Your reading comfort
TRACK 1

🧭 Fundamentals

Understand what the decision solves before installing any model.

2 modules 12 topics 70–100 min with practice 12 exercises
Understand Try Verify LAYA / INEMA · conceptual flow
Your progress

Track map

1.1 35–50 min

🧭 Deciding is not conversing

Choose the tool by output type.

1.2 35–50 min

🧭 The three primitives

Write questions that can be evaluated.

Detailed content

MODULE 1.1

Deciding is not conversing

Choose the tool by output type.

What it is

A decision engine takes a state and chooses within a defined set.

Why learn

Overlapping categories make the label ambiguous even before involving AI.

Key concepts

State

observed information

Schema

question contract

Label

exit option

Action

effect on the system

What it is

System 1 is an analogy for quick, bounded decisions; System 2 represents tasks that require elaboration, planning, or generation.

Why learn

Separating steps lets you measure the cost and error of each one.

Key concepts

Reflex

narrow task

Deliberation

extensive analysis

Composition

distinct steps

Rule

deterministic decision

What it is

In Laya inference, an encoder processes the sequence and computes values for the options.

Why learn

A forward pass does not mean constant cost.

Key concepts

Encoder

represents input

Batch

multiple sequences

Logit

value before softmax

Inference

model calculation

What it is

Jev appears in sources as a decision service accessed via API.

Why learn

Hosting a model involves installation time, memory, energy, monitoring, and updates.

Key concepts

Self-hosted

own execution

API

remote service

Total cost

complete operation

Dependency

required service

What it is

The provided images present a narrative of competition, with phrases like the end of LLMs and an alternative that’s even faster.

Why learn

In the course, the image serves as an editorial reference.

Key concepts

Promotion

gets your attention

Hypothesis

testable claim

Evidence

recorded result

Scope

condition of the conclusion

What it is

This course project is a triage console in Portuguese.

Why learn

Before installing, write the minimal input, the categories, the meaning of urgency, and who decides the final routing.

Key concepts

Minimal input

no excess

Responsible

confirms the decision

Outside the domain

residual case

Criterion

expected result

View Full →
MODULE 1.2

The three primitives

Write questions that can be evaluated.

What it is

Choice returns the alternative with the highest value in the distribution and the options’ probabilities.

Why learn

Short names with clear descriptions help distinguish classes without consuming the entire token budget.

Key concepts

Argmax

highest value

Distribution

set of probabilities

Criterion

class description

Residual

other option

What it is

Score uses an ordered list of levels.

Why learn

A scale only makes sense when the levels have order and distinguishable criteria.

Key concepts

Ordinal

ordered levels

Expectation

weighted average

Legend

meaning of the levels

MAE

mean absolute error

What it is

Noul responds to a statement with a value between zero and one.

Why learn

Questions about explicit intent are easier to label than vague predictions about future behavior.

Key concepts

Statement

proposition

P(true)

modeled probability

Evidence

observed phrase

Threshold

operational cut

What it is

In the analyzed SDK, the confidence of choice and score is 1 minus the normalized entropy of the distribution.

Why learn

Do not compute ECE using a field called confidence without checking the code.

Key concepts

Entropy

dispersion

Top probability

highest probability

Calibration

frequency versus prediction

Concentration

internal certainty

What it is

The schema contains stable identifiers, type, instructions, and criteria when necessary.

Why learn

Validate results against the policy: classes must be known, values must be finite, and probabilities should approximately sum to 1.

Key concepts

Contract

stable format

Validation

data checking

Tolerance

rounding

Consumer

code that reads output

What it is

Write six customer support messages and manually answer the four questions.

Why learn

Disagreements between humans show where the question or rubric needs improvement.

Key concepts

Labeling

human answer

Ambiguity

multiple readings

Adjudication

documented agreement

Reservation

unaligned examples

View Full →
Module reading