Artificial Intuition
Decision models that keep getting better at your work.
Hosted: VAKYN MAX, with an API key. Your servers: open-server, free and MIT.
- noulIs this domain pretending to be a bank?
- choiceWhich team should get this ticket?
- scoreHow risky is this expense report?
- noulDoes this CV show Kubernetes experience?
- choiceApprove, flag or reject this expense report?
- noulIs this product review fake?
For teams that make the same decision thousands of times a day.
Support inbox
Every ticket routed as it comes in. The unsure ones go to a person.
choiceWhich team should get this ticket?
Security alerts
Every alert triaged the moment it arrives. The unsure ones go to an analyst.
scoreHow urgent is this alert?
New certificates
About 6 million new TLS certificates a day. VAKYN checks every one as it appears.
noulIs this domain pretending to be a bank?
Volume: public Certificate Transparency statistics.
Expense reports
Every report checked against the policy before finance pays it.
choiceApprove, flag or reject this expense report?
Hiring
Every CV checked against every skill the role asks for.
noulDoes this CV show Kubernetes experience?
Reviews
Every review checked before it goes live on the product page.
noulIs this product review fake?
VAKYN MAX
Our hosted version, with our biggest model. Send a document and your questions with an API key; nothing to install.
Open the consoleopen-server
The open models and a free server on your own machines. Already on a Jev-compatible API? Change the base URL.
open-server on GitHub (opens in a new tab)AI that answers instead of talking.
You ask a typed question about a document: yes or no, pick one, or a score. VAKYN returns the answer and how sure it is.
- 01
Gets better at your work.
The VAKYN loop finds where it fails on your cases, trains exactly there, and proves the fix. Again whenever you need it.
- 997occupations
- in 22 domains, covered by the training
- 02
Sovereign.
It runs on your servers, in your country, under your rules, and your data never leaves. Or we run it for you on VAKYN MAX.
- Apache-2.0
- open model weights; the server is MIT
- 03
Fast and cheap at any scale.
Milliseconds per decision on one graphics card. On your own servers there is no request limit.
- 16.6ms
- median, one question on a short ticket (179 tokens); open-server, VAKYN-4B Q8_0, one RTX 5090
- ~215,000an hour
- documents with 10 parallel clients, same setup, 0 errors
Your servers. Your country. Your rules.
The model weights are open and the server is free. Run them on your own machines and the documents you send never leave them. Rather not run servers? We host it on VAKYN MAX.
- Apache-2.0
- open model weights
- MIT
- the free server
- 0.8B–4B
- model sizes
Your servers
data never leavesThe open models and the free server on your own machines. One graphics card gives the fastest results.
Your country
data never leavesIn your data center or a cloud in your country, under your rules.
VAKYN MAX
nothing to installRather not run servers? We run it for you. Send a document and your questions with an API key.
One expense report, asked both ways.
The same report and the same question, sent to a chat model and to VAKYN. The VAKYN answers are real, captured from the open model; the chat replies are written by us and labelled.
Ines Varga, field engineer
Customer site visit in Lyon, 6 October 2026
- Flight, Brussels to Lyon and back, business class, booked privately1240no receipt
- Hotel, three nights for a one-day visit1260no receipt
- Dinner, alone, two bottles of wine310no receipt
- TotalEUR 2,810
The policy sent with it
- Rail
- Second class, booked through the travel desk
- Hotel
- Up to EUR 180 a night
- Meals
- Up to EUR 60 a day while travelling, no alcohol
- Receipts
- A receipt for every line over EUR 25
choice
What should finance do with this expense report?
approve · flag · reject
This report breaks the policy in several places. The flight is business class and was booked privately, the hotel covers three nights for a one-day visit, the dinner includes two bottles of wine, and no line has a receipt. I would reject it, or at least flag it for a closer look.
- Options a parser finds
- flag, reject
- How sure, as a number
- none
Written by us to show the shape of a chat reply. Not a measured output.
- approve0%
- flag12%
- reject88%
Captured 2026-10-11 from the open model. Nothing edited.
- Wait for the last word
- Search the text for an option
- Found flag and reject. Which one did it mean? No number says how sure.
Illustrative reply, written by us.
{
"answers": {
"decision": {
"choice": "reject",
"confidence": 0.82,
"probabilities": {
"approve": 0,
"flag": 0.12,
"reject": 0.88
}
}
}
}Real answer to the clear expense report in step I.
- Time per decision
- 16.6ms
- median for one question on a short ticket (179 tokens); open-server, VAKYN-4B Q8_0, one RTX 5090
answer = reply["answers"]["decision"]
if answer["confidence"] >= 0.70:
act(answer["choice"]) # sure
else:
send_to_person(case) # unsure“I'm confident it can be approved.”
A chat model sounds just as sure when it is wrong. “I'm confident” is part of the text it writes, not a measurement, so there is no number to set a threshold on. You either trust every case or check every one.
Illustrative reply to the borderline report in step I, written by us.
Agent refund, EUR 900
Battery returned sealed and checked in by the warehouse
allow
100% sure
Code actsReview of an espresso machine
One star: stopped heating in week five
quality
97% sure
Code actsExpense report, EUR 2,810
Private business-class flight, no receipts
reject
82% sure
Code actsExpense report, EUR 498
EUR 27 taxi without a receipt, card reader broken
reject
65% sure
Person checksEight job applications
Night shift lead, several close candidates
application_3
49% sure
Person checksReview of a kettle
Boils fine, arrived late in a crushed box
quality
23% sure
Person checks
Real VAKYN answers, captured 2026-10-11 from the open model: one choice question per case. The line on each bar is the 70% threshold.
Show us your hardest decision.
We'll show you where VAKYN gets it right on your cases, where it gets it wrong, and how the VAKYN loop fixes that.
vali@vakyn.com
01
Send us your hardest decision
A sample of your cases and the call you make on each.
02
See where VAKYN stands
We run it on your cases and show you where it's right, where it isn't yet, and how sure it is.
03
Get your own VAKYN
Trained on your decisions, on your servers or on VAKYN MAX, and getting better as your team corrects it.