Books FAQ

Books is an AI bookkeeper that helps close the month. It automates routine bookkeeping tasks while keeping all financial data on your infrastructure.

Here's how it works:

1. Import transactions: Pull bank feeds (CSV, OFX, QFX, or API integrations via Plaid/Teller)
2. AI categorization: AI categorizes transactions based on your chart of accounts
3. Reconciliation: AI matches bank feed items to ledger entries
4. Anomaly detection: AI flags duplicates, unusual amounts, missing documentation
5. Human review: You review and approve AI suggestions
6. Month-end reports: Generate P&L, balance sheet, cash flow, trial balance

The key difference from other bookkeeping tools: self-hosted, human-in-the-loop, suite-integrated. Your financial data stays on your infrastructure, and no ledger-affecting decision is made without human approval.

Bookkeeping is simultaneously critical and operationally painful:

• Manual bookkeeping is slow: SMBs spend 10-30 hours per month on routine tasks (categorization, reconciliation, anomaly review)
• Existing AI tools are cloud-only: Zeni, Truewind, Docyt, Bench, Pilot, Xero AI, QuickBooks AI all require sending financial data to third-party servers
• Global complexity: Multi-currency, multi-entity, cross-border tax treatment remain painful
• Trust gap: AI-generated journal entries without audit trails or human oversight create compliance risk

Books solves this by providing self-hosted, human-in-the-loop bookkeeping automation with full audit trails.

Books is designed for SMBs and global founders in regulated industries:

• Healthcare: Clinics, health tech — HIPAA-adjacent workflows
• Legal: Law firms — attorney-client privilege
• Defense: Government contractors — strict data sovereignty
• Fintech: Financial services — strict compliance
• Privacy-conscious founders: Global founders who want data control
• Any SMB: That wants bookkeeping leverage without sending financial data to the cloud

If you can't afford a compliance failure in your bookkeeping, Books is for you.

QuickBooks and Xero are cloud-based accounting tools. Books is a self-hosted, AI-first bookkeeper.

If you need full data control and AI-first bookkeeping, Books is the better choice.

"Human-in-the-loop" means no ledger-affecting decision is made without human approval:

• AI proposes: AI categorizes transactions, suggests reconciliations, flags anomalies
• Human approves: You review and approve every AI suggestion before it affects the ledger
• Audit trail: All AI suggestions and human decisions are immutably logged

This is an architectural constraint, not a feature gap. Books literally cannot make ledger-affecting decisions without human approval.

Books is both:

• Standalone: You can use Books by itself for bookkeeping
• Suite-integrated: Books is part of the ODW.ai suite and integrates with other modules:
  • Vault: Document context (invoices, receipts, contracts) for transaction categorization
  • Loop: Workflow automation (flag → notify → escalate)
  • Shield: Governance, audit logging, compliance reporting

The suite integration is what makes Books powerful — it draws on your document context and feeds anomalies into workflows.

"Sovereign" means full control over financial data:

• Data location: All financial data (transactions, ledger, reports) stays on your infrastructure
• Processing: All AI processing happens on your infrastructure (or your chosen cloud)
• No external dependencies: No financial data sent to third parties (unless you choose to use their APIs)
• Auditability: You can inspect the code, logs, and data flows

This is critical for regulated industries. You can't claim data sovereignty if your bookkeeping tool is sending financial data to a cloud vendor.

Basic accounting knowledge is helpful, but Books is designed to be accessible:

• For setup: You need to understand your chart of accounts, or work with an accountant to set it up
• For day-to-day use: The web UI guides you through transaction review, reconciliation, and reporting
• For complex scenarios: Multi-currency, multi-entity, cross-border tax — you may need an accountant

Books automates routine tasks, but it doesn't replace the need for accounting expertise in complex scenarios.

No. Books is designed to augment your accountant, not replace them.

Books automates routine tasks (categorization, reconciliation, anomaly detection), freeing your accountant to focus on:

• Complex decisions: Tax planning, financial strategy
• Compliance: Ensuring regulatory compliance
• Advisory: Business insights and recommendations

Books makes your accountant more efficient — it doesn't replace the human expertise that's critical to good financial management.

