Practice the work. Own the result.

Build AI systems.Defend your decisions.

Practice the decisions behind reliable AI: what to build, how to test it, and what to do when it fails. Start with Core. Explore specializations that fit your goals.

  • 12 months per product
  • Required lab usage included
  • No automatic renewal
Explore six new paths — US$497 each

One foundation.
An optional next step.

Choose the capability you want to build—not a bigger list of features.

Already have Core? Sign in to see your options

The production foundation

AI Production Systems Core

US$497one-time

12 months

Turn a model response into a bounded AI capability you can evaluate, operate, and defend.

  • Set quality, cost, privacy & safety boundaries
  • Practice evaluation, deployment, observation & repair
  • Work toward an evidence pack & portable source

Optional specialization

AI Agent Path

+US$497one-time

US$994 total with Core

Practice systems that take action—with bounded tool use, human control, and recoverable failure.

  • Define tool contracts & limit agent authority
  • Control state, handoffs & human approval
  • Evaluate trajectories & recover from failures
Explore the Agent curriculum

More ways to build your skills

Six new directions. US$497 each.

Choose the topic that matters to you. Each path is a separate purchase; you do not need to buy them all or buy Core first.

Each path has existing labs to explore, with a broader curriculum still in development. Review the current lab list before choosing. Your 12-month term starts at payment; future labs have no promised release date.

AI-Native Software EngineeringVibe Coding

Explore the building blocks behind reusable AI coding assistance. The current starting set focuses on skill packages: what they contain, when to use them, and whether to trust them.

3 current labs

Explore the current curriculum: AI-Native Software Engineering

US$497one-time · 12 months

AI Security & Red Teaming

Practise spotting unsafe authority and checking safeguards in AI systems. Start with bounded decisions about tools, skills and recovery; add optional incident-leadership practice when useful.

6 current labs + 3 optional

Explore the current curriculum: AI Security & Red Teaming

US$497one-time · 12 months

AI Evaluation, Testing & Reliability

Learn to question an impressive score and build more useful tests. Practise finding leakage, checking evaluators and matching a decision threshold to the cost of being wrong.

15 current labs

Explore the current curriculum: AI Evaluation, Testing & Reliability

US$497one-time · 12 months

AI Product Engineering

Practise decisions that make an AI feature more useful and dependable: finding relevant information, handling memory, controlling failures, and balancing serving cost with capacity.

16 current labs + 11 optional

Explore the current curriculum: AI Product Engineering

US$497one-time · 12 months

AI Privacy Engineering

Follow data through an AI system and practise reducing unnecessary exposure. Work through where processing happens, who may retrieve information, and what should be removed or forgotten.

7 current labs

Explore the current curriculum: AI Privacy Engineering

US$497one-time · 12 months

Real-Time Voice & Conversational AI Engineering

Explore decisions behind spoken and real-time AI interactions. The current labs cover modalities, conversation timing, handoff failures, and safe handling of tool actions.

4 current labs

Explore the current curriculum: Real-Time Voice & Conversational AI Engineering

US$497one-time · 12 months

Your selection

AI Product Engineering

One learner · 12 months per selected product

US$497one-time, before discounts
Have a coupon?

Your discount and final total will appear on Stripe before you confirm.

Try the method before deciding

Enable JavaScript to continue to Stripe. Prices and product details remain available. No payment has been started. Get help purchasing.

Stripe shows your discount and final payable total before you pay. It handles billing details; learner setup comes after payment. Your card issuer may charge currency-conversion fees.

Core is useful on its own. When a system can take actions, weaknesses in evaluation, authorization and recovery have additional consequences. Core develops the shared controls; Agent applies and extends them. Valid Core purchase history is required, not a perpetual Core renewal.

What is implemented today?

Interactive laboratories and private portable exports are available to authorized accounts. Integrated production missions and full credential issuance are not yet released. The evidence previews below are labeled illustrations, not completed missions or graduate results. Inspect the current product scope.

