build on Forge so it inherits governance rather than holding its own keys.

Guardrails and evidence

Stop conditions, audit trail, and cost governance defined with the build.

Where it earns its place

A team building an internal assistant

The prototype uses a broad credential. Production should not.

An organization with several integrations

Each one is a caller, and collectively they are a population nobody has listed.

Questions we get

Should we build or connect?
Connect through the standard where it covers the need. Build where it does not, and build inside the permission model.
Who owns the integration afterwards?
That question has to have an answer before it goes to production, and it is frequently the one nobody asked.

Anthropic's own page for Claude Developer Platform, 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