Books uses AI-powered categorization:

1. Import transactions: Pull bank feeds (CSV, OFX, QFX, or API integrations)
2. AI analysis: AI analyzes transaction descriptions, amounts, vendors
3. Chart of accounts mapping: AI maps transactions to your chart of accounts
4. Human review: You review and approve AI suggestions

Target: ≥92% categorization accuracy at launch, ≥95% by month 6.

Books provides AI-powered reconciliation:

• Side-by-side view: Bank feed vs. ledger entries
• AI matching: AI suggests matches between bank feed items and ledger entries
• Human approval: You review and approve matches
• Unmatched items: AI surfaces unmatched items for human review

Target: ≥80% auto-match rate.

Reconciliation ensures your ledger matches your bank statements — a critical control for financial accuracy.

Books detects multiple types of anomalies:

• Duplicate payments: Same vendor, same amount, close dates
• Unusual amounts: Transactions significantly larger or smaller than typical
• Missing documentation: Transactions without supporting documents (invoices, receipts)
• Policy violations: Transactions that violate your expense policies
• Timing anomalies: Unusual transaction timing (e.g., weekend transactions)

Target: ≥70% precision (avoid alert fatigue), ≥90% recall (avoid missed issues).

Books generates standard financial reports:

• Profit & Loss (P&L): Revenue, expenses, net income
• Balance Sheet: Assets, liabilities, equity
• Cash Flow Statement: Operating, investing, financing cash flows
• Trial Balance: List of all accounts with debit/credit balances
• Custom reports: Filter by date range, entity, currency, etc.

Reports can be exported as PDF, CSV, or XLSX.

Yes. Books provides native multi-currency support:

• Transaction-level currency: Each transaction can be in a different currency
• Exchange rate management: Configure exchange rates (manual or auto-fetch)
• Realized/unrealized gains: Automatically calculate FX gains/losses
• Multi-currency reporting: Report in your base currency or any other currency

Multi-currency is native from day one — not an add-on or higher-tier feature.

Yes. Books provides native multi-entity support:

• Separate ledgers: Each entity has its own ledger
• Inter-company transactions: Track transactions between entities
• Consolidated reporting: Generate consolidated reports across entities
• Entity-specific settings: Different chart of accounts, currencies, tax settings per entity

Multi-entity is native from day one — not an add-on or higher-tier feature.

Books provides basic cross-border tax treatment:

• VAT/GST/Sales Tax identification: Flag transactions subject to VAT, GST, or sales tax
• Tax jurisdiction tracking: Track which jurisdiction's tax rules apply
• Tax reporting: Generate tax reports by jurisdiction

Not in v1.0: Automated tax calculation engine (planned for v1.1). In v1.0, you'll need to calculate taxes manually or use a tax service.

Yes. Books supports data migration:

• Import chart of accounts: Import your existing chart of accounts
• Import transactions: Import historical transactions
• Import vendors/customers: Import vendor and customer lists
• Migration guides: Step-by-step guides for QuickBooks and Xero

Migration typically takes 1-2 days depending on data volume and complexity.

Books competes on sovereignty + human oversight + auditability. If you need data control and compliance, Books is the best option.

Books reduces month-end close time by automating routine tasks:

• Transaction categorization: AI categorizes transactions in seconds (vs. hours of manual review)
• Reconciliation: AI matches bank feed items (vs. manual matching)
• Anomaly detection: AI flags anomalies automatically (vs. manual review)
• Report generation: Automated report assembly (vs. manual compilation)

Target: ≥40% reduction in month-end close time vs. pre-Books baseline.

Books ensures accuracy through multiple mechanisms:

• Human-in-the-loop: Every ledger-affecting decision requires human approval
• Audit trails: All AI suggestions and human decisions are immutably logged
• Reconciliation: Bank reconciliation ensures ledger matches bank statements
• Anomaly detection: AI flags potential errors for human review
• Learning: Books learns from your corrections — accuracy improves over time

Target: ≥92% categorization accuracy at launch, ≥95% by month 6.