See exactly what Agent adds
Core foundation and the additional scope of Agent
The decisionCore foundationAgent adds
What should I build?A bounded AI capability with explicit requirements and limits.Decide whether autonomous action is justified at all.
What may it do?Authorization, retrieval security, privacy and input boundaries.Tool contracts, limited authority, approval and escalation.
How do I evaluate it?Representative cases, evidence quality and release criteria.Multi-step trajectories, tool choices and consequential actions.
What happens over time?Observability, latency, cost and operating limits.Durable state, handoffs and uncertain side effects.
How does it recover?Containment, diagnosis, repair and regression evidence.Action containment, safe retry and controlled restart.
What is the evidence target?A system contract, evaluations, deployment and repair records, portable source.An agent contract and trajectory evidence, plus deployment and repair records.

These are curriculum and evidence targets. Integrated production missions and complete credential issuance are not yet available. Explore the pathways.

No paid lab top-ups

Required model, API, simulation, evaluation and managed deployment usage is included during active access. No learner credit balance.

Keep pace during your term

Updates, corrections, supported-model changes and major revisions are included. New paid paths are separate.

A clear purchase policy

14-day satisfaction guarantee, in addition to statutory rights. One-time purchase, never an automatic subscription.

Read the refund policy

Try one decision

The demo works.
Would you release it?

A good response is only the start. Practice spotting what the evidence does—and doesn’t—establish.

Make a release call. Find the failure. Repair the cause. Then explain what your check actually proves.

A local illustration with synthetic data, not a released mission, learner result or credential assessment. No AI calls or account required.

Try the actual free learning experience
Support assistant / release checkEvidence incomplete

Good answers. Enough evidence?

The assistant answers the sample questions. A deletion request has been processed. Here is what the checks establish.

Answers cite the sample sources
Checked
Unauthorized access is rejected
Checked
Deleted content is unretrievable
Not checked

One deletion. Three places to check.

A synthetic document was removed from the source. Check whether its retrievable copies were removed too.

Source storeNot checked
Search indexNot checked
Answer cacheNot checked

Repair the path.
Recheck the result.

First inspect the deletion path. A repair should respond to observed evidence, not a guessed cause.

  1. Contain — block retrieval and cached answers for the affected document.
  2. Repair — purge indexed and cached copies, not just the source.
  3. Verify — repeat the deletion check across all three stores before reopening the route.
Synthetic data · no assessment credit

Enable JavaScript for this local exercise. The missing check is deletion across every retrievable copy; passing answer checks alone is not release evidence.

The intended learning loopDecide Build & test Diagnose & repair Defend the result

Work you can inspect.
Not just a course you watched.

The target is a working capability plus the evidence behind it. Explore the anatomy of the intended deliverables.

production-evidence / outlineILLUSTRATIVE ANATOMY

The decision, with its evidence.

A system contract and release record that makes scope and remaining unknowns visible.

Scope
A bounded support assistant using approved sources. No consequential actions.
Evidence
Representative evaluations, source traceability, authorization and adverse-case checks.
Release call
Hold until required privacy and deletion checks have supporting evidence.
Limits
A passed fixture check is not proof of broad release readiness.
Ownership
The learner explains the controls, observes behavior and defends the decision.

Staff-authored contract outline, not an actual learner evaluation or completed mission.

deployment-record / outlineILLUSTRATIVE ANATOMY

What ran. What was observed.

A record ties behavior to a specific endpoint and version—not an assumption about a screenshot.

Endpoint
A learner-owned endpoint and its provider boundary would be identified here.
Version
Manifest and package identifiers identify the submitted version.
Checks
Observed behavior, verifier conditions and failed checks stay inspectable.
Limits
Observed behavior and endpoint key control do not independently attest source or complete a mission.
Teardown
A removal or shutdown record closes the operating scope.

No endpoint, hash, signed receipt or deployment result has been fabricated.

incident-repair / illustrative recordILLUSTRATIVE ANATOMY

Make the repair explainable.

Record impact, containment, causal diagnosis, correction and the evidence needed to resume.

Observed
Deleted source content remained retrievable in the derived fixture stores.
Contained
The example blocks the affected retrieval route while repairing it.
Cause
Deletion did not propagate to the search index and answer cache.
Repair
Purge every tracked copy and repeat the deletion check.
Boundary
This check does not establish future re-ingestion safety or full operating readiness.

Anatomy of the local example above, not a real incident or a paid-platform assessment result.

portable-source / expected structureILLUSTRATIVE ANATOMY

A package you can understand.

Source plus the context needed to inspect, test and operate it—not a mystery export.

Source
Application source, dependency lockfiles and attribution.
Setup
Configuration schema, required migrations and documented environment boundaries.
Verification
Tests, disclosable fixtures and a deployment manifest.
Operations
Runbook, known limits, shutdown and recovery instructions.
After access
Already-created exports remain under the policies; new exports and funded verification need active access.

Illustrative anatomy. This preview does not contain proprietary course source or a fabricated working production package.

These are staff-authored outlines, not an approved end-to-end artifact or learner success story. Read the actual artifact contracts.

Private until you deliberately publish. Public sharing is a separate choice with privacy, secret, rights and attribution checks. Access expiry does not force publication.

New to AI?
Start here.

Built for people with no coding or AI experience. You do not need to learn programming or take another AI course first.

No technical background needed

Using AI, understanding unfamiliar terms and checking results are things to learn here—not an entrance requirement.

A laptop or desktop

Start with a current browser and internet connection. Reading and compatible simulations also work on mobile.

Setup when you reach that step

An email inbox is needed for your account. Learner-owned deployment later uses a free Cloudflare account and local tools. You do not need Git, a terminal or a cloud account to try a lab.

About the time commitment
Reliable completion-time estimates are not yet available across experience levels. Twelve months is the access period—not a promise about study time.

Choose a starting point

Pick what interests you. This is not a skills test or eligibility check. Your answer stays on this page and is not stored or sent.

What would you like to learn?

Core is the starting point, including if you have never coded or used AI. Agent builds on Core and can be added later. You can also try a free lab before deciding.

See how to get started

Learn to use AI.
Build your own judgment.

You can also explore independently with documentation and an AI assistant. These labs are for people who want practice, feedback and a path toward skills they can use.

The aim is to learn how to use AI, check its answers, spot mistakes and improve the result—not to arrive knowing how. This is a learning product, not a custom development service. See how the method works.

Twelve months. No subscription.
No surprise overlap.

Each product has its own access term. Choose when to add Agent based on your work—not pressure to buy everything today.

Initial-purchase illustration only. Exploring this timeline does not change your selection or estimate your study pace. Early renewal extends from the existing expiry; a new or post-expiry term starts at payment.

Core starts with its successful payment.

Months from the first payment

Independent product access periodsCore lasts from month zero to twelve. Agent may be purchased separately; both products bought together run concurrently.06121824CoreAgent12 monthsAdd only when you need it

Core: 12 months from successful payment. Agent is separate. If you buy both together, both terms start at the same payment and run concurrently—not consecutively. A later Agent purchase does not renew Core.

When an access term ends

That product’s full labs close. Account records, invoices, valid purchase history, retained artifacts, already-created exports and historical receipts remain, subject to account and privacy policies. New exports and funded verification need current access.

When you operate independently

Required completion usage is included. Keeping your system running beyond the included verification scope may create your own provider or Cloudflare costs. Renewal is optional at the then-current price; new paid paths are separate.

A few things
worth knowing.

Clear scope before a commitment. Still unsure about fit, access or a purchase?

Ask a specific question

Human support
Target: first response within one business day. This is not a guaranteed resolution time or contractual SLA.

What can I use today?

