Judgement is becoming cheap.
Every company makes thousands of small judgements a day. Is this complaint urgent? Is this report complete? Does this invoice match the order? Most are made on a sample or too late, because a person has to make them. A new kind of AI model makes them in about half a second, for a fraction of a cent, and says how sure it is.
A new kind of model that decides, and says how sure it is.
A chat model writes an answer. A decision model, the first of which is Jev from TypeSafe, picks one of the answers you allow and says how sure it is. Below, both get the same fault report at the same moment.
Fault reportLine ID attachedCustomer offline since 07:40Line test: no light at the fibre boxAccess next week, date to be agreed
Is this report complete enough to send a technician?
0.87 is below the 0.90 you set
No, this fault report is not complete enough to dispatch a technician. Key information is missing, including the specific Line ID (it says “attached” but isn’t shown), the exact nature of the fault (no light at ONT could indicate multiple issues), and crucially, no confirmed appointment date/time has been scheduled with the customer for next week.
No number to compare
Someone has to read the sentence
Where it is strong
- About half a second and $17 per million decisions
- A probability with every answer, so software can act on it
- The same input gives the same answer
Where it is weak
- It writes no text and gives no reason
- Its probabilities need checking on about 50 of your own cases
- It runs in the US only: personal data is pseudonymised first, or an open model runs on your own servers
On short texts, close to a large chat model at a fifth to a seventh of the cost. On long contracts, 4 points behind.
Four public test sets, each run through Jev, a large chat model (GPT-5.6 Luna) and a free model that runs on your own hardware, with the same instructions, September 2026.
| Test | Right answers | Cost per million decisions | Time per case | ||||
|---|---|---|---|---|---|---|---|
| Jev | GPT-5.6 Luna | Free model | Jev | GPT-5.6 Luna | Jev | GPT-5.6 Luna | |
| News sorting300 public news articles, each sorted into one of four sections | 89% | 87% | 86% | $17 | $87 | 0.5 s | 2.0 s |
| Telecom requests300 customer requests to a telecom operator, routed to one of seven teams | 95% | 98% | 83% | $20 | $144 | 0.4 s | 2.4 s |
| One detail flips the answer100 pairs such as “please cancel” and “please don’t cancel” | 100% | 100% | 58 to 72% | $17 | $87 | 0.5 s | 2.0 s |
| Full contracts300 checks of full confidentiality agreements against fixed statements | 80% | 84% | 48% | $90 | $720 | 0.4 s | 2.8 s |
GPT-5.6 Luna: a large chat model from OpenAI. Free model: a similarity model that runs on your own hardware, so it has no cost per decision. Cost and time for the pairs follow the news test, since the texts are of the same length. The telecom requests are synthetic, written for chatbot training (Bitext, CDLA-Sharing licence). In these four tests the large chat model cost 5 to 8 times as much per decision as Jev; on longer support emails, about 11 times.
Method, data and the independent tests others published: the details.
Not plug and play: each question needs a threshold calibrated on your own cases.
A threshold only works if “90% sure” means right about 90% of the time. That holds on familiar tasks and slips on unfamiliar ones, so every question goes through a short calibration before it runs on its own.
Calibration decides how much runs on its own. In the telecom test, 90% of the requests cleared 0.90 and 98.9% of those were right; the large chat model cleared 0.90 on 75%. In the news test, 82% of the articles needed no person. On tasks the model has not seen, independent testers found calibration 2 to 4.4 times worse. Where a company’s categories differ from the plain meaning of the words, a model can be very sure and still wrong; only a check on your own cases shows it.
- Check the labels firstDo two people give the same answer on 30 to 50 cases? Where they disagree, no model will be reliable, and the categories need cleaning before anything else.
- Label about 50 past cases per questionfrom your own data. For a rare outcome, about 300 cases with at least 100 of the rare one.
- Compare and correctthe model’s probabilities against the true answers. A one-line correction usually brings them back in line.
- Set the threshold from what an error costsA wrong automatic dispatch costs a wasted visit; sending back a complete report costs the customer a day.
- Pin the model version and check againbefore a new version takes over the same question.
Method and sources: how the tests are run.
What you could decide on every case.
Pick a department. Each card is one decision: the question, the answers you allow, and what one million of them cost. The cost is the measured price; how often each decision is right is tested on your own cases before it runs.
Costs as measured. Short texts such as messages and reports: about $17 per million with Jev, $87 with a large chat model. Full documents such as contracts: about $90 against about $720. At 2 million fault reports a year the model bill is about $34 with Jev, so the money lies in the staff hours on the cases that no longer need a person. Mark the decisions that fit your company; the first conversation starts with them.
Companies already report results.
Four companies in their own figures, within weeks of the release.
Unblocked
Their assistant answers engineers' questions from internal notes. Jev decides which notes belong in each answer.
More of the right notes and fewer wrong ones, in production, for under two dollars per thousand questions.
SourceFurtherAI
An AI agent fills in insurance quotes on broker portals. Jev picks each next step.
A quote that took 18 minutes now takes about 5, and the setup is moving into production.
SourceCinchOps
A small IT firm sorts customer reviews and search queries by topic.
5,300 reviews sorted for 14 cents instead of 50 dollars, as accurately as the expensive model.
SourcePricogni
A pricing tool matches competitors' products so prices can be compared.
9,081 product pairs checked for 32 cents. The unclear ones go to a person.
SourceWhere would cheap judgement pay off for you?
Pick the one closer to your situation; the next step starts there.
Where does your company make the most of these judgements?
What usually comes up in the first meeting.
Jev runs on US servers. Personal data is pseudonymised before a case is sent, or an open model of the same kind runs on your own servers. The details list what a works council usually asks.
Below the threshold every case still goes to a person. People set the thresholds, handle the unclear cases and check a monthly sample of the automatic ones.
Each decision is one call from the system you already use: a ticket, a dispatch or an invoice step. The wiring for one decision is part of the Decision Test.
The default version can change without notice. The threshold is set on a pinned version, and a new version goes through the same check before it takes over.
The model bill is small. The work lies in labelling about 50 cases per question, the integration and the handling of unclear cases; the Decision Test prices this for one decision.
Four public tests are measured, one of them on telecom requests. In German, results were a few points lower than in English, so a rollout in German is tested in German. Each decision in your company is tested on your own past cases before anything runs on its own.
More on data protection, works council and IT: the details.
Talk one decision through with Peter.
30 minutes on one decision in your company. If it fits, three steps can follow, and you can stop after any of them.
- Decision Discovery90 minutes
3 to 5 decisions worth testing
- Decision Test1 to 2 weeks
Your past cases, a go or no-go
- Production Pilot4 to 8 weeks
One live decision
Reply within 48 hours. No customer data needed. Data protection, works council and IT

Strategist and builder for AI and new ventures, with startup experience. Peter works inside your team, from the first question to a process that runs in production. Email: peter.milan.trapp@gmail.com, LinkedIn
- Tested independently. Every comparison and calculation on this page comes from own runs through the public interface, without TypeSafe’s involvement. Results of other companies are their own figures.
- Pilots and workshops in several industries on where cheap judgement changes decisions, processes and teams.
- A workshop kit inside the lab, so a team can run the inventory on its own.
The details for your team →How it works, the measurements against chat models and free methods, where it fails, and a free check on a decision of your own.
More from the lab: IndustriesWhat people took from thisPrivacy