Yes. Books supports high transaction volumes:

• Batch processing: Process thousands of transactions at once
• Scalable infrastructure: Kubernetes-based deployment scales horizontally
• Efficient storage: Optimized database schema for large datasets

Target: 10,000+ transactions per month per organization.

For very high volumes (100,000+ transactions/month), we recommend:

• Kubernetes: For auto-scaling and high availability
• Managed database: RDS, Cloud SQL, or Azure SQL

Yes. Books supports complex scenarios:

• Multi-currency: Native support from day one
• Multi-entity: Native support from day one
• Cross-border tax: Basic VAT/GST/Sales Tax identification
• Inter-company transactions: Track transactions between entities
• Accrual accounting: Full accrual accounting support

Not in v1.0: Full ERP functionality (inventory management, manufacturing, project accounting). Books focuses on bookkeeping, not full ERP.

Yes. Books provides fully customizable chart of accounts:

• Custom accounts: Create accounts specific to your business
• Hierarchical structure: Organize accounts in a hierarchy
• Account types: Assets, liabilities, equity, revenue, expenses
• Import existing: Import your existing chart of accounts from QuickBooks/Xero

The chart of accounts is the foundation of your bookkeeping — Books gives you full control over it.

Not in v1.0. Payroll processing is explicitly out of scope for MVP.

In v1.0, Books focuses on bookkeeping — transaction categorization, reconciliation, anomaly detection, reporting.

If you need payroll processing, use a dedicated payroll service (Gusto, ADP, Rippling). Books can integrate with payroll exports to import payroll transactions.

Not in v1.0. Accounts payable (AP) and accounts receivable (AR) automation is explicitly out of scope for MVP.

In v1.0, Books focuses on bookkeeping — transaction categorization, reconciliation, anomaly detection, reporting.

Books can track AP/AR transactions (as part of the ledger), but it doesn't automate invoice creation, payment execution, or collection workflows.

If you need AP/AR automation, use a dedicated AP/AR tool (Bill.com, Tipalti, etc.).

Books is GAAP/IFRS-compatible:

• Accrual accounting: Full accrual accounting support
• Standard reports: P&L, balance sheet, cash flow statement (GAAP/IFRS format)
• Audit trails: Immutable logs of all ledger changes

Books helps you maintain GAAP/IFRS-compliant books. However, you still need accounting expertise to ensure proper application of accounting standards.

Books is designed for SOC 2 compliance:

• Security: Encryption at rest and in transit, RBAC, MFA
• Availability: High-availability deployment options
• Processing integrity: Human-in-the-loop for all ledger-affecting decisions
• Confidentiality: Self-hosted, zero data egress by default
• Privacy: Full data control, audit trails

Books provides the technical controls required for SOC 2. You still need to address organizational and procedural requirements separately.

Target: SOC 2 Type II certification framework in place by month 12.

Yes. Books is GDPR-compatible:

• Data residency: All financial data stays on your infrastructure
• Right to erasure: Delete data on request (with audit trail)
• Right to access: Export data on request
• Data minimization: Only collect what's necessary

Books helps you meet the technical and organizational measures required by GDPR. You still need to address legal and procedural requirements separately.

Yes. Books provides audit report exports:

• Formats: PDF, JSON, CSV
• Scope: Export by date range, entity, currency, or custom filters
• Content: All AI suggestions, human decisions, ledger changes, data access
• Speed: Generate a full audit export in <5 minutes

When an auditor asks for documentation, you can generate a complete report in minutes — not days.

Yes. Books provides comprehensive audit logging:

• Who: Which user made the change
• What: Which ledger entry was changed
• When: Timestamp
• Why: Reason for change (if required)
• AI vs. human: Whether the change was AI-suggested or human-initiated

All audit logs are immutable and tamper-evident — any tampering is detectable.

