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.
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
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
Order summary
Subtotal38.00
Tax4.00
Total42.00
Place orderStep you write
Set cell 'Qty' to '5' on the 'Approved' row
Compiled once
{"verb":"set-cell","target":{"grid":"Orders","column":"Qty","row":{"Status":"Approved"}},"value":"5"}Resolved viaLive vision: the grid exposes no cells
Qventis Core sees the screen
Order entry custom-drawn grid
OrderStatusQty
10421Draft2
10422Approved5
10423Hold1
Step you write
Type '{{po.number}}' into 'PO NUMBER' and press Enter
Compiled once
{"verb":"type","target":{"label":"PO NUMBER","screen":"PO INQUIRY"},"value":"{{po.number}}","then":"enter"}Resolved viaTerminal data stream
Qventis Core sees the screen
PO INQUIRY SCREEN 04
PO NUMBER . . . 4500017731
VENDOR . . . . 120044
STATUS . . . . OPEN
F3=EXIT F5=REFRESH ENTER=INQUIRE
Step you write
Run 'Create sales order' and check that 'Status' shows 'Created'
Compiled once
{"verb":"run","target":{"task":"Create sales order"},"then":{"verb":"check","target":"Status","expect":"Created"}}Resolved viaDOM and accessibility tree
Qventis Core sees the screen
Create sales order packaged ERP screen
StatusCreated
Step you write
Send POST to '/orders' and check status '201'
Compiled once
{"verb":"send","method":"POST","path":"/orders","expect":{"status":201}}Resolved viaHTTP contract
Qventis Core sees the screen
POST /orders
{
"customer": "acme-retail",
"lines": 3
}201 Created
{ "id": "ord_10422" }Step you write
Compare 'staging.orders' with 'dw.fact_orders' on 'order_id'
Compiled once
{"verb":"compare","left":"staging.orders","right":"dw.fact_orders","key":"order_id"}Resolved viaSQL connection
Qventis Core sees the screen
staging.orders
104211042210423=
dw.fact_orders
104211042210423Every 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.
| Layer | Checkout pageWeb | Custom-drawn gridWinForms desktop | Order entryCitrix session |
|---|---|---|---|
| Web DOM and shadow DOM | Resolved | None | None |
| Accessibility and UI Automation trees | Cross-checked | Grid only, no cells | None |
| Native control APIs (Java, SAP GUI, .NET) | Not needed | Partial | None |
| Terminal data streams | Not needed | Not needed | None |
| Live vision | Confirms | Resolved | Resolved |
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.
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
- Web
await expect(page.getByLabel('Total')).toHaveText('42.00'); - API
expect(body.total).toBe('42.00'); - Desktop
engine.check(Label("Total"), TextEquals("42.00")) - Mobile
expect(await $('~Total').getText()).toBe('42.00'); - Data
SELECT 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.
The same verbs mean the same thing on web, desktop, mobile, API and data. Targets are labels people recognize, never selectors.
OpenClickTypeSelectTick / UntickChoose
PressWait forRememberCheckUseRepeat / If
Select 'Express' in 'Shipping method'
Remember 'Order number' as {{order.id}}
Send GET to '/orders/{{order.id}}'
Qventis Core reads every layer a Windows app exposes, then switches to live vision for custom-drawn controls that object-based tools see as one blank pane.
- Record a journey and watch plain-English steps appear as you click
- Custom-drawn controls, dense grids and remote sessions
- Every check retries to its timeout and records evidence
Heal proposal: Checkout total is correctNeeds approval
Step 4 could not find the 'Total' field. A field labeled 'Order total' now sits in the same place.
Was
the 'Total' field
the 'Total' field
Proposed
the 'Order total' field
the 'Order total' field
Evidence: before and after screenshots and every other test affected.
Approve healAgents can propose. Only people approve.
Runs anywhere
Keep what you build
# run a suite and fail the pipeline on errors qventis run --suite smoke --env test # take your web tests with you qventis export --to playwright ./exported
- Headless from the CLI and SDK, in any CI
- Coding agents call the same runs through the Agent gateway
- Playwright export and Git-friendly files. No lock-in.
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.