MODULE 3.2 / 8 OF 9
JEV: AI Decisions in Practice
Explain what a structured decision with Jev is, choose between Choice, Noul, and Score, and separate what has already been observed from what still needs to be measured.
Area page: eventos.inema.pro/jev/en/ · in the menu: “AI decisions in practice”
1What JEV is
What it is
Jev is TypeSafe’s structured decision model. A structured decision is a closed question with context and criteria. Its answer is a choice, a probability, or a level, not free-form text. The Jev Decision Lab is INEMA’s educational project for formulating questions, comparing answers, and understanding when a decision needs review. The model receives context and criteria; your system remains responsible for taking action. The lab separates this choice from text generation and tool execution.
Why learn it
Many AI tasks at work don’t call for text; they call for a decision: which queue should this ticket go to? Does this passage support the claim? Separating decisions, generation, and execution makes clear who is responsible for each part and makes it easier to measure accuracy.
Key concepts
structured decision model; TypeSafe; Jev Decision Lab; context and criteria; the system is responsible for actions
In practice
A support team wants AI to route tickets. Instead of asking for a paragraph, it uses Jev to choose a queue from fixed options. The company’s system moves the ticket, and uncertain cases go to a person.
✓ Do
List two repetitive decisions in your work that currently turn into free-form text, and rewrite each as a closed question with options.
✗ Avoid
Judging the area by its name: read the main idea on the page before deciding if it’s for you.
2Choice, Noul, and Score
What it is
The page presents three ways to ask a question. Choice selects from explicit alternatives, such as which queue or which agent. Noul estimates the probability of an affirmative answer, such as the chance that a passage supports a claim. Score evaluates a rubric with ordered levels, such as low, medium, and high. One course module covers how to distinguish the three based on the kind of answer you need, and another covers confidence and error: using uncertainty without turning it into automatic authorization.
Why learn it
Choosing the wrong format produces answers that are hard to use: a score when you needed a queue, or a yes when there were several levels. The form of the question determines how you will measure results and which policy to apply.
Key concepts
Choice: explicit alternatives; Noul: probability of yes; Score: ordered levels; confidence is not authorization
In practice
For meeting follow-up, "does the meeting record include an owner and a deadline?" is Noul; "which team handles this?" is Choice; "what is the log’s priority, from 1 to 4?" is Score. The same meeting can lead to all three questions.
320 cases in the public lab
What it is
The lab runs in your browser, requires no key, and doesn’t call any API: its answers are simulated. Each of the 20 cases includes context, questions, criteria, a simulated answer, an explanation, and a next step. Examples include support triage, a contract checklist, agent routing, and semantic diff review. You can edit the questions, import a request, export the result, or open a report; changing a case invalidates its previous simulated answer. To go further, you can clone the project and run the local server with Python 3.10 or later. The core uses only the standard library.
Why learn it
The lab lets you make mistakes without cost or risk. You learn to formulate the context, options, and policy before spending credits or touching a real system.
Key concepts
lab requires no key; simulated answers; 20 cases; context, questions, criteria; local Python server
In practice
A coordinator opens the "Simultaneous intents" case and sees that a conversation can include sales and scheduling at the same time. They realize their company’s question, which allows only one option per message, needs to change.
Steps to try
- Open the area page beside this lesson.
- Open https://inematds.github.io/jev/app/, choose the case closest to your work, and rewrite one of its questions using your criteria.
- Write one sentence about what changed in your understanding.
4The course: 3 learning paths, 36 lessons
What it is
The course "Jev in Practice" has three learning paths, 12 modules, and 36 lessons with theory, examples, exercises, and answers. The Understand path covers where Jev fits, the three question types, confidence and error, and cost. Apply covers support, documents, models and agents, and the browser. Build and Evaluate covers integration, quality measurement, operations, and the final project. Modules 1 through 8 are conceptual; modules 9 through 12 use JSON, the terminal, and Python. The estimated time is 18 hours. There are 12 labs with fictional data and answer keys. The final project asks you to decide whether there is evidence to adopt, collect more data, or not automate. The HTML v2 course is in Portuguese, with progress tracking, questions, and notes.
Why learn it
The course takes you from "understanding the idea" to "deciding whether to adopt" using a rubric. The final project accepts "do not automate" as an answer, which trains sound judgment rather than enthusiasm.
Key concepts
Understand; Apply; Build and Evaluate; 12 modules; 36 lessons; 12 labs; final project; 18 hours
In practice
An analyst with no programming experience completes modules 1 through 8 and works through the labs on support and evidence. Their programming colleague continues with modules 9 through 12 and builds the real request.
✓ Do
Open the course at https://inematds.github.io/jev-curso/ and choose the module that matches the decision you listed.
✗ Avoid
Jumping to the tool or course without understanding the problem the area addresses.
