Context Architecture for Business Analysts and Product Owners

Illia Shapoval

AI context systems for BAs & POs

Your AI Writes Empty Specs. The Context Layer Is Why — and How You Fix It

This workshop is about the context layer — the part that decides whether AI output is usable or just fluent.

Skip it, and you get specs that are polished on the surface and empty underneath: generic phrasing, invented fields, rules your product never had.

Overcorrect — "just give it all the context" — and it's worse. Do you even have all the context in one place? Would you want every Confluence page, every PRD revision, every deprecated business rule shaping the answer?

The usual fixes all carry a bill:

  • RAG pipelines — powerful, but now you build and babysit infrastructure.

  • Mega-prompts — thorough, but every answer comes out diluted.

  • Docs dumps — comprehensive, but light on the specifics that matter.

  • Letting AI manage its own context — convenient, right up until it takes the wheel.

This workshop gives you a Context Engineering system that costs the least to start and grows with your product.

You leave with a working starter context base, your own agents.md, your SKILL.md files, one real feature specced end to end — and a system you shape as you go, not a framework you serve.

I spent years sharpening this. Now it saves me days.

What you’ll learn

Engineer a compact context system that turns a four-line brief into a spec draft your team trusts — on your product, in your template.

  • Decompose any requirement into the context blocks an AI can address — users, data, workflows, processes, domain, business rules

  • Separate context-dependent quality (valuable, testable, relevant) from prompt-dependent quality (unambiguous, readable)

  • Diagnose why a "complete-looking" spec is actually hollow

  • Construct the addressable folder structure your AI reads from

  • Teach the AI to maintain the content itself, so they never go stale.

  • Compose a `SKILL.md` and your own `agent.md` that turn the context base into a working system

  • Lock the AI to attributes it can actually see — no invented fields, no hallucinated rules

  • Promote new business rules, user groups, and entities from each ticket back into the base — without bloating it

  • You'll leave able to tune and rebuild this system for any product you own

Workshop agenda

  • ▸ Start 14:00 Warsaw / 8 AM New York

    Join 5 minutes before to say "Hi" and set up for the session.

  • Welcome & use-case round (~15 min)

    Share the use case you're bringing! That will be the foundation for the whole session.

  • Setup the environment (15-20 min)

    Tools + the LLM you already use, wired and ready. → You leave with: a working setup — no "install later," you build today.

  • Context Engineering basics (~20 min)

    Rules for context management applied to requirements. → You leave with a solid understanding of why this set up works

  • Requirements qualities (~25 min)

    Align on what makes a requirement good, then dissect a real one together. → You leave with: the quality split — what a better prompt fixes vs. what only context can.

  • Build-along: wiring context system (~45 min)

    Build the addressable base + the extraction skill, live. → You leave with: your own agents.md + extraction SKILL.md, running on your product.

  • ▸ Break — 16:00–16:30 Warsaw / 10:00–10:30 AM New York

    30 min break

  • Build-along: your first requirement draft (~30 min)

    Turn a four-line brief into a spec draft the model grounds in your base. → You leave with: a draft skill + template that drafts specs from your context

  • Build-along: the context-population flywheel (~30 min)

    Promote new rules, roles, and entities from the draft back into the base. → You leave with: the flywheel skill that keeps your context alive without bloating it.

  • Case clinic & Q&A (~30 min)

    Bring the example that didn't fit — we work it live. → You leave with: your stuck case unstuck, and the pattern to rebuild this for any