Yes. Books provides approval workflows:

• Threshold-based: Require approval for transactions above a certain amount
• Role-based: Different approval requirements for different roles
• Multi-level: Require multiple approvers for high-risk changes
• Automated routing: Route approval requests to the right people

Approval workflows ensure proper oversight for high-risk ledger changes.

Yes. Books is designed for external audit support:

• Audit trails: Complete, immutable logs of all ledger changes
• Export: Export audit logs in auditor-friendly formats (PDF, CSV, JSON)
• Read-only access: Grant auditors read-only access to review data
• Provenance: Full provenance for every ledger entry (who, what, when, why)

Books makes external audits straightforward — you can provide auditors with complete documentation in minutes.

Yes. Books provides data retention policies:

• Auto-deletion: Automatically delete old data after N years (e.g., 7 years for tax compliance)
• Legal holds: Flag data that can't be deleted (e.g., during litigation)
• Audit trail: All retention/deletion actions are logged

This is useful for compliance (data minimization) and storage management.

Yes. Books is built with security best practices:

• Self-hosted: All financial data stays on your infrastructure
• Encryption: AES-256 at rest, TLS 1.3 in transit
• Access control: RBAC, SSO (via Shield integration)
• Audit logging: Tamper-evident logs of all access (via Shield)
• Open source: Code is auditable — you can verify there are no backdoors or data exfiltration

Books is designed for regulated industries. If you can use Books, you can pass a compliance audit.

No. Books is self-hosted on your infrastructure. ODW.ai has zero access to your financial data.

Unlike cloud-based bookkeeping tools (QuickBooks, Xero, Zeni), Books doesn't send financial data to a third party. Everything stays on your servers.

This is critical for regulated industries. You can't claim data sovereignty if your bookkeeping tool is sending financial data to a cloud vendor.

Yes. Books supports air-gapped deployment (no internet access):

• Offline installation: Install Books without internet access
• Local models: All AI models run on your device — no API calls to external services
• No external dependencies: Books doesn't require internet access for core functionality

Air-gapped deployment is common for government contractors, military, and high-security environments.

Yes. Books provides role-based access control (via Shield integration):

• Admin: Full access — configure settings, manage users, view all data
• Accountant: Access to ledger, reports, transaction review
• Bookkeeper: Access to transaction review, reconciliation
• Viewer: Read-only access

You can also set per-entity permissions (e.g., only specific users can see data for a specific entity).

Yes. Books provides audit logging (via Shield integration):

• Who: Which user accessed the data
• What: Which financial data was accessed
• When: Timestamp
• Why: Reason for access (if required)

All audit logs are tamper-evident and can be exported for compliance purposes.

Books provides access control and alerting:

• Access control: Role-based access prevents unauthorized access
• Alerting: Get notified of unauthorized access attempts
• Audit trail: All access is logged (including blocked attempts)
• Investigation: Use audit logs to investigate incidents

For critical incidents, you can generate a full audit report for regulators or legal counsel.

Yes. Books' core is open source:

• Transparent: All code is publicly available on GitHub
• Auditable: You (or your security team) can inspect the code for vulnerabilities, backdoors, or data exfiltration
• Verifiable: You can verify that Books does what it claims — no hidden telemetry, no data sent to third parties

This is critical for sovereignty-focused organizations. You should be able to verify what your bookkeeping tools are doing.

Books is HIPAA-compatible for healthcare bookkeeping:

• On-premise processing: Financial data stays on your infrastructure
• Encryption: AES-256 encryption for local storage
• Access control: Password protection, role-based access
• Audit logging: Tamper-evident logs of all access

Books helps you meet the technical safeguards required by HIPAA. You still need to address administrative and physical safeguards separately.

Books is model-agnostic — it supports a wide range of models:

• Local models: Llama 3, Mistral, Gemma, Qwen (via Ollama, vLLM, llama.cpp)
• API-based models: OpenAI (GPT-4o, GPT-4o-mini), Anthropic (Claude 3.5 Sonnet), Google (Gemini 1.5 Pro), Mistral API
• Custom: Any model that exposes an OpenAI-compatible API

You can switch models at any time — no code changes required.

