COURSE 08Beginner9 IN-DEPTH LESSONS

Prompting, Use and Verification

Mastering model steerability: prompt engineering patterns, structured output formatting, chain-of-thought, hallucination reduction, and verification workflows.

Start Lesson 1: Prompting →← All 29 Courses

Course Syllabus & Units

Unit 1

Prompting

1 lessons
1.1L0

Prompting

A **prompt** is the text (and sometimes images) you give a model so it can continue. Because LMs predict next tokens, your words are the steering wheel—not a magical spell language.

Read lesson →
Unit 2

Failure

1 lessons
2.1L0

Hallucinations

In everyday AI talk, a **hallucination** is when a model produces confident content that is **not grounded in reality**—fake citations, invented biographies, wrong numbers—while sounding fluent.

Read lesson →
Unit 3

Patterns

1 lessons
3.1L0

Prompting patterns

**Prompting patterns** are reusable ways to structure instructions: roles, examples, checklists, step-by-step reasoning requests, and output schemas.

Read lesson →
Unit 4

Multimodal

1 lessons
4.1L0

Multimodality

**Multimodal** systems handle more than one kind of signal—text plus images, audio, video, or other sensors.

Read lesson →
Unit 5

Evaluation

1 lessons
5.1L0

Evaluation of prompts

Treating prompts like code: version them, test them on a fixed set, and reject changes that regress quality.

Read lesson →
Unit 6

Structured

1 lessons
6.1L0

Structured outputs

Getting models to return **JSON/schemas** (or other strict formats) so software can parse results safely.

Read lesson →
Unit 7

Security

1 lessons
7.1L0

Prompt injection literacy (builder)

**Builder-facing literacy** on prompt injection: untrusted text (users, web pages, emails, retrieved docs) trying to override instructions or exfiltrate data. Defensive posture only—see Course 29 for citizen overview without how-to attacks.

Read lesson →
Unit 8

Style

1 lessons
8.1L0

Style and audience controls

Steering **tone, reading level, format, and audience** without changing the underlying facts you still must verify.

Read lesson →
Unit 9

Verification

1 lessons
9.1L0

Claim-checking workflow

A repeatable workflow to verify AI claims: extract claims → find sources → accept/hedge/reject → only then publish.

Read lesson →