qventisqventis

Qventis CoreQventis Core

The automation core of Qventis One, built for the systems that run your business. Write the step in plain English. It compiles once and runs the same way every time on your runners, with no model in the loop.

  • No AI bill per run
  • Same result every time
  • Reads custom-drawn screens
Live: one step, six channels
Step you write

Check that 'Total' shows '42.00'

Compiled once{"verb":"check","target":{"label":"Total","role":"field"},"expect":"42.00"}

Resolved viaWeb DOM, cross-checked by vision

Qventis Core sees the screen
checkout

Order summary

Subtotal38.00
Tax4.00
Total42.00
Place order
Passed, evidence saved0 AI tokens at run time

Every layer, then vision

For each control, Qventis Core uses the richest signal the screen offers: the DOM, accessibility and UI Automation trees, native control APIs or terminal data streams. When a layer is missing, custom-drawn or remote, live vision takes over automatically in the same step, and both signals cross-check each other wherever both exist.

How Qventis Core resolves a controlPer step, in real time
Which technical layer resolves a control on three kinds of screen
LayerCheckout pageWebCustom-drawn gridWinForms desktopOrder entryCitrix session
Web DOM and shadow DOMResolvedNoneNone
Accessibility and UI Automation treesCross-checkedGrid only, no cellsNone
Native control APIs (Java, SAP GUI, .NET)Not neededPartialNone
Terminal data streamsNot neededNot neededNone
Live visionConfirmsResolvedResolved
Object layers first, live vision the moment they run outEvery step records the layer that resolved it

Not static OCR

Vision finds controls by label, role and layout, live, rather than matching stored image snippets. Nothing to recapture when a theme, font or resolution changes.

Switches per control

One step can resolve a field from the DOM and the next from vision. No separate script, no mode to set.

Evidence of how

Every step records which layer resolved it, so reviewers can see exactly how each control was found.

How other approaches find a control, and what it costs you

Image and OCR tools, object-only frameworks, cloud screenshot vision and runtime model lookups each stop somewhere. Qventis Core uses every layer first and live vision when a layer runs out, on your own runners.

How recognition approaches compare
ApproachHow it finds a controlWhat it means for you
Image matching and OCRStored image snippets matched against pixels, text read by OCR; no awareness of the objects underneathBreaks when theme, resolution, scaling or font changes; an image library to maintain per environment
Object-only frameworksSelectors and accessibility IDs from the DOM or UI treeStops at custom-drawn controls, canvas, terminals and remote sessions
Cloud screenshot visionScreenshots go to a vendor-run cloud service that resolves each elementScreens leave your network and every step waits on a round trip
Runtime model lookupsA language model is asked to find the element during the runCost on every step, and results can vary between runs
Qventis CoreEvery technical layer first, then live vision per control, switched automatically and cross-checkedThe richest signal for every control, nothing stored to maintain, screens stay in your network

One step, every channel, no model in the loop

Choose a step and see what it compiles to for each channel. Nothing is interpreted at run time.

Step you write

Check that 'Total' shows '42.00'

0AI tokens spent while it runs, on every channel, every time
WebAPIDesktopMobileData compiled once
  • Webawait expect(page.getByLabel('Total')).toHaveText('42.00');
  • APIexpect(body.total).toBe('42.00');
  • Desktopengine.check(Label("Total"), TextEquals("42.00"))
  • Mobileexpect(await $('~Total').getText()).toBe('42.00');
  • DataSELECT total FROM orders WHERE order_id = :order_id; -- expect '42.00'

Inside Qventis Core

One sentence, one structure

People read and edit the sentence. Qventis Core versions and compiles the structure underneath, so plain English never drifts into prose nobody can run. Select a highlighted part to see what it means.

Verb

Select a highlighted part of the sentence.


          

What runtime AI would cost you

Runtime-AI tools send a model the page and the step on every run. Estimate the model spend compile-once execution avoids.

Illustrative defaults. Enter your own figures on a basic model.

Runtime-AI model spend per year$219,000
Qventis Core model spend per year at run time$0

Put Qventis Core on your hardest screen

Bring the app your current tools cannot see. We will record it with you.