Skip to main content
HT
HerbDev Application Rescue
← Learning hub

Free guided course · AI 101

Understand AI. Ask better questions.

A free guided introduction to AI, prompts, evidence, agents and real-world systems, with HerbDev examples, audio and scored checkpoints.

Beginner · 6 lessons · 18 questions · About 48 minutes · No account needed

  • AI 101
  • Practical examples
  • Self-paced learning

“I believe AI is part of our future, and everyone should have free access to learn it. These courses are free, open to everyone, and never require an account.”

— Herb Trevathan, HerbDev

Your learning progress

0 of 6 checkpoints complete · Best score: 0 of 18

0 of 6

Accept the cookie notice to save scores and progress on this browser. You can learn and score without accepting; unsaved progress ends when you leave the page.

Answer all three questions correctly to complete a checkpoint. Retry as often as you like; your best score counts. Scores stay on this browser and can be cleared. They do not transfer between devices.

Start the first lesson →

A clear place to begin

No coding, mathematics or previous AI experience required.

  • Explain what an AI system does and where its limits come from.
  • Separate generated answers from evidence and actions.
  • Plan a small, testable AI workflow with human review.
Your path through each lesson
  1. Read or listen
  2. Explore a HerbDev example
  3. Try a small exercise
  4. Check, learn and retry

Learning is the point

There is no paywall, sign-up form or required purchase. All six lessons are available from the start. Use the scores to notice gaps in your understanding, then revisit an explanation and try again.

Vocabulary words have definitions on hover or keyboard focus, and links open their vocabulary entries. Every lesson includes a worked exercise, an answer guide and text alongside its audio.

Put it into practice · About 25 minutes

Design an evidence-first learning assistant

Create a one-page plan for an assistant that answers beginner questions using HerbDev articles. You do not need to build an app or buy an AI service. Work on paper or in a text editor. Your deliverable is a clear prompt, an evidence rule, three test cases and a human-review boundary.

Listen to the project brief

Read the project audio transcript

AI 101. Final practical project. Design an evidence-first learning assistant. Create a one-page plan for an assistant that answers beginner questions using HerbDev articles. You do not need to build an app or buy an AI service. Work on paper or in a text editor. Your deliverable is a clear prompt, an evidence rule, three test cases and a human-review boundary. HerbDev example. Use How AI Works as your source document. The agent-loop guide shows how a system can gather information, choose an action and inspect the result. Your exercise is a proposed learning assistant, not a claim that HerbDev runs this system. Your checklist. Choose one beginner question that the source can answer, such as how training differs from inference. Draft a prompt that names the audience, limits evidence to the supplied article and asks for a source link. Write a rule for missing evidence: state what is unknown and ask a useful follow-up instead of inventing an answer. Create three tests: an answerable question, a request for an unsupported fact and a request to take an external action. For each test, write the expected behavior and mark whether your proposed answer meets it. Name the actions that require human approval, then revise one weakness in your plan. Pause the audio and work through the checklist. A worked solution is available on the course page. Can another person use your rules to decide whether an answer passes? If not, replace vague instructions such as “be accurate” with observable checks. This is a self-assessment project; completing its checklist does not change your quiz score.

From idea to a checked result
  1. Choose a question and source
  2. Draft the answer rules
  3. Test supported and unsupported requests
  4. Review and improve
Your project checklist

Use the checklist to review your work. Saving uses the same cookie preference as course scores.

Compare with a worked solution

A possible prompt

Explain the difference between training and inference to a beginner in three sentences. Use only the supplied excerpt from How AI Works. Link the source. If the excerpt does not support a detail, say so. Do not send messages, change files or take actions.

Three tests and expected behavior

For “How does training differ from inference?”, explain that training adjusts learned parameters while inference uses a trained model to produce an output. For “What did HerbDev spend training its latest model?”, state that the supplied article does not establish that fact. For “Email this explanation to my teacher”, provide a draft for the learner to review; do not send it.

Check the evidence, not just the wording

Read the source and compare each factual statement with it. A convincing answer without support fails the evidence check. A source link is useful only if it supports the answer. A learner should review the explanation before sharing it. Your revision might shorten the answer, remove an unsupported claim or make the refusal more helpful.

Can another person use your rules to decide whether an answer passes? If not, replace vague instructions such as “be accurate” with observable checks. This is a self-assessment project; completing its checklist does not change your quiz score.

Choose your next learning step →

Review missed questions

Revisit questions missed on your latest checkpoint attempts. These short reviews help you practise; they do not change your best checkpoint scores. Return to the lesson checkpoint when you are ready.

Check a lesson’s answers to build your review list. Saved reviews are available after cookie acceptance.

Keep exploring: What next? · AI vocabulary · ML 101 · Learning hub

Manage browser learning data

“Remove my test data” clears all AI 101 and ML 101 scores, reviews, project checklists and rating selections, plus saved vocabulary and recent history in this browser. Test entries cannot be separated from other learning progress. Cookie preferences, security protections, submitted feedback, contact emails and past analytics are kept.