Yes. Books supports local models via:

• Ollama: Easiest way to run local models. Supports Llama 3, Mistral, Gemma, etc.
• vLLM: High-performance inference server for production workloads
• llama.cpp: Lightweight, CPU-friendly inference (good for edge devices)

Local models run on your own hardware — no data leaves your infrastructure. Full sovereignty.

Yes. Books supports API-based models:

• OpenAI: GPT-4o, GPT-4o-mini
• Anthropic: Claude 3.5 Sonnet, Claude 3 Opus
• Google: Gemini 1.5 Pro
• Mistral: Mistral Large, Mistral Medium
• Custom: Any model that exposes an OpenAI-compatible API

API-based models are useful when you need frontier capabilities (e.g., complex reasoning, long context windows) that local models can't match yet.

Choosing a model depends on your priorities:

Recommendation:

• Maximum sovereignty: Use Llama 3 8B or 70B (local, free)
• Maximum quality: Use GPT-4o or Claude 3.5 Sonnet (API, paid)
• Balanced: Use Llama 3 8B for routine tasks, GPT-4o-mini for complex reasoning

Yes. Books is model-agnostic — you can switch models at any time:

• No code changes: Just update the model configuration in the admin console
• Per-task: Use different models for different tasks (e.g., small model for categorization, large model for anomaly detection)

This future-proofs your investment — when better models are released, you can adopt them immediately without re-architecting your system.

Not in Books v1.0. Books uses existing models — it doesn't support fine-tuning.

However, you can:

• Use prompt engineering: Customize prompts to guide the model's behavior (e.g., "Focus on expense categorization for SaaS companies")
• Use Vault: Ground AI in your chart of accounts, policies, historical data
• Fine-tune externally: Fine-tune a model outside of Books (using tools like Hugging Face Transformers), then use the fine-tuned model in Books via a custom endpoint

Fine-tuning support is planned for v2.0 (Q2 2027).

No. Books is designed so that no ledger-affecting decision is made without human approval.

This is an architectural constraint, not a feature gap. Books literally cannot:

• Auto-post journal entries without approval
• Auto-reconcile without approval
• Auto-generate reports without approval

All ledger-affecting decisions require human approval. AI assists; humans decide.

Books offers three deployment options:

1. Docker Compose: Easiest. One command (docker-compose up) and you're running. Best for development and small deployments.
2. Kubernetes (Helm): Production-ready. Helm chart provided. Best for large deployments, high availability, auto-scaling.
3. Bare metal: For advanced users. Install directly on Linux servers. Maximum control, but requires more setup.

For most customers, Docker Compose is the fastest path. For production, we recommend Kubernetes.

Setup time depends on your deployment:

• Docker Compose: 30 minutes. Pull images, configure environment variables, run docker-compose up.
• Kubernetes: 2-4 hours. Deploy Helm chart, configure ingress, set up storage, test.
• Bare metal: 1-2 days. Install dependencies, configure services, test.

After deployment, you need to:

• Configure your chart of accounts (1-2 hours)
• Import your first bank feed
• Review and approve AI categorizations

Target: ≤1 day from deployment to first month-end close.

For deployment: Yes. Books is self-hosted, so you need someone who can manage Docker/Kubernetes, configure networking, and monitor infrastructure.

For day-to-day use: No. The web UI is designed for non-technical users (accountants, bookkeepers). You can review transactions, reconcile accounts, and generate reports without writing code.

For developers: Books provides a REST API and SDKs for custom integrations.

Books' requirements depend on your deployment:

If you use API-based models (OpenAI, Anthropic), you don't need a GPU. If you use local models, GPU is strongly recommended.

Yes. Books can be deployed on any cloud provider:

• AWS: Use EC2 (for Docker Compose) or EKS (for Kubernetes)
• GCP: Use GCE (for Docker Compose) or GKE (for Kubernetes)
• Azure: Use VMs (for Docker Compose) or AKS (for Kubernetes)

We provide deployment guides for each cloud provider. For production, we recommend Kubernetes with managed databases.

