CORRECT BY DESIGN

Code now ships at machine speed. Govern it at the same pace.

AI writes the code. Arko is the independent check that decides what ships — and signs the proof. One control layer across security, code health, cost and compliance — in your IDE, your agents, your pipeline, and up to a fully air-gapped deployment.

Know Your Code Risk. Prove What's Fixed. Ship With Evidence.Know Your Code Risk. Prove What's Fixed. Ship With Evidence.Know Your Code Risk. Prove What's Fixed. Ship With Evidence.Know Your Code Risk. Prove What's Fixed. Ship With Evidence.
Architecture Overview
Your AI writes code. ARKO understands
what it builds before it ships.
From raw codebase to full attack surface. ARKO maps architecture, models threats,
and scores risk in real time, so you ship fast without shipping vulnerabilities.
Inputs
Codebase
Files as you write
.ts.py.go.js
AI Copilot Output
Generated code from copilots and AI agents, via MCP
CursorCopilotAntigravityWindsurfClaude Code
App Config & Routes
Dependencies, env, API surface
package.json.envroutes
Engine
DevSecOps Context Engine
Reasons about architecture - Not a scanner
Always On
Code Analysis
Threat Modeling
Business Context
Attack Path Analysis
Outputs
74
Code Health Score · 74/100
one score across security, maintainability, cost and architectural drift
3
severe
Threat Model
Ranked attack paths, blast radius
PCI
SOC2
Compliance Map
Findings linked to your frameworks
AI
fix ready
Fix with AI
1-click context-aware fix, paste & ship
ARKO decides if it ships - full DevSecOps context, not pattern matching.
Use cases
arko/ ai-chat.ts6 ISSUESCODE HEALTH SCORE92%Code Health Score · 92/100CRITExposed API KeyLine 3 · hardcoded secretCRITSQL InjectionLine 7 · template literalCRITPrompt InjectionLine 10 · unsanitized inputWARNPII Leaked to AILine 14 · user data in ctxWARNNo Rate Limitingchat() · no throttlearko/ ai-chat.tsSECURECODE HEALTH SCORE4%Code Health Score · 4/100FIXEDAPI Key → env variableprocess.env.API_KEYFIXEDSQL → parameterized querydb.query($1, [id])FIXEDPrompt → sanitizedinjection blockedFIXEDPII → redacted before AIredactPII() appliedFIXEDRate limiter + filtermiddleware added

AI writes the code. ARKO decides if it ships based on the score.

AI copilots generate faster than humans can review. ARKO continuously analyses AI‑written code in real time, mapping risk to real attack paths – before it reaches production.

CODE TRUST & HEALTH

Everything Arko covers in AI-written code

Tools scan code. Arko understands it in context — then answers for security, health, cost and developer experience, all from one graph.
What Arko catches

AI SAST

The insecure code AI tools tend to write — from injection to unsafe data handling — caught as you build, with a clear fix.

Hardcoded secrets

API keys, tokens and credentials caught before they ever reach a commit.

Vulnerable dependencies

Risky open-source packages and supply-chain issues, with an SBOM for every build.

Cloud & IaC misconfig

Infrastructure and cloud config that quietly leaves you exposed — flagged with the fix.

AI-era risks

Prompt injection, personal data leaked to the model and unsafe tool calls — the new risks AI code introduces.

Threat modelling

Ranked attack paths and real business impact — not just a long list of findings.

Validated by Arko's decision engine before it reaches you — real risks, not noise.
One graph, many lenses

Security

Vulnerabilities, secrets and attack paths — caught and fixed at the moment code is written.

Health

One score for whether your code is correct — security, compliance and maintainability, trending over time.

Cost

Forecast the cloud spend of code as it's written — and the decisions bending the curve.

DevEx

Change-failure rate, review latency and rework — tied back to the architecture that causes them.

Where it runs
In your IDE · VS Code, Cursor, Windsurf, VSCodium
Inside AI agents · Claude Code, Cursor, Windsurf · via MCP
In your terminal · gate changed files, fail the build on real risk
Repositories · build scans
CI/CD pipelines · Enterprise
Every finding — tagged by where it ran: agent, IDE, terminal or CI — rolls up to your Code Health Score: one score across security, maintainability, cost and architectural drift.
OWASP Top 10PCI DSSSOC 2ISO 27001NISTGDPRHIPAACISMITRE ATT&CK
CODE TRUST & HEALTH

Everything Arko covers in AI-written code

Tools scan code. Arko understands it in context — then answers for security, health, cost and developer experience, all from one graph.
What Arko catches

AI SAST

The insecure code AI tools tend to write — from injection to unsafe data handling — caught as you build, with a clear fix.

Hardcoded secrets

API keys, tokens and credentials caught before they ever reach a commit.

Vulnerable dependencies

Risky open-source packages and supply-chain issues, with an SBOM for every build.

Cloud & IaC misconfig

Infrastructure and cloud config that quietly leaves you exposed — flagged with the fix.

AI-era risks

Prompt injection, personal data leaked to the model and unsafe tool calls — the new risks AI code introduces.

Threat modelling

Ranked attack paths and real business impact — not just a long list of findings.

Validated by Arko's decision engine before it reaches you — real risks, not noise.
One graph, many lenses

Security

Vulnerabilities, secrets and attack paths — caught and fixed at the moment code is written.

Health

One score for whether your code is correct — security, compliance and maintainability, trending over time.

Cost

Forecast the cloud spend of code as it's written — and the decisions bending the curve.

DevEx

Change-failure rate, review latency and rework — tied back to the architecture that causes them.

