Data Pipeline
Datasets in, SQL transforms on top. Every step is a node you can open and read.
Your reports: built once, always up to date.
For the reports you produce every month, quarter and year. With AI you turn your logic and your data into interactive applications that you fill with data every reporting period. All logic is transparent, traceable, adaptable and versioned.
How it works
You bring the logic and the data.Factophant builds the rest.
Your own AI
Bring the AI your team already uses.
Connect your Claude, ChatGPT or any MCP-compatible AI. It acts on your behalf, only within the permissions you and your admin set, and uses no Factophant AI credits.
Audit trail
Focus on what matters most.The documentation is maintained automatically.
Factophant keeps the rule, the version and the audit trail behind every figure, so the answer is there if someone asks.
Draft in private
Change a rule or a query in a draft. Viewers keep seeing the published version until you publish.
Fully versioned
Each run records the version it executed and who started it: a person, Vera or a connected system.
Trace the figure
Follow a result back through the pipeline: the inputs, the calculation logic, and the run and version it came from.
Approve & lock
A reporting period can be approved only when every required figure is in and no blocking check fails. Approving freezes the values and publishes one immutable version.
Full transparency
Every calculation's logic can be viewed and exported in full. All values and logic can be traced and reused outside Factophant.
Who uses Factophant
Many perspectives, brought together in one solution.Factophant lets people work together at different levels.
Management
Everything that matters, at a glance.
Key figures and how they change, always current and in one place.
The business team
You own the data and the logic.
You know your process best. Factophant takes care of most of the technical work.
The technical team
Full control in the background.
The SQL data pipeline is fully visible and editable. Automatic versioning and fine-grained control over roles, permissions and AI access give you peace of mind when your business teams work on their own.
The software
Data collection comes with very different requirements.Whether sent automatically, entered by hand or gathered in a survey:the right app type for each requirement.
Where your report comes together.
Data arrives through the API, as a file upload, typed in directly, or from your indicator apps and surveys. With AI you build the pipeline, the knowledge base and the visualisation on top, and every step stays traceable.
Knowledge Base
Every source and transform has a page, so the definition travels with the number.
Vera · AI analyst
You describe the rule. Vera asks back instead of guessing.
Visualisation
Charts, pivots and tables your team edits in place, on top of the pipeline.
Why Factophant
What sets Factophant apart?All your reporting in one modern solution.
Factophant brings together everything you need for your reports and data analysis: AI, data analysis, exportable reports, dashboards, surveys and many more features around your reporting obligations.
| Approach | Breaks because … | In Factophant |
|---|---|---|
| AI assistants (Claude, ChatGPT, Copilot)Works when you want to explore data. | The result is not deterministically reproducible, so it cannot be audited. | AI builds the logic with you, and it is fixed as an SQL pipeline. Every run gives the same result, traceable and versioned. |
| Spreadsheet (Excel)Works when the analysis is one-off and small. | Traceability, versioning and documentation are made by hand and often depend on one person. | Every rule is a step in the pipeline, every change a new version, and the documentation sits next to it in the knowledge base. |
| BI toolWorks when the data arrives already calculated. | It draws the chart. The calculation happens somewhere else beforehand and is not versioned with it. | The data arrives, is calculated and is shown in one app, and all three are versioned together. |
| Data warehouseWorks when IT capacity is available for the long term. | A high upfront investment, and maintaining the business logic stays with IT instead of the business team. | The business team describes the report itself, and the technical team can still read every query. |
| Standard reporting softwareWorks when your process matches the software's exactly. | The logic is locked inside the software: you cannot see it or change it, and every deviation becomes a change request. | The logic is yours: fully visible, adaptable and exportable. |
AI assistants (Claude, ChatGPT, Copilot)
Works when you want to explore data.
- Breaks because …
- The result is not deterministically reproducible, so it cannot be audited.
- In Factophant
- AI builds the logic with you, and it is fixed as an SQL pipeline. Every run gives the same result, traceable and versioned.
Spreadsheet (Excel)
Works when the analysis is one-off and small.
- Breaks because …
- Traceability, versioning and documentation are made by hand and often depend on one person.
- In Factophant
- Every rule is a step in the pipeline, every change a new version, and the documentation sits next to it in the knowledge base.
BI tool
Works when the data arrives already calculated.
- Breaks because …
- It draws the chart. The calculation happens somewhere else beforehand and is not versioned with it.
- In Factophant
- The data arrives, is calculated and is shown in one app, and all three are versioned together.
Data warehouse
Works when IT capacity is available for the long term.
- Breaks because …
- A high upfront investment, and maintaining the business logic stays with IT instead of the business team.
- In Factophant
- The business team describes the report itself, and the technical team can still read every query.
Standard reporting software
Works when your process matches the software's exactly.
- Breaks because …
- The logic is locked inside the software: you cannot see it or change it, and every deviation becomes a change request.
- In Factophant
- The logic is yours: fully visible, adaptable and exportable.
FAQ
Questions before you start.
Factophant is a solution for your recurring reports and data analysis. With AI you develop interactive applications from your logic and your data, collect data through surveys and collection rounds, and fill your reports again every period. Every figure stays traceable and versioned.
You don't rebuild anything. New data arrives by upload, through the API, a survey or a collection round, and your application calculates the report again. If a rule needs to change, you adjust it in a draft and publish it as a new version. Earlier results are kept.
No. You describe the rule and the AI writes the SQL, and it asks when a rule is unclear. Every query stays readable, so someone who knows SQL can check it.
Yes. A survey app gives you one link anyone can answer without an account. In an indicator app, each reporting unit's figures come from the people responsible for it.
On AWS in Frankfurt (eu-central-1). Each workspace has its own database schema.
Only what the person who asked it may do, checked again on every request. An admin decides, per member, what the AI may do on their behalf.
Yes. You can download an app as a portable bundle, and a connected system can pull a run's results as CSV through the Automation API.
Sign up, name your workspace and upload a file. Billing details are optional at sign-up.
Docs
Read how it works before you start.
The user docs cover the three apps, connecting your own AI, the Automation API and how your data is handled. In English and German.
Your next report starts here.
Start with a file you already have. Develop the rest with AI, traceable at every step.