Skip to content
reKoncepcjaRethink. Build. Create.

Extended course · Advanced

AI Product Engineering Advanced

From first customers to scale: growth and retention, unit economics, AI costs, security and an architecture ready to grow. 30 weeks in total.

€13,900 · PLN 60,750 · 7 months · 900 h of learning

For companies: €11,301 net (PLN 49,390) + 23% VAT

Online · one-to-one · taught in Polish or English · starts on the second Monday of every month.

Apply for the next start →Weekly scope ↓

Applying takes 2 minutes. First a short call and diagnostic, then the agreement — there’s no commitment when you apply.

What you will learn

  • Weeks 1–20: the whole full-course scope, with the defense in week 20
  • Review the architecture after launch and ship a change with contract tests (week 21)
  • Analyse cohorts and drop-off, improve onboarding and measure activation (week 22)
  • Test a second acquisition channel; measure the funnel, CAC, LTV/CAC and AI cost per customer (weeks 23–24)
  • Compare models on quality, latency and cost; catch AI regressions and design fallback (week 25)
  • Build a threat model, run security and load tests, rehearse incidents and rollback (weeks 26–28)
  • Run a growth experiment and defend your development plan at the final review (weeks 29–30)

Problems you will solve

  • What do you do when you have customers but AI costs grow faster than revenue?You compare models on quality, latency and cost, measure scaling costs and ship a validated optimisation.
  • How do you convince a B2B customer that your AI system is secure and predictable?You show a threat model, security and load test results, AI evaluations and a recovery plan — with the remaining risks stated openly.
  • How do you change the architecture of a live product without breaking it?Contract tests, architecture decision records and a rehearsed rollback before the change reaches users.
  • Customers arrive but leave after a month — what do you do?You analyse cohorts and drop-off points, improve onboarding, test a second acquisition channel and measure the effect with a growth experiment.

Tools and technologies

Growth

  • Activation and retention
  • Cohorts and funnel
  • LTV/CAC
  • Growth experiments
  • PostHog

AI quality

  • Evaluations · Promptfoo
  • Model comparison: quality, latency, cost
  • Fallback and human escalation

Scale and security

  • Threat modelling
  • OWASP LLM Top 10
  • k6
  • OpenTelemetry
  • Sentry
  • Backup and rollback

Plus

  • The full-course stack

How it differs from the full course

What you get on top

  • 4 growth weeks: activation and retention, a second acquisition channel, LTV/CAC and a growth experiment.
  • Extended AI evaluation: model comparison, regressions, fallback and human escalation.
  • Threat model, security and load tests, disaster recovery.
  • 450 h with your instructors instead of 300: 90 h of one-to-one sessions, 180 h of pair coding and 180 h of mentorship.

What stays the same

  • Weeks 1–20: the whole full-course scope, with the defense in week 20.
  • A 30 h weekly rhythm: 3 h of one-to-one sessions, 6 h of pair coding and 6 h of mentorship.
  • Instructor chat at every stage and access to materials with no time limit.
  • A certificate of completion after the final review.

Hours and weekly rhythm

900 h over 30 weeks — about 30 h a week (roughly 6 h each weekday). One-to-one sessions, pair coding on your product and mentorship make up half the week; the rest is recordings, materials, assignments and your own work on the project.

Interactive one-to-one sessions
90 h
~3 h/week · live with your instructor
Pair coding on your product
180 h
~6 h/week · we write the code for your problem together and explain every decision
Mentorship and reviews
180 h
~6 h/week · code, product, decisions
Lesson recordings
90 h
~3 h/week · watch at your own pace
Materials and reading
90 h
~3 h/week · docs and examples
Practical assignments
105 h
~3.5 h/week · assessed against criteria
Project work
165 h
~5.5 h/week · from idea to launch

Instructor chat and materialsAt every stage you have access to a chat with your instructors and to all course materials — recordings, documentation and examples. You don't wait for the next session when you get stuck — we answer in the chat within 1 working day. The materials stay with you after the course, with no time limit.

Stretch tasksFor the ambitious: optional stretch tasks and extensions within the course. They never affect passing — take on as much as fits without overloading yourself.

Prerequisites

No programming experience required: Advanced includes the whole full course (weeks 1–20), so you can start from zero — but it is 7 months of intensive work at 30 h a week. If you already code, you move through the basics faster and gain more time for architecture and scaling. Entry diagnostic.

You need a suitable laptop and a separate budget for AI tools, APIs and hosting — about USD 20–50 a month. Placement is not automatic.

Intended outcomes

  • A product developed from growth and retention data
  • Unit economics and AI costs under control
  • Architecture, security and reliability ready for scale

Program areas / modules

  • AI-Powered Learning & Critical Thinking
  • Problem Discovery & Human Understanding
  • AI-Assisted Development
  • Software Engineering Foundations
  • Full-Stack Product Development
  • AI Engineering
  • AI Agents & Automation
  • Product Design & UX
  • Business, Marketing & Product Strategy
  • Infrastructure & Production Engineering
  • Security, Quality & Responsible AI
  • Product Launch & Continuous Improvement
  • Growth: activation, retention and acquisition
  • Architecture and post-launch development
  • Extended AI quality and security
  • Scaling and reliability

Weekly stage outline

  1. Week 1

    Learn With AI, Think Without It

    Set up an AI-assisted learning system, choose a problem space, and ship a first public artifact.