Where it runs
In your IDE · VS Code, Cursor, Windsurf, VSCodium
Inside AI agents · Claude Code, Cursor, Windsurf · via MCP
In your terminal · gate changed files, fail the build on real risk
Repositories · build scans
CI/CD pipelines · Enterprise
Every finding — tagged by where it ran: agent, IDE, terminal or CI — rolls up to your Code Health Score: one score across security, maintainability, cost and architectural drift.
OWASP Top 10PCI DSSSOC 2ISO 27001NISTGDPRHIPAACISMITRE ATT&CK

A harness cannot certify its own work.

THE ASSURANCE CONTINUUM

Shift left to prevent it. Shift right to prove it.

DESIGN

architecture and policy documents

arko.design

IDE

the file open in front of the developer

arko.ide

AGENT

the agentic coding session

arko.mcp

COMMIT

the staged diff

arko.hook

MERGE

the pull request

arko.pr

BUILD

the CI/CD gate

arko.pipe

SIMULATE

the built artefact, running

arko.sim

RUNTIME

production

arko.watch

Decision Ledger

— every judgement at every station, signed and hash-chained into one tamper-evident record

THE LEFTMOST POINT

When the agent writes the code, the control has to sit in the agent’s loop.

THE OLD SHAPE

Developer writes → Commit → Pull request → Pipeline scan → Finding → Ticket → Sprint → Fix

Post-commit. Weeks between cause and correction.

THE NEW SHAPE

arko.ide — the human loop: risk surfaces as the line is typed; the fix is validated before the commit.

arko.mcp — the agent loop: the coding agent queries Arko before it writes, and Arko re-verifies after it writes.

Pre-commit, in both loops. Seconds between cause and correction.

An AI agent can write a thousand lines before a human reads one. A pipeline gate catches that at the end of the run. Arko catches it inside the run.

SHIFT RIGHT — BEFORE PRODUCTION

Static analysis produces a suspicion. Simulation produces a fact.

Once the static pass is done, Arko stands your application up in an isolated, ephemeral environment and drives it with agents — exercising routes, authentication boundaries and data paths against the artefact you actually built.

the same engine, now with executable evidence

01 · Static pass

Map the suspicion.

02 · Stand it up

Run the built artefact in isolation.

03 · Drive it with agents

Exercise routes, boundaries and paths.

04 · Adjudicate

Decide with observable proof.

05 · Re-simulate

Close the loop after the fix.

Re-simulate feeds the next static pass.

IDE / MCP — ‘This pattern is dangerous here’ — INFERENCE FROM CODE

Commit / PR / Build — ‘This pattern reached the main branch’ — INFERENCE FROM CODE AND HISTORY

Simulation — ‘Reproduced it in a running instance, and after the fix I could not’ — EXECUTION

Runtime — ‘It has not recurred in production for 90 days’ — OBSERVATION

Every other station finds. This one proves.

ONE ENGINE, MANY LENSES

The same graph answers six questions. Security is only the first.

Security

Can this actually be exploited?

CISO

Code health

Complexity, duplication, dead code, test-coverage debt — is this maintainable in a year?

VP ENGINEERING

Cost

What does AI-generated code cost to run?

CTO · FINOPS

Strategy alignment

Does the code match the architecture that was approved?

ARCHITECTURE

Licence and IP

What obligations did the model just import into your product?

LEGAL

Compliance evidence

DORA, EU AI Act, ISO 27001, SOC 2 — as signed exports, not a spreadsheet.

RISK · AUDIT

Machines verify. Humans decide.

DEPLOYMENT

We host it, or you do. Same product either way.

Same scanner, same engine, same screens. The only thing that changes is whose machines it runs on — so you can start hosted and move in-house later without re-integrating anything.

Managed SaaS

Source code: Arko cloud · Models: Arko cloud · Dashboard: Arko cloud

Your model

Source code: Arko cloud · Models: Your account · Dashboard: Arko cloud

Private Runner

Source code: Never leaves you · Models: Your account · Dashboard: Either

Sovereign · air-gap

Source code: Never leaves you · Models: Your GPU offline · Dashboard: Yours

Running on your servers is a packaging job, not a rebuild — the artefact we hand you is the artefact serving our own cloud.

Private endpoints, independently checked.

One evidence standard across every deployment.

Your account. Your boundary. Arko assurance.

What Our Customers Have to Say.

C

CISO

CISO

“The Arko team’s focus on developer experience, real-world attack scenarios and practical models was spot on”
“The Arko team’s focus on developer experience, real-world attack scenarios and practical models was spot on”

IN PRODUCTION

Deployed at enterprise scale, on real estates.

A 450-developer European ERP group runs Arko across its estate under a multi-year production agreement — SSO for the whole developer population, the CI check moving repository by repository at their pace.

A global trade-finance platform uses Arko to give its security champions one shared view of code risk across teams — and to produce the evidence its own customers ask for.

SOC 2 Type II — attestation programme underway

AWS London — EU-resident inference

Never trained on your code

Isolation verified on every deploy

FAQ

The questions security leaders ask first.

Where does our code go?

It depends on the deployment mode you choose. Hosted, your code is scanned in our EU cloud and deleted on scan completion. In Private Runner and sovereign modes, source never leaves your estate — only signed finding metadata and ledger receipts cross the boundary, and you read exactly what leaves before permitting it.

Is our code used to train models?

Can we use our own AI models?

Does Arko replace our existing scanners and pipeline tools?

How is this different from our coding assistant’s built-in checks?

What evidence do we get for auditors and regulators?

How long does deployment take?

How is Arko licensed?

>