For software developers building with AI

Learn AI you can build with.

Focused lessons that respect your time. See how the ideas connect, then apply them in your own projects.

Shaped by experience at

  • Google
  • Meta
  • Apple

$347 one-time · Lifetime accessOffer valid through October 31, 2026 (US Pacific Time). $647 from November 1.

Try free mini-course ↓

All 28 courses. Every course’s practice skill.
Fresh technical content every month.

Start the free AI Evals mini-course ↓A complete course in 17 minutes.
No email. No account.

Start learning. No sign-up.

A first win, on us.

Free mini-courseComplete course · 16:47

AI Evals:
Proof, Not Guesswork.

Follow a fictional scheduling assistant’s double booking. Catch the failure with code checks, a clear rubric and an eval suite.

The whole course. No email. No account.

Follow the failure. Build the check.16:47 · English captions

01 / Inspect

Check the actual state.

A confident answer can hide a broken schedule.

02 / Evaluate

Choose the right check.

Code for hard rules. Rubrics for judgment.

03 / Improve

Repair. Rerun. Verify.

Catch regressions before the next release.

Inside the mini-course

YOUR MINI-COURSE, IN ACTIONFree companion

Your first eval. Your first fix.

Catch a confident claim with saved-state checks, repair the schedule, and rerun every case. Take the mini-course from watching to doing.

YOUR FIRST MISSION

Find a double booking and a false coverage report in the offline practice cases. Repair the saved schedule, then check what improved and what still needs human review.

You’ll make: FIRST_WIN.md · EVAL_REPORT.md · eval_results.json · RUBRIC.md

Download the free Evals skill ↓

ZIP · 12 KB · Claude Code + Codex

Included with this free mini-course. No account, API key or paid tool required. Runs offline with Python 3.9+.

Install it in 3 steps
  1. Download the ZIP above.
  2. Extract its folder into ~/.codex/skills/ or ~/.claude/skills/.
  3. Start a new agent session and ask it to use vivid-ai-evals-mini-course for your first eval.

You can also run the helper directly from its folder:

python3 scripts/vivid.py firstwin /path/to/project
What the practice does

Original fictional cases, deterministic checks and a human-review rubric. The tool does not call a model or execute your project code. It writes practice reports inside your chosen project’s .vivid/vivid-ai-evals-mini-course/ folder. Prepared replays teach the method; they do not establish production reliability. Files you ask an AI agent to read may go to its model provider.

Read the key ideas

A claim is not proof. A fluent message can say that every station is covered while the saved schedule contains overlapping bookings. Evaluate the state and the trace, not just the assistant’s wording.

Match the grader to the question. Code can check availability, qualifications and consent rules. A clear rubric helps people and model judges assess whether a message explains a gap and offers a safe next action.

Rerun after every repair. Check the cases that improved and the cases that regressed. Separate development cases from held-back checks, and report counts and failure types.

The film uses prepared teaching examples and real code checks. Its model-judge verdicts and reviewer labels are illustrations, not live model measurements. This complete, standalone free mini-course is separate from the paid course catalog.

Sample episode · AI Agent Architecture

Give your agent
the right context.

Your model doesn’t know your docs. See where retrieval fits between a user’s question and the model call.

5:10 Episode 1 of the full course No login

View the full syllabus →

A practical look at context limits, relevant evidence and retrieval.

Read the lesson notes

Training knowledge is not your project’s knowledge. A model’s general training does not include your private repository or internal policies. To answer a question about those documents, your application must supply the relevant information when it makes the model call.

Context is a budget. Instructions, conversation, retrieved material and the response all need room. Token limits vary by model; check the model you actually use. Sending the entire document collection is rarely a useful first design.

Relevance matters as much as capacity. Unrelated facts make the useful evidence harder to isolate. Start by selecting documents that address the question, preserve their source IDs, and define what to do when there is no evidence.

Retrieval is a step, not the answer. Question → retrieve relevant snippets → build context → ask the model → check the answer against its sources.

From a first win to your next build

Put what you learn to work.

Build with 28 focused courses in agents, evaluation, retrieval and more. Your one-time purchase includes the practice skill for each course you own; the full Vault unlocks every paid-course skill. Each skill gives you a concrete first task for your own project. Courses and technical content are updated every month.

$347 one-time · All 28 course skills includedOffer valid through October 31, 2026 (US Pacific Time). $647 from November 1.

Lifetime access · 14-day money-back guarantee

The Concept Galaxy

Short lessons.
A connected understanding.

See how each lesson fits into the bigger picture. Scroll between concepts, follow their connections to related episodes, and see your progress as you learn.

Make the whole learning path yours.

$347 one-time · All 28 courses + practice skillsOffer valid through October 31, 2026 (US Pacific Time). $647 from November 1.

No testimonials. Here's why.

We don't have student quotes, success counts, or revenue figures to show you — so we show you the courses instead. Start exploring AI topics with our open learning resources, then discover more courses in Explore. More first episodes are free with a login. Verify the quality yourself before paying anything. That's the whole trust model, plus a named seller and a 14-day money-back guarantee.

Your milestones, made visible

A look at the finish line.

Preview a course completion certificate, a milestone badge, and a purchase receipt.

Sample AI Vault certificate for fictional learner Alex Morgan completing AI Agent Architecture.

Completion certificate

Your effort, on record.

A preview of your course milestone. Completion reflects the episodes you mark complete; it is not an externally accredited qualification.

Sample lime and ink AI Vault course completion badge with a connected constellation.

Milestone badge

One more world conquered.

A preview of the course completion badge: a small reminder of the concepts you have connected and the progress you have made.

Illustrative purchase receipt labelled sample and not valid for an expense claim; fictional buyer and 79 dollar course subtotal. Illustrative purchase receipt labelled sample and not valid for an expense claim; fictional buyer and 799 rupee full Vault total including applicable tax.

Receipt & reimbursement

Make the case at work.

Planning to use a learning allowance? Check your employer’s policy first. Paddle emails your actual purchase receipt; prices and tax depend on your checkout.

These are samples. They contain fictional learner details. The receipt preview is not a tax invoice and cannot support an expense claim. Use the real document issued by Paddle after payment; reimbursement is subject to your employer’s approval.

The full AI Vault

One purchase.
Your next chapter in AI.

Go from understanding the ideas to building with them. Take the whole collection, connect the concepts, and keep putting what you learn to work.

  • 28 focused coursesAgents, evals, retrieval, tools and more.
  • 28 practical course skillsA concrete first task for your own project.
  • A connected learning pathThe galaxy ties concepts, episodes and progress together.
  • Updated every monthCourses and technical content keep pace with AI.

$347USD · one-time paymentOffer valid through October 31, 2026 (US Pacific Time). $647 from November 1.

Lifetime access. No subscription.
14-day money-back guarantee.

Secure checkout by Paddle. No account needed to buy. Any applicable tax is shown before payment.

See all purchase options →