Use it when the data already exists: exports, spreadsheets or another system.

Bring the data you have. Shape it into the report.

Upload the exports you already have and describe what the report should show. AI builds the pipeline, writes the knowledge base and puts the Visualisation on top, and you can read every step.

Four parts

From a file to a published version.

The pipeline, its knowledge base and the Visualisation are published as one version. Vera builds the pipeline from what you describe.

Data Pipeline

Docs

CSV, Excel or an API, in the shape you already have.

Next year you don't rebuild the calculation, you re-run it. Dataset nodes, SQL transforms and bridges to other apps form one graph, and every run is stored with the version it ran against.

  • Upload CSV, XLSX or XLS; columns are typed on import
  • Push files nightly through the automation API
  • Pull an indicator app's figures or a survey's responses

Knowledge Base

Docs

Every number carries its definition.

Sources, rules and definitions in Markdown, next to the logic they describe and versioned with it. Part of every analytic app, so whoever checks a number reads its definition beside it.

  • A page for every source and transform
  • Import Markdown, CSV, PDF, Word, PowerPoint or Excel
  • Skills: a reusable AI task, written once

Vera · AI analyst

Docs

You describe the rule. Vera asks back instead of guessing.

Vera builds the pipeline, the logic and the documentation from a plain-language description, and pauses on a rule it is unsure of instead of deciding it alone.

  • Asks a question and waits for the answer
  • Writes SQL you can read afterwards
  • Acts only within your own permissions

Visualisation

Docs

Charts and pivots, plus tables your team edits in place.

The app that calculates the number is the one the data arrives through. The views are part of the versioned definition.

  • Nine widgets: table, chart, pivot, figure, parameters, SQL editor, text, AI and knowledge base
  • Ask the data a question in plain language
  • Query anything downstream with plain SQL

Also in an analytic app

The parts you reach for in the second week.

Bridges to other apps

Pull an indicator app's figures, another app's published result, or a survey's responses into the pipeline.

Validation rules

Compiled on every run into two tables you can query: every rule, and every failing row.

Skills

A reusable AI task written once, offered as a one-click widget and to your own AI over MCP.

Ad-hoc SQL

Ask anything downstream with plain SQL, on the same engine the pipeline runs on.

Runs and versions

Run the draft as a private preview. Publish it when it is right. Every published version stays, and you can restore one.

Knowledge base imports

Markdown, CSV, PDF, Word, PowerPoint and Excel become pages next to the logic they describe.

Works with

When the report needs more than this app.

Indicator app

Collect figures period by period from the people responsible, check them, and lock the period.

Its published figures come into the pipeline through a bridge.Explore the Indicator appSurvey app

One link, no account and no sign-in, and every answer lands as a row.

A published survey appears as a source in the pipeline.Explore the Survey app

Build an analytic app on a file you already keep.

Upload it, describe what you measure, and Vera builds the first pipeline.

Book a demo (opens in a new tab)