KrelunaClient documents
Classify, search, summarise and organise authorised information.
Kreluna ecosystem
AI for accounting firms and advisory teams
Kreluna Office is designed to prepare and organise document-heavy work while keeping review, advice and consequential decisions with qualified professionals.
Kreluna is in active development. Early access, feature availability and integration coverage are confirmed individually for each request.
Workflows Kreluna can support
Deadlines and communication
Prepare reminders, drafts and tasks for professional review.
Firm workflows
Coordinate handoffs, roles, permissions and approval steps.
Prepare recurring client work
A firm can start with document intake, missing-information checks, assignment, draft communication and professional approval. The workflow is adapted only after the actual process is understood.
- Organise authorised client documents
- Prepare tasks and reminders
- Review before communication or changes
Keep professional responsibility where it belongs
Kreluna does not provide tax advice or replace qualified accountants. It helps prepare and coordinate work while interpretation, review and client advice remain with the firm.
- A use case defined with the firm
- Least-necessary access to data
- Software compatibility checked first
Frequently asked questions
Does Kreluna provide tax advice?
No. It may support preparation and organisation while interpretation and client advice remain with qualified accountants.
Can it check for missing documents?
That is a potential use case to configure and validate against the firm’s sources, rules and responsibilities.
How is client data handled?
Access and scope must be limited to what is necessary, with details agreed before any real data is used.
Built around control and clarity
Every project starts with a defined objective, authorised information and a clear review process. Capabilities are enabled progressively and important actions remain subject to approval.
- Defined scope and responsibilities
- Human review for important actions
- Clear limits and measurable outcomes
Practical applications
Document workflows for accounting firms
These examples concern preparation and coordination. Kreluna is not presented as a tax authority, tax-advice engine or replacement for the firm’s system of record.
Recurring collection
Organise received files by client and period and prepare a missing-items list before professional work begins.
Files and retrieval
Locate passages in authorised client documents and show the source without turning a summary into an unchecked accounting entry.
Client communication
Draft recurring requests or reminders from approved firm templates while keeping review and sending with the professional.
Deadlines and ownership
Coordinate tasks, owners and matter status without calculating tax or making professional judgements.
Project method
Use one recurring workflow as the first test
A pilot can focus on document completeness or file preparation. Synthetic or minimised data helps test the workflow before real archives are involved.
- Define the outcome
Describe the problem, who performs the work today and which observable result should improve.
- Map data and exceptions
Identify sources, permissions, manual hand-offs, unusual cases and points where a person must decide.
- Test a narrow scope
Run the pilot on authorised sample data against acceptance criteria agreed before the test.
- Measure and decide
Compare the workflow with its baseline, then extend, revise or stop it on evidence rather than enthusiasm.
Data and accountability
Tax and professional judgement stay with the firm
Outputs must be checked against authorised documents and sources. Tax accuracy, legal currency and client communication are not delegated to a model.
- Separate clients and engagements
- Check document provenance
- No official posting without professional review
- Distinguish drafts from approved communication
- Name integrations only after testing the real practice system
Measuring value
Completeness before speed
Assess the pilot on work avoided and the quality of the file reaching the reviewer, not on the amount of text generated.
Missing documents
Ability to flag absence and inconsistency against an agreed checklist.
Preparation time
Work spent organising, renaming, retrieving and summarising.
Corrections
Changes needed to classification or drafts before proceeding.
Repeated requests
Follow-ups caused by incomplete or uncoordinated communication.
Before you begin
Boundaries of accounting workflow support
Does the AI interpret current tax rules?
It is not proposed as an autonomous tax source. Any source must be authorised, current and reviewed by the competent professional.
Is client data used to train a model?
That must never be assumed. Provider, purpose, retention and data use have to be documented for the actual configuration before real data is loaded.
Which accounting systems are already integrated?
This page claims none. Systems are named only after interfaces, authorisation and behaviour have been verified.
References for responsible design
The AI Act and GDPR can apply together: duties and safeguards depend on the organisation’s role, the data and the system’s actual use. Assessment therefore comes before configuration.
- European Artificial Intelligence ActOfficial text of Regulation (EU) 2024/1689.
- EDPB Opinion 28/2024 on AI modelsAnonymity, legal basis and consequences of unlawful personal-data processing.
- EDPB — Data protection by design and by defaultSME guidance on safeguards, minimisation and accountability.
- OWASP — LLM Prompt Injection PreventionRisks and defences for AI applications connected to documents and tools.
These sources help frame the work; they do not replace legal, privacy or security advice for a specific situation.