Yes. Books supports data migration:

• Import chart of accounts: Import your existing chart of accounts
• Import transactions: Import historical transactions
• Import vendors/customers: Import vendor and customer lists
• Migration guides: Step-by-step guides for QuickBooks and Xero

Migration typically takes 1-2 days depending on data volume and complexity.

Yes. Books includes a sandbox mode:

• Test environment: Deploy Books in a test environment with sample data
• Experiment: Test different workflows, integrations, and configurations
• Evaluate: Measure accuracy, latency, and compliance before going live

We recommend spending 1-2 weeks testing in sandbox mode before deploying to production.

For Docker Compose: Pull the new image, restart containers.

For Kubernetes: Update the Helm chart, rolling update.

For bare metal: Follow the upgrade guide in the documentation.

Total update time: <10 minutes (for Docker/Kubernetes).

Books pricing is based on features and deployment:

Additional costs:

• API costs: If you use API-based models (OpenAI, Anthropic), you pay the API provider directly
• Infrastructure: You pay for your own servers/cloud (if self-hosting)

It depends. QuickBooks costs $30-$180/month. Xero costs $13-$70/month.

Books costs $0-$699/month (depending on tier). For most SMBs:

• Books Core: Free (single-entity)
• Books Pro: $99-$199/month (multi-entity)
• QuickBooks: $30-$180/month
• Xero: $13-$70/month

For single-entity bookkeeping, Books Core is free — cheaper than QuickBooks/Xero.

For multi-entity bookkeeping, Books Pro is comparable to QuickBooks/Xero — and you get data sovereignty and human oversight.

However, Books requires you to manage your own infrastructure. If you factor in infrastructure costs, the total cost of ownership may be higher.

No hidden costs. The total cost of ownership includes:

• Books subscription: Monthly fee based on tier (or free for Core)
• API costs: If you use API-based models (OpenAI, Anthropic), you pay the API provider directly
• Infrastructure: You pay for your own servers/cloud (if self-hosting)

That's it. No setup fees, no surprise charges, no per-transaction fees.

We accept:

• Credit/debit cards: Visa, Mastercard, American Express (via Stripe)
• Bank transfer: For annual subscriptions or enterprise customers
• Cryptocurrency: Bitcoin, Ethereum, USDC (for privacy-conscious customers)

Invoicing is available for annual subscriptions. Contact us for details.

Yes. We offer a 30-day money-back guarantee for paid tiers. If you're not satisfied within the first 30 days, contact us for a full refund — no questions asked.

After 30 days, you can cancel anytime. You'll continue to have access until the end of your billing period, but no refund is provided for partial months.

The Core tier is free, so there's no refund needed.

Yes. Books is part of the ODW.ai suite. You can:

• Purchase Books standalone: Use Books by itself
• Purchase the full suite: Get Desk, Voice, Vault, Books, Shield, and other modules at a discounted price

The suite bundle includes Books at a 20-30% discount compared to purchasing separately. And all modules integrate natively — Books uses Vault for document context, Loop for workflow automation, Shield for governance.

Neither. Books pricing is unlimited — no per-transaction or per-user fees.

You pay a flat monthly fee based on your tier (Core, Pro, or Enterprise). Process as many transactions and users as you want.

The only variable cost is API costs (if you use API-based models). You pay the API provider directly for token usage.

Books can handle unlimited transactions:

• No transaction limit: Process as many as you want
• Scalable infrastructure: Kubernetes-based deployment scales horizontally

Target: 10,000+ transactions per month per organization.

For very high volumes (100,000+ transactions/month), we recommend:

• Kubernetes: For auto-scaling and high availability
• Managed database: RDS, Cloud SQL, or Azure SQL

Books supports unlimited users:

• Core tier: Unlimited users
• Pro tier: Unlimited users
• Enterprise tier: Unlimited users

Books scales horizontally — add more nodes to handle more concurrent users. Typical deployments support 50-200 concurrent users per node.