  2. Week 2

    Find a Problem Worth Solving

    Turn a vague idea into an evidence-based problem statement through real conversations.

  3. Week 3

    Your First Working Prototype

    Use spec-driven, AI-assisted development to build a working prototype and put it in front of users.

  4. Week 4

    Understand the Code You Ship

    Build the fundamentals needed to read, reason about and safely change AI-generated code.

  5. Week 5

    Data That Persists

    Design a relational data model from user needs and persist product data safely.

  6. Week 6

    Users, Accounts and Boundaries

    Build a full-stack architecture with authentication, authorisation and a clear server/client boundary.

  7. Week 7

    Design for Humans

    Improve the product with UX principles and evidence from usability testing.

  8. Week 8

    Refactor and Prove the Critical Flow

    Add an end-to-end regression test, simplify the architecture and check the available error states. Deliverable: version v0.5, tests and an architecture decision record.

  9. Week 9

    LLM Foundations and the AI Value Case

    Justify an AI use case and integrate LLM APIs with validated structured outputs.

  10. Week 10

    Mid-Program Review, Knowledge and Retrieval

    Explain your architecture and make a change without AI during the review. Then build RAG with citations and a 30-question set to assess quality.

  11. Week 11

    Evaluate, Compare and Control AI Costs

    Compare two configurations on an independent question set, including unanswerable questions. Add cost limits, a timeout and a safe fallback; present quality, latency and cost.

  12. Week 12

    AI Agents and Tool Use

    Design an agent with explicit tools, permissions, stop conditions and human checkpoints.

  13. Week 13

    Automation and Integrations

    Connect the product to the outside world with reliable background jobs and integrations.

  14. Week 14

    Quality, Security and Responsible AI

    Systematically test, secure and evaluate the product — including its AI components.

  15. Week 15

    Production Engineering

    Deploy and operate the product with containers, CI/CD, monitoring and cost control.

  16. Week 16

    Operational Readiness and Recovery

    Load-test, restore a database backup, rehearse rollback and data export and deletion. Deliverable: a readiness report, a measured recovery time and an operations runbook.

  17. Week 17

    Business Model and Go-to-Market

    Build positioning, pricing and an acquisition plan grounded in evidence from your users.

  18. Week 18

    Launch, Measure, Improve

    Launch to real users, learn from data and feedback, and ship a measured improvement.

  19. Week 19

    Validate the Next Iteration and Prepare Handover

    Go back to users after launch, ship a second improvement and measure its effect. Have someone else follow your setup guide and rehearse the defense without AI, stating the limits of a small sample.

  20. Week 20

    Defend, Document, Continue

    Present and defend your product and architecture, and leave with a 12-month learning roadmap.

  21. Week 21

    Architecture after launch

    Review system boundaries and architecture decisions; ship a selected change with contract tests and documented trade-offs.

  22. Week 22

    Activation and retention

    Analyse cohorts and where users drop off; improve onboarding and measure the effect on activation.

  23. Week 23

    A second acquisition channel

    Launch and test a second acquisition channel; measure the funnel and customer acquisition cost (CAC).

  24. Week 24

    Unit economics at scale

    Calculate LTV/CAC and AI cost per customer; test pricing tiers and the plan at which the product makes money.

  25. Week 25

    Extended AI evaluation

    Expand the evaluation set and compare models on quality, latency and cost; check regressions, fallback and human escalation.

  26. Week 26

    Threat modelling and security testing

    Review permissions and data flows, test safeguards and document remaining risks without claiming certification.

  27. Week 27

    Load and scaling costs

    Measure limits, bottlenecks and costs; validate one optimisation.

  28. Week 28

    Reliability and recovery

    Practise monitoring, incident response, data recovery and rollback.

  29. Week 29

    Growth experiment and development plan

    Run a growth experiment, measure its effect on activation or retention and prepare a 6-month development plan.

  30. Week 30

    Advanced final review

    Present growth metrics and unit economics, evidence of AI quality, security and reliability, and the development plan; defend architecture trade-offs.

Final review and certificate

Weeks 1–20 are the full-course scope with the defense in week 20; weeks 21–30 develop the product after launch. In week 30 present growth metrics and unit economics, a growth experiment, architecture decisions, AI evaluations, security and load tests, monitoring and known limitations.

You receive a Certificate of Completion after passing the course's final review. It lists your hours, assessed competencies and project title.

Compare the three courses

The same weekly rhythm and the same support — what differs is the scope and what you finish with. You can start any course from zero.

