Course · AI & Technology

AI for Professionals: Using LLMs at Work

A practical course on using large language models confidently and safely at work: how they work and why they hallucinate, prompting (role, context, task, format, examples, reasoning, structured output), iteration and verification, RAG and agents, data privacy and AI literacy (EU AI Act). Tool-neutral.

0 / 18 lessons done

New lesson →

Unit 1. How an LLM actually works

Lesson 1: It predicts the next token, it does not look things up

6 exercises · Explain that an LLM generates text by predicting the most likely next token from patterns in its training data, and that by default it does not browse the internet or remember past sessions.

Lesson 2: Why models hallucinate (and confidently)

6 exercises · Explain why an LLM can produce fluent, confident statements that are factually wrong, including the 'rewarded for guessing over admitting uncertainty' framing.

Lesson 3: Tokens, the context window, and what models can and cannot do

6 exercises · Explain tokens and the limited context window, and classify everyday tasks into things LLMs are reliably good at versus things they are weak at.

Unit 2. Anatomy of a good prompt

Lesson 1: Role, context, task, format

6 exercises · Identify the four building blocks of an effective prompt — role, context, task, and output format — and recognize each in a sample prompt.

Lesson 2: Why a vague request gives a vague answer

6 exercises · Diagnose the specific weaknesses in a vague prompt (missing audience, goal, context, or format) and predict how they degrade the answer.

Lesson 3: Rewrite a weak prompt (first writing practice)

4 exercises · Rewrite a weak, underspecified prompt into a strong one that supplies role, context, task, and format for a realistic work scenario.

Unit 3. Advanced prompting

Lesson 1: Examples (few-shot) and step-by-step reasoning

6 exercises · Apply few-shot examples and chain-of-thought (step-by-step) prompting, and choose which technique fits a given task.

Lesson 2: Constraints, style, and structured output

6 exercises · Add constraints (length, style, what to rely on) and request structured output (list, table, or JSON) so the answer is usable and predictable.

Lesson 3: Break a big task into steps

6 exercises · Decompose a large, fuzzy task into an ordered sequence of smaller prompts and assemble the result.

Unit 4. Iterate and verify

Lesson 1: The dialogue is the process

6 exercises · Run the model as an iterative dialogue, using follow-up moves like 'critique your own answer', 'redo it shorter', and 'give me three options' instead of accepting the first reply.

Lesson 2: Spotting and catching hallucinations

6 exercises · Identify high-risk claims in an LLM answer (facts, citations, numbers, code) and apply concrete techniques to catch hallucinations.

Lesson 3: Verify facts, numbers and code — and own the result

5 exercises · Verify an LLM's factual, numeric, and code output and articulate that the human remains responsible for what is shipped.

Unit 5. RAG, agents, and tools

Lesson 1: Grounding the model in your own data (RAG)

6 exercises · Explain retrieval-augmented generation as grounding the model in external documents and citing retrieved passages to reduce hallucinations.

Lesson 2: Agents and tool use

6 exercises · Explain what an AI agent is — a model that calls tools and acts step by step — and describe the reason–act–observe loop with a human in the loop.

Lesson 3: Realistic scenarios at work

6 exercises · Choose the right approach — plain prompting, RAG, or an agent — for realistic workplace scenarios and frame the task for it.

Unit 6. Safety, privacy, ethics; and the capstone

Lesson 1: What you must never paste, and data policies

6 exercises · Apply privacy and security rules for using public AI services: never paste secrets, personal data, or trade secrets without permission, and check data-use settings and company policy.

Lesson 2: AI literacy, the EU AI Act, bias and transparency

6 exercises · Explain workplace AI literacy as a duty (including the EU AI Act Article 4 example) and identify ethics issues: data bias, transparency/disclosure, and copyright/attribution.

Lesson 3: Capstone — build and improve a prompt for your own task

5 exercises · Build, critique, and improve a prompt for the learner's own real work task, applying role/context/task/format, constraints, iteration, verification, and privacy, checked against a rubric.