If Books goes down, bookkeeping operations are unavailable, but your data is safe:

• Data storage: All data is stored in your database (PostgreSQL) — not lost
• Recovery: Restart Books, and it reconnects to your database
• High availability: For production, deploy Books with multiple replicas (Kubernetes)

For high-availability deployments, we recommend:

• Kubernetes: 3+ replicas across availability zones
• Managed database: RDS, Cloud SQL, or Azure SQL (99.9% uptime SLA)
• Load balancer: Distribute traffic across replicas

Books includes a monitoring dashboard:

• System health: CPU, memory, disk, network usage
• Bookkeeping metrics: Number of transactions, categorization accuracy, reconciliation rate
• Model metrics: API costs, token usage, model latency
• Error tracking: Track failures by transaction type

You can also export metrics to external monitoring tools (Prometheus, Grafana, Datadog) via standard protocols.

Books data is stored in PostgreSQL. Back up using standard PostgreSQL tools:

• Automated backups: Configure daily backups via pg_dump or WAL archiving
• Off-site storage: Store backups in a different location (e.g., S3, GCS, off-site server)
• Test restores: Periodically test restoring from backups to ensure they work

Books provides backup guides and scripts for common deployment modes (Docker, Kubernetes, on-premises).

Yes. Books supports multi-tenancy:

• Multiple entities: Create separate ledgers for each entity
• Multiple clients: For accountants, create separate workspaces for each client
• Isolation: Each entity/client has its own ledger, transactions, and settings

This is useful for accountants managing multiple clients, or enterprises with multiple business units.

Books is designed to be intuitive, but we provide training resources:

• Documentation: Comprehensive user guides for admins, accountants, and bookkeepers
• Video tutorials: Step-by-step walkthroughs of key features
• Onboarding session: For paid customers, we offer a 2-hour onboarding session (remote)
• Support: Priority support for Pro and Enterprise customers

Most teams are productive within 1-2 days of training. The web UI is particularly intuitive — no technical skills required for accountants and bookkeepers.

Books integrates natively with all ODW.ai products:

• Vault: Document context (invoices, receipts, contracts) for transaction categorization
• Loop: Workflow automation (flag → notify → escalate)
• Shield: Governance, audit logging, compliance reporting

If you're using the ODW.ai suite, Books integration is automatic — no separate configuration required.

Yes. Books provides a REST API for programmatic access:

• Transaction management: Create, update, retrieve transactions via API
• Ledger management: Create, update ledger entries via API
• Report generation: Generate reports via API
• Webhooks: Get notified when transactions are categorized, anomalies are flagged, etc.

The API is fully documented (OpenAPI/Swagger) and supports authentication via API keys or OAuth 2.0.

Yes. Books supports bank integrations:

• Plaid: Connect to thousands of banks via Plaid API
• Teller: Connect to banks via Teller API
• CSV/OFX/QFX: Import bank feeds as files
• Direct bank APIs: Some banks provide direct APIs (e.g., Stripe Treasury, Mercury)

Bank integration enables automatic transaction import — no manual data entry required.

Books is your accounting software. It replaces QuickBooks, Xero, etc.

However, if you need to integrate with other financial systems:

• ERP systems: Export data to SAP, Oracle, NetSuite via API
• Payroll systems: Import payroll transactions from Gusto, ADP, Rippling
• Payment processors: Import payment data from Stripe, PayPal, Square

Books is designed to be the source of truth for your bookkeeping — other systems integrate with Books, not the other way around.

Yes. Books can be used with existing AI tools:

• LangChain: Use Books as a bookkeeping tool in LangChain pipelines
• LlamaIndex: Use Books as a bookkeeping tool in LlamaIndex pipelines
• Custom RAG: Use Books' API in your custom pipelines

Books is designed to be a bookkeeping layer — it provides bookkeeping automation, and you can use any AI tool for other tasks.

