Use case · Finance & Controlling
New figures.
Current forecast.
Deviations explained.
We start from your planning logic, chart of accounts and previous forecasts. Together with controlling, treasury and IT we clarify which data flows in, who may see which entities and when controlling decides. The result is your workflow for continuously updated forecasts.
Your team
“Use our chart of accounts, the budget and the forecasts of recent quarters. Create a workflow that updates liquidity for the next 13 weeks and earnings for the financial year every week: read actuals, open items and order intake. Calculate according to our planning logic and flag deviations above our threshold. Explain the causes with reference to the data. Publish only after approval by controlling.”
CORA is drafting the process …
The description becomes the workflow
Describe once.
Run every time.
Your description becomes a weekly forecasting run: from current postings to an approved liquidity and earnings forecast.
CORA builds the process. Your team reviews the test cases and approves it. Only then does it run for every matching event – with your permissions.
Read data · Calculate forecast · Explain deviations
- Week close
- Read data
- Calculate forecast
- Explain deviations
- Approval
One run in detail
How CORA rolls a week forward.
A forecasting run after the week close: from postings to an approved liquidity outlook.
All names, numbers and values in this example are fictitious.
- TriggerClose of calendar week 46.
- IntegrationRead data
Read: postings of three entities, 412 open items, bank transactions and the week's order intake.
- CodeCalculate forecast
Week Plan Forecast Deviation Week 47 €4.2m €4.1m −2 % Week 48 €4.0m €3.4m −15 % Week 49 €4.3m €4.2m −2 % - RuleFlag deviation
Week 48 is above the deviation threshold and needs an explanation and controlling's approval.
- AIExplain cause
The gap in week 48 is mainly caused by a postponed incoming payment at entity North (invoice RE-7781) and an early supplier payment. Without these two items the deviation would be 3 %.
- HumanApprove
Controlling confirms the explanation and adds a note about the payment reminder.
- IntegrationPublish
Forecast version week 46 saved in the planning system and sent to management and treasury.
From existing documents to a tested workflow
From existing documents
to a tested workflow
1Your documents and example cases
2Business systems and data
3People, roles and rights
- Build process
- Test
- Approve
Running process
- Week close
- Read data
- Update forecast
- Report
- Explain causes
- Controlling approval
- Clarify with accounting
Process steps in detail
What AI does – and what rules, code and integrations handle.
CORA uses AI where language, context or unstructured information needs to be understood. Calculations run as tested code, limits and responsibilities as rules, system access through defined integrations. Approvals stay with people.
- AILanguage model: understands, summarises, drafts1×
- RuleFixed conditions, thresholds, responsibilities2×
- CodeCalculations and models, versioned and testable2×
- IntegrationRead and write access via MCP servers or interfaces2×
- HumanReview, approval and decision1×
- 01
Start run
The forecasting run starts as soon as the week's postings are closed.
- 02
Read actuals
CORA reads postings, open items, bank transactions and order intake.
- 03
Reconcile data
Missing or duplicate data is detected before calculating.
- 04
Calculate forecast
Liquidity for 13 weeks and earnings for the financial year, per entity and cost centre.
- 05
Flag deviations
Items above the threshold are queued for explanation.
- 06
Explain causes
The AI describes which items drive the deviation and refers to the underlying postings.
- 07
Review and approve
Assumptions and explanations are reviewed, adjusted if needed and approved.
- 08
Publish version
After approval, the version is saved and distributed to the defined recipients.
Connected systems
- ERP financial accountingreads postings and open itemsvia MCP server
- Bank accountsreads transactionsvia bank interface
- CRMreads order intakevia MCP server
- Planning systemwrites the approved forecast versionvia interface (API)
- Company sign-inchecks identity and rolevia single sign-on
How we work
We start with your
actual work.
- 01
Understand existing documents
Budget, chart of accounts, forecast templates and past forecasts show us your planning logic. From them we derive drivers, time horizons and deviation thresholds. We resolve differing spreadsheet calculations with controlling.
- 02
Connect data and business systems
With your IT we connect financial accounting in the ERP, bank accounts, CRM and planning system. Entity, account and cost centre link the data. We define where data is read and where forecast versions are stored.
- 03
Assign identities, rights and roles
Identity comes from your company sign-in. Controlling sees all entities, unit heads only their cost centres. The AI applies these rights; it reads postings but never posts.
- 04
Test together and go live
From the description, documents and clarified system access, CORA drafts the process. Together with your business unit we select test cases and expected results. Testing runs without write access. Example tests: Normal week, large incoming payment postponed, new entity without plan values, missing bank statement.
Your team decides on rules, AI steps and approvals. We activate the tested workflow, compare effort and results and practise the next changes in the skill workshop. Integrations, knowledge and reusable building blocks remain as the foundation for further processes.
Discuss your projectHow the case
runs
Every week CORA reads actuals, open items and order intake, reconciles the data and calculates the forecast according to your planning logic. Deviations above the threshold are explained and presented to controlling for review.
What it
produces
Updated 13-week liquidity and earnings forecast per entity, flagged deviations with causes and an approved, versioned forecast. Data status and assumptions are documented.
Where your team
decides
Controlling reviews assumptions and explanations and approves the forecast. CORA does not post and does not change plan values without approval. Missing data goes to accounting for clarification.
More use cases
- HR & Workforce ManagementStrategic workforce planning
- SalesIntelligent sales steering
- HR & People DevelopmentAI-supported talent management
- ProductionDynamic production planning
- ProcurementIntelligent supplier management
- Production & MaintenancePredictive maintenance
- Supply Chain & LogisticsPredictive supply chain steering