517 packages and ways to use them
What it is
A package is a kit for a specific area with context, criteria, a request, a fixture (a ready-made example for testing), and instructions. The current collection has 17 packages, covering areas from support and sales to YouTube comments, meetings, video clips, and curation. All packages share the executor and Python core: without the --live option, a package uses the simulated fixture; with it, the package makes a real query, which requires a backend key and may use credits. There is also batch execution with resume support, the jev-decidir skill for Codex and Claude Code, and jev-gw, a gateway with a daily spending cap, cache, cost logging, and a conservative failure mode that sends cases for human review. The packages are in the repository; there is no PyPI distribution, universal installer, or ready-made n8n connector yet.
Why learn it
You can move gradually: start offline, understand the output, and only then pay for real queries. The gateway shows how to protect the system that calls Jev when something fails.
Key concepts
area-specific package; fixture; --live; batch runs and resume; jev-decidir skill; jev-gw; conservative failure mode
In practice
A content team first uses the YouTube comments package with the fixture. When the output makes sense, they configure the real query on the server and put jev-gw in front of it, so exceeding a spending cap sends the case for review instead of breaking the system.
6What has been observed and what still needs to be measured
What it is
The page separates four situations. Learning simulation: the 20 cases and replay are original and simulated; they do not measure model quality. Rules baseline: 20 correct out of 24 fictional tickets (83.33%), a result of the rules, not Jev. Real integration tested: on 09/19/2026, the ten original packages received responses through OpenRouter with the expected classifications in the fictional examples. This confirms the integration, not a benchmark; the seven new packages have only controlled tests. Evaluation still needed: quality in Portuguese, calibration, and operational use require independent data and human reference judgments. Laya, a local alternative under evaluation, passed 14 application tests and got 13 correct out of 16 synthetic examples. This does not prove it is superior.
Why learn it
This separation is what makes the area trustworthy: every number comes with what it proves and what it does not prove. Repeating these numbers out of context would overstate the results.
Key concepts
simulation; rules baseline; real integration; evaluation needed; Laya under evaluation; not a benchmark
In practice
A manager reads "ten real queries without failures" and nearly approves the adoption. After reading the whole section, they see that the test confirms the integration works, not that Jev gets the company’s data right, and ask for a pilot with human reference judgments.
Criteria for reviewing your worksheet
Use this rubric after the lab. Each row asks for evidence; marking a topic as read doesn’t mean the worksheet is complete.
| Criterion | Expected evidence | If it doesn’t meet the criterion |
|---|---|---|
| Main idea | You can describe the area in one sentence that reflects the page. | Reread the top of the page and topic 1. |
| Audience | You can say who the area is for and who it isn’t for. | Return to topic 2 and write an example from your work. |
| Core elements | You can name the area’s core elements. | Use the module diagram as a guide. |
| First step | You chose a small, concrete step. | Copy the first step recommended on the page itself. |
| Starting point | You know which course, kit, or project to open first. | Check topic 6 and the page’s access section. |
| Source | Every statement in the worksheet comes from the page. | Replace your assumptions with what the page says. |
HANDS-ON / ~10 MIN
Your structured decision, from case to pilot
Keep the area page open: https://eventos.inema.pro/jev/en/. Use an example from your work, without personal or client data.
Prompt: my structured decision with JEV
Paste it into Claude, ChatGPT, or Codex. Replace the words inside < and > with details about your situation.
Read https://eventos.inema.pro/jev/ and the guide https://inematds.github.io/jev/guia/.\nI want to turn a repetitive decision from my work into a structured decision, without claiming quality I haven’t measured.\nMy decision: <describe, e.g., which team each customer email should go to>.\nPossible options or levels: <list them>.\n1. Say whether the question is Choice, Noul, or Score, and why.\n2. Write the minimum context, criteria, and question.\n3. Propose the policy: when to follow the suggestion, when to abstain, and when to send it for human review.\n4. Indicate which of the lab’s 20 cases and which of the page’s 17 packages are most similar to my decision.\n5. Make a "already observed vs. still needs measuring" list for my case. Do not treat simulation as a quality measurement.
Completion criterion
Explain what a structured decision with Jev is, choose between Choice, Noul, and Score, and separate what has already been observed from what still needs to be measured. Keep the worksheet with the main idea, audience, first step, and starting point.
Open the area page ↗Review what you’ve learned
The public lab showed correct answers in every case you opened. Does that measure Jev’s quality?
View suggested answer
No. The 20 public cases and the replay are original and simulated; they are for studying formulation, policies, and errors. Quality in Portuguese and calibration still need independent data and human reference answers.
If your answer was different, return to the relevant topic and describe the difference in one sentence. This check won’t block your progress.
Module summary
- structured decision model; TypeSafe; Jev Decision Lab; context and criteria; the system is responsible for actions
- Choice: explicit alternatives; Noul: probability of yes; Score: ordered levels; confidence is not authorization
- lab requires no key; simulated answers; 20 cases; context, questions, criteria; local Python server
- Understand; Apply; Build and Evaluate; 12 modules; 36 lessons; 12 labs; final project; 18 hours
- area-specific package; fixture; --live; batch runs and resume; jev-decidir skill; jev-gw; conservative failure mode
- simulation; rules baseline; real integration; evaluation needed; Laya under evaluation; not a benchmark
Check the source
Pages read on 28/09/2026. Area content changes; the official page takes precedence over this summary.