Yes. Books provides data export:

• Reports: Export P&L, balance sheet, cash flow as PDF, CSV, XLSX
• Transactions: Export transactions as CSV
• Audit logs: Export audit logs as JSON, CSV, PDF
• Full database: Export the entire database (PostgreSQL dump)

Data export is useful for backup, migration, and integration with other systems.

Yes. Books provides data import:

• Bank feeds: Import CSV, OFX, QFX files
• Chart of accounts: Import from QuickBooks, Xero
• Transactions: Import historical transactions from CSV
• Vendors/customers: Import from CSV

Data import is useful for migration from other systems, or for importing historical data.

Books is powerful, but it has limitations in v1.0:

• No payroll: Payroll processing is out of scope
• No AP/AR automation: Invoice creation, payment execution are out of scope
• No tax filing: Books doesn't file taxes or submit to tax authorities
• No full ERP: Inventory management, manufacturing, project accounting are out of scope
• No mobile app: Web-responsive design only for v1.0
• No real-time bank feeds: Batch ingestion only (no streaming)
• English-only UI: Multi-language UI planned for v1.1

Yes. Automated tax calculation is planned for v1.1 (Q4 2026):

• VAT/GST/Sales Tax: Automatic calculation based on jurisdiction
• Tax reporting: Generate tax reports by jurisdiction
• Tax filing: Integration with tax filing services (optional)

This is a high-priority feature for global businesses with cross-border tax obligations.

Not in the current roadmap. Payroll processing is a complex, regulated domain that requires deep expertise.

We believe the right approach is to integrate with dedicated payroll services (Gusto, ADP, Rippling) rather than building payroll from scratch.

If payroll is a must-have for your use case, contact us — we may reconsider based on customer demand.

Key milestones:

• v1.0 (Q3 2026): MVP launch. Self-hosted, human-in-the-loop, multi-currency, multi-entity, suite integration.
• v1.1 (Q4 2026): Automated tax calculation, advanced forecasting, budget vs. actual analysis.
• v1.2 (Q1 2027): OCR for receipt/invoice scanning, natural language querying, mobile apps.
• v2.0 (Q2 2027): Model fine-tuning, advanced fairness testing, white-label/OEM licensing.

Roadmap is subject to change based on customer feedback. Contact us for the latest roadmap or to request features.

Books is not the right fit if:

• You don't have compliance requirements: If you don't care about data sovereignty or human oversight, cloud-based tools (QuickBooks, Xero) are easier (no infrastructure to manage).
• You need payroll: If you need payroll processing, use a dedicated payroll service (Gusto, ADP, Rippling).
• You need full ERP: If you need inventory management, manufacturing, project accounting, use a dedicated ERP (SAP, Oracle, NetSuite).
• You need mobile apps: Books is web-responsive only in v1.0. If you need native mobile apps, wait for v1.2.

No. No system can guarantee 100% accurate bookkeeping — errors happen (data entry errors, mis-categorizations, etc.).

Books helps you maximize accuracy through:

• AI categorization: ≥92% accuracy at launch, ≥95% by month 6
• Human oversight: Every ledger-affecting decision requires human approval
• Reconciliation: Bank reconciliation ensures ledger matches bank statements
• Anomaly detection: AI flags potential errors for human review

But accurate bookkeeping requires ongoing effort: proper chart of accounts setup, regular review, and accounting expertise.

No. Books is designed to augment your accountant, not replace them.

Books automates routine tasks (categorization, reconciliation, anomaly detection), freeing your accountant to focus on:

• Complex decisions: Tax planning, financial strategy
• Compliance: Ensuring regulatory compliance
• Advisory: Business insights and recommendations

Books makes your accountant more efficient — it doesn't replace the human expertise that's critical to good financial management.

Three paths:

1. Free Core tier: Download Books and deploy it yourself. No credit card required. Try it with your bookkeeping process and see if it works for your use case.
2. Demo: Book a demo with our team. We'll walk you through Books, answer your questions, and help you evaluate if it's right for your business.
3. Contact sales: For Pro or Enterprise tiers, contact our sales team for a tailored quote.