Skip to content

Your AI Architecture Co-Worker

Powered by Claude. Configured per workspace. Operating in two directions — extracting candidate directives from your standards, and applying approved directives to every project.

The Two-Way AI Pipeline

Most teams reach for AI either at the front of governance (turn documents into rules) or at the back (review projects against rules). cajeX does both, on a single pipeline that traces back to the same approved directives.

Knowledge Base

Curate architectural standards, best practices, and reference materials

Directives

AI proposes candidate directives; architects review and approve

Review

Automated review of incoming projects against approved directives

Findings

Actionable findings with severity, confidence, and remediation steps

What the AI Does at Each Stage

The pipeline is not a black box. Here is exactly what happens when cajeX AI extracts a directive or reviews a project.

Knowledge base ingestion

When you add a document to the knowledge base, cajeX parses and indexes it so the AI can read it later. PDFs, Markdown, HTML, and plain text are all supported. Documents stay in the knowledge base whether or not extraction has run yet — they remain available as source material for future directive extraction and as supporting context during project reviews.

Directive extraction

When you run extraction on a knowledge base document, the AI ingests its full text in a single context window, identifies the rules it implies, and proposes them as candidate directives. Each candidate includes a suggested name, scope, severity, and a link back to the source passage. Architects review the candidates and approve, edit, or reject them before they enter the active rule set. The AI never adds a directive autonomously.

Project review

When a project is submitted for review, the AI loads your active approved directives and the project description. It evaluates each project claim against the directive set and surfaces violations as findings. Every finding references the specific directive ID it violates, so the audit trail stays clean and traceable.

Findings generation

Every finding includes a severity classification (informational, low, medium, high, critical), an AI confidence score, the directive it violates, and a suggested remediation step. Findings are mapped 1:1 to directive IDs so auditors can trace every recommendation back to an approved governance rule.

Watch an AI Review Run End-to-End

The same flow described above, on a real project. Submit a project, watch the AI evaluate it against the active directive set, and read findings as they appear with severity, confidence, and remediation.

Part 3 of the four-part Getting Started Guide. Watch the full walkthrough on /product.

AI Capabilities

Everything you need to run AI-powered architecture reviews at enterprise scale.

Knowledge Base Pipeline

Ingest standards documents, policies, and whitepapers in PDF, Markdown, HTML, or plain text. The AI parses the full document and proposes candidate directives, each linked back to the source passage.

Model Selection

Powered by Claude (Anthropic) by default. Each workspace can configure its own model and API credentials — OpenAI and Gemini support are on the roadmap. Plan-based review quotas keep costs predictable.

Scoped Reviews

Run a review against your full approved directive set or a targeted subset. Scope by governance area, severity threshold, or project type — keeps reviews fast and tokens predictable.

Usage Dashboard

Monitor AI token usage, review counts, and per-workspace costs — broken down by model, task, and day. Set per-workspace quotas to manage your AI budget.

Example Findings the AI Generates

Real-shape examples of what an AI-generated finding looks like. Each one references the directive it violates and proposes a concrete remediation step.

DIR-0042High

Directive

All public-facing services must implement circuit breakers with fallback responses

Finding

Payment Gateway service has no circuit breaker on upstream calls to the fraud-check API.

Suggested fix

Wrap upstream HTTP calls with a circuit breaker library (Polly, resilience4j, etc.) and define a fallback response for fraud-check timeouts.

AI confidence92%
DIR-0091Medium

Directive

PII must be encrypted at rest with per-tenant encryption keys

Finding

User profile table uses a single application-level encryption key shared across all tenants.

Suggested fix

Migrate to per-tenant KMS keys with envelope encryption. Re-key the existing rows in a background migration.

AI confidence87%
DIR-0017Critical

Directive

Service-to-service authentication must use signed JWTs with short TTL

Finding

Order service authenticates to inventory service via a shared API key stored in an environment variable.

Suggested fix

Issue scoped JWTs from a service identity provider with TTL <5 minutes. Rotate the shared key out before deprecation.

AI confidence95%

Why Claude?

Claude (Anthropic) is the default model behind cajeX AI. Three properties make it a strong fit for architecture governance.

Constitutional alignment

Claude is trained with Constitutional AI to reduce harmful or hallucinated outputs — important when the output is governance guidance that architects will act on.

Long context

A large context window means cajeX can process entire standards documents in a single pass, without chunking that loses cross-section context.

Privacy by policy

Anthropic's API terms exclude API requests from model training. You bring your own API key per workspace — your data never enters anyone's training set.

AI Safety & Privacy

cajeX gives you full control over what data the AI sees, how long, and whether it sees anything at all.

  • Per-workspace encrypted credentials. AI provider API keys are encrypted at rest with per-workspace AES-GCM-256 keys. No shared keys, no cross-workspace data leakage risk.
  • Disable AI entirely if needed. Workspaces with regulated data can turn off AI features completely. Every other governance module — knowledge base, directives registry, sessions, findings, reports — still works. See Regulated Industries for the BYOC story.
  • Full audit trail. Every AI interaction — prompt, model, token count, response, timestamp — is logged for review. Auditors can trace every AI recommendation back to its full context.

Frequently Asked Questions

How does cajeX AI review architecture?
cajeX runs incoming project descriptions through Claude (or your configured AI model) along with your active approved directives. The model maps project claims against the directive set and produces findings with severity, confidence, and remediation steps — each linked to the directive ID it violates.
What AI model does cajeX use?
Claude (Anthropic) is the default. Each workspace can configure its own model and API credentials. OpenAI and Gemini support are on the roadmap. All API keys are encrypted at rest with per-workspace AES-GCM-256 keys.
Is my data used to train AI models?
No. Anthropic's API terms exclude API requests from model training, and you bring your own API key per workspace. For workspaces that prohibit outbound AI calls entirely, AI features can be disabled — every other governance module still works.
How accurate are AI-generated findings?
Every AI finding includes a confidence score. Architects review findings before they propagate to projects; cajeX never auto-closes or auto-acts on AI findings. The full audit trail records every AI interaction for review.
Can the AI extract directives from PDFs?
Yes. You upload standards documents (PDF, Markdown, HTML, plain text) to the knowledge base. The AI ingests the full document and proposes candidate directives that architects review and approve before they enter the active rule set.
How does cajeX handle large standards libraries?
The AI pipeline is scoped: you can run a review against your full active directive set or a targeted subset relevant to the project type. This keeps reviews fast and tokens predictable, even with thousands of directives.

See cajeX AI in Your Stack

A 30-minute demo walks you through directive extraction, project review, and findings generation against your real standards.