Key Concepts

MCP (Model Context Protocol)#

The Model Context Protocol is the open standard that makes Artifi possible. MCP defines how AI tools like Claude.ai, Cursor, Windsurf, and VS Code communicate with external services — in this case, your financial infrastructure.

When you connect Artifi's MCP Server to your AI tool, that tool gains access to 150+ financial operations: posting invoices, running reports, managing vendors, reconciling bank accounts. You're not locked to any single AI provider. Any tool that speaks MCP can operate your ERP.

This is the same standard used across the AI ecosystem, which means Skills and Plugins you build for Artifi work across Claude, Cursor, VS Code, and OpenAI.

---

Data Isolation#

Every Artifi client gets their own dedicated PostgreSQL schema. Your financial data lives in a completely separate database schema from every other client — not filtered rows in a shared table, but a fully independent data store.

This means:

• No data leakage risk between clients
• Each schema can be backed up, restored, or migrated independently
• Schema structure is identical across clients (consistent, predictable)
• New organizations get a fresh clone of the template schema

---

Organizations & Legal Entities#

Your company in Artifi is an Organization. Inside it, you can have multiple Legal Entities — subsidiaries, branches, country offices, or any distinct legal unit that maintains its own books.

All legal entities within an organization share the same master data (chart of accounts, vendor list, item catalog) but maintain separate financial records. This means:

• A parent company with three subsidiaries = one organization, three legal entities
• Each entity has its own transactions, balances, and reporting periods
• Master data is defined once and shared across all entities
• Cross-entity reporting and consolidation works naturally

Most businesses start with a single legal entity and add more as they grow. The multi-entity architecture is there from day one — no migration needed.

---

Master Data & MSEO#

Artifi uses a pattern called MSEO (Master + Scopes + Entity Overrides + Effective Views) to manage shared data efficiently.

The problem it solves: If you have 100 accounts and 5 legal entities, a traditional system would duplicate all 100 accounts for each entity — 500 rows of identical data. Updating an account name means updating it 5 times.

How MSEO works:

1. Master records are defined once at the organization level (100 accounts stored once)
2. Every legal entity automatically sees all master records
3. If one entity needs something different, it creates an override for just that field
4. Effective views automatically merge masters with overrides — you always see the resolved result

Master: "4000 - Revenue"  (defined once)
  → Entity A sees: "4000 - Revenue"           (uses master)
  → Entity B sees: "4000 - Product Sales"      (has override)
  → Entity C sees: "4000 - Revenue"            (uses master)

Stored: 1 master + 1 override = 2 rows
Visible: 3 rows (one per entity)

This pattern applies to accounts, vendors, customers, items, tax codes, and dimension values. You define things once and override only where needed.

---

Workflow Engine & Audit Trail#

Every action that changes data in Artifi — whether triggered by you in Claude, by an autonomous agent, or by an API call — goes through the Workflow Engine.

Approval Routing#

The workflow engine uses risk-based lanes to decide how each operation is handled:

Lane assignment is fully configurable. You define the rules: which operations need approval, at what thresholds, and who can approve.

Full Audit Trail#

The workflow engine is also your complete audit trail. Every action records:

• Who initiated it (user, agent, or API key)
• What was requested (the full operation details)
• When it happened (timestamps for each step)
• What lane it was assigned (green/yellow/red)
• Who approved it (if approval was required)
• What changed (the resulting data modifications)

This isn't a separate audit log bolted on after the fact — it's the core mechanism through which all changes flow. Whether a human posted a journal entry via Claude, or the bill processor agent created a vendor bill at 3am, the full history is there.

Workflow Lifecycle#

submitted → validating → validated → approved → executing → completed
                                   ↘ pending_approval → approved → completed
                                                      → rejected → closed

---

Plugins & Skills#

Skills#

Skills are portable instruction sets that enhance how your AI tool works with Artifi. A skill might teach Claude how to handle Estonian payroll, or guide it through a month-end close process specific to your industry.

Skills work across Claude, Cursor, VS Code, and OpenAI — they're not locked to any single platform. You can download skills built by others, or create your own.

Plugins#

Plugins extend Artifi's capabilities with custom business logic that runs on the server side. Where skills guide the AI's behavior, plugins add new functionality to the system itself:

• Payroll calculation rules for specific countries
• Tax declaration logic for specific jurisdictions
• Industry-specific reports or validation rules
• Custom allocation algorithms

Plugins are activated per-organization and can be built by anyone — your team, a consulting firm, or the Artifi community. Browse existing plugins and contribute your own at github.com/ar-ti-fi/plugins.

Why This Matters#

Traditional ERPs hardcode specialized logic. If their payroll doesn't match your country's rules, you wait for a vendor update. If their reporting doesn't fit your industry, you export to spreadsheets.

With Artifi, specialized logic lives in Plugins and Skills — open, replaceable, and buildable by anyone who understands the domain.

---

Agents#

Agents are autonomous AI workers that handle tasks in the background without your involvement. They're triggered by events (an email arrives, a bank statement is imported) and execute multi-step workflows independently.

Built-in Agents#

Optional by Design#

Agents are powerful but entirely optional. You can:

• Use all built-in agents for maximum automation
• Use some and handle the rest through Claude conversations
• Build your own agents using the Agent SDK
• Skip agents entirely and manage everything manually

The agents work through the same workflow engine as everything else, which means their actions follow the same approval rules and appear in the same audit trail.

---

Connectors#

Connectors bring external data into Artifi and push actions out — banking integrations, accounting system syncs, payment processing.

Current Integrations#

• Stripe — card transactions, payment processing, webhook events
• Merit Aktiva — accounting data sync with Merit ERP
• SmartAccounts — accounting data sync with SmartAccounts

Extend with Any Integration Tool#

Everything else can be connected through n8n, Zapier, Make, or any integration platform. The MCP Server is an open endpoint — if your integration tool can make HTTP calls, it can interact with Artifi.

Common patterns:

• Import bank statements from your bank's API via n8n
• Push approved invoices to an external payment service via Zapier
• Sync employee data from your HR system via Make
• Receive webhook events from any external service

Connector credentials are encrypted with AES-256-GCM and managed through the admin dashboard — never exposed in chat or logs.

---

Tools#

Tools are the 150+ operations that Claude can perform through the MCP Server. They fall into two categories:

Read Operations (Direct)#

Queries, reports, and lookups execute immediately — no approval needed:

• Search — find any record across all entity types
• Reports — financial statements, aging, budget variance, custom reports
• Lookups — get details on any account, vendor, customer, transaction

Write Operations (via Workflow)#

All changes to data go through the workflow engine:

• Submit — the universal gateway for creating and modifying records
• Validation, risk assessment, and approval routing happen automatically
• Full audit trail for every change

This separation ensures that reading data is always fast and frictionless, while writing data is always validated, approved, and auditable.

---

Next Steps#

• Getting Started — set up your organization in under 10 minutes
• Overview — understand what Artifi is and how it works
• Browse the feature documentation to learn about specific capabilities