Interactive laboratories, saved work and evaluation, account/evidence controls, private portable exports and observed-behavior verification are implemented for authorized accounts. Integrated production missions, full completion and credential issuance are not yet available; laboratory results and exports do not substitute for those gates.

The prices and purchase interface are shown so you can inspect the actual offer. Checkout remains subject to the current payment, availability and eligibility checks. Read the current product scope or try the free experience.

Do I need Agent, or is Core enough?

Core is a standalone foundation for building and operating a bounded AI capability. Agent adds model-directed actions: tools, authority, state, approval, trajectories and recovery. Add it when those are part of your goal, not merely because it exists.

Valid Core purchase history is required for Agent. A qualifying existing purchaser does not have to renew Core just to add Agent; an expired access term does not erase valid purchase history. After full Core access expires, an active Agent term includes only its declared Core prerequisite reference/refresh materials—not the full Core curriculum.

Will I need extra API credits or a paid cloud plan?

No paid external model/API/cloud credits are required to complete the supported work. Required model, API, simulation, evaluation and managed deployment usage is included during active access. No learner credit balance or paid top-up.

The portable workflow requires a free learner-owned Cloudflare account. Optional independent operation beyond the included scope can incur your own costs.

What help and assessment retries are included?

Learning activities provide feedback against their evidence targets. Support covers accounts, billing, access, platform problems, the official environment, included execution, rubric interpretation, accessibility, privacy and security. Platform and scoring defects can be escalated to a human.

The defined active-term assessment policy includes three full submissions, then targeted remediation to unlock a later submission without a retake fee. Formative retries have protective limits. Full credential issuance is not yet released.

Routine private artifact review, custom development, arbitrary external-code debugging and operating a post-course system are not included. Support scope and escalation.

Is there a certificate, and what would it prove?

The defined credentials assess demonstrated performance—not attendance or purchase. All module, mission, deployment, incident/repair, transfer and evidence-integrity gates must pass. Full completion and issuance are not yet available.

An issued record would describe assessed versions and conditions, including permitted AI assistance. It is not an employment guarantee, checked government identity, accreditation or regulatory approval. Inspect the credential definitions.

Can my employer pay while I take the labs?

Yes. Stripe collects the billing details; after confirmed payment you explicitly choose and confirm the learner email. The receipt email does not silently become the learner. Each assigned seat belongs to one person and is non-transferable.

Stripe handles supported tax IDs, billing details and the available payment methods. An optional PO reference can be recorded after payment; it does not create credit terms or purchase-order approval. Business billing does not include multi-seat administration or transferable seats. Support can investigate genuine billing or account-linking errors.

How do payment, refunds and location eligibility work?

Prices are in US dollars. Stripe shows your discount and final payable total before payment. Your card issuer may charge currency-conversion fees.

Access requires successful payment and eligibility verification. An ineligible paid transaction follows the protected refund process; payment alone does not grant access. Each purchase includes a 14-day satisfaction guarantee in addition to statutory rights. Read the refund policy and purchase terms.

Does buying both give me two consecutive years?

No. An initial Core + Agent purchase starts two independent 12-month terms at the same payment. They run concurrently. Adding Agent later starts its own term and never renews Core.

An eligible early renewal extends from that product’s current expiry. New or post-expiry terms start at payment. Renewals are deliberate, optional and priced at the then-current published price. Future prices are not locked.

What happens after I select Continue to Stripe?

We create or safely resume a Stripe-hosted checkout for your selected products. Stripe handles payment and billing. After payment, return here to confirm the learner email and finish account setup. A setup link is also sent to the receipt email; the nominated learner receives their separate secure account link.

If confirmation is pending, do not pay again. Use the purchase setup link to check progress or contact support. A declined payment or service error does not erase your selection. Returning from Stripe does not by itself prove that no charge occurred.

Choose what you’ll
build next.

Start with the scope that fits. Your selection is preserved, and billing stays on Stripe.

Review your selectionTry a free lab first