Basic course · Essentials

AI Product Engineering Essentials

€4,450/ PLN 19,450

2 months · 240 h

3 h one-to-one, 6 h pair coding and 6 h mentorship each week

Who it's for
You want to check quickly whether an idea has a market before investing in building it.
You finish with
An AI prototype, a landing page and demand evidence — or proof the idea needs to change.
Product and sales
Customer interviews, value proposition, an offer test on a landing page.
Engineering and AI
A one-scenario prototype: interface, model API, basic response checks.
How it ends
Demonstration and final review in week 8.

Moving up: within 6 months of finishing Essentials you can join the full course and pay only the difference — €4,450 / PLN 19,450.

Apply →Program

Professional education · new specialism

AI Product Engineering

€8,900/ PLN 38,900

5.5 months · 600 h

3 h one-to-one, 6 h pair coding and 6 h mentorship each week

Who it's for
You want a new specialism and the whole route: from problem to sales.
You finish with
A deployed AI product with first users, pricing, positioning and a sales plan.
Product and sales
Validation, positioning, pricing, unit economics, an acquisition channel, activation.
Engineering and AI
A full application: accounts, database, RAG, tests, CI/CD, monitoring, payments.
How it ends
Review in week 10, launch in week 18, defense in week 20.

Moving up: within 6 months of your defense you can add Advanced weeks 21–30 for the price difference — €5,000 / PLN 21,850.

Apply →Program

Extended course · Advanced

AI Product Engineering Advanced

€13,900/ PLN 60,750

7 months · 900 h

3 h one-to-one, 6 h pair coding and 6 h mentorship each week

Who it's for
You want the full program, then to grow the product after launch: growth, costs and scale.
You finish with
Everything in the full course, plus growth metrics, unit economics and evidence of quality, security and reliability.
Product and sales
Plus: retention and cohorts, a second acquisition channel, LTV/CAC, a growth experiment.
Engineering and AI
Plus: model comparison, AI regressions, threat model, security and load tests, disaster recovery.
How it ends
Defense in week 20 and the Advanced final review in week 30.

The Twój StartUp 10% discount applies only to the full course: €8,010 (PLN 35,010) after eligibility is confirmed. You receive the certificate after passing your course's final review. Terms →

A little clarity

Good questions.
Honest answers.

Choosing a course is a real commitment. Here are a few things worth knowing first.

All frequently asked questions
Which course should I choose?

The basic course (2 months) if you want to test an idea fast: customer conversations, an AI prototype and a demand test. The full course (5.5 months) if you want the whole route from a problem through a product to first sales. The extended course (7 months) if you want to go further: growth, AI costs, security and scale. You can also start with the basic course and move up later, paying only the price difference. You don't have to decide alone — we'll match the course on a call before you enrol.

Do I need to know how to code?

No. You can start any of the three courses from zero — you write code with an AI assistant, and we teach you to read, check and explain it. We set the pace in the entry diagnostic: starting from zero, more time goes to the basics; if you already code, you move on faster to architecture and AI.

How much time does it take?

About 30 hours a week — roughly 6 hours each weekday. The full course is 20 programme weeks in 5.5 months — the 4 spare weeks cover holidays, illness, rescheduled sessions and support after launch. Every week includes 3 h of one-to-one sessions, 6 h of pair coding on your product and 6 h of mentorship; the rest is recordings, materials, assignments and work on your own product. Optional stretch tasks are there for the ambitious — they never affect passing.

How is this different from a bootcamp or an online course?

You don't build a tutorial project. You pick a real problem, test it with people and build your own product — learning each technology when your product needs it. Every week you work one-to-one with a practitioner, and you're assessed on your code, demos and a defense, not quizzes.

When and where are the sessions?

Online, at times agreed with you (CET/CEST): every week 3 h of one-to-one sessions, 6 h of pair coding and 6 h of mentorship — live and as code and product reviews. Between sessions you have an instructor chat and access to the materials. In-person sessions are only for team training.

What language is the program in?

Polish or English — you choose when you enrol.

Before enrolment

Tuition covers one-to-one teaching, pair coding, mentorship, reviews, the certificate and access to the materials with no time limit. AI tool subscriptions, API usage and hosting for your product are paid separately — about USD 20–50 a month.

Enrol →Terms

Enrolment

Enrol on the course

How enrolment works

  1. Send the application form
  2. A short call and entry diagnostic
  3. Choose the course — basic, full or extended — and sign the agreement

Advice before enrolling

On the call we learn your goal and experience — including if you are starting from zero — and match the course and pace. Classes are taught in Polish or English, mainly online.

Twój StartUp discount

Confirmed beneficiaries receive 10% off the full course: €8,900 → €8,010 (PLN 38,900 → PLN 35,010). Status is confirmed before the agreement.

Apply online

On the application page, in a few minutes:

  • choose a program and start date (with the end date),
  • see the full training offer: hours, format, language, gross price and certificate,
  • send your application — also if a company pays or you're applying for co-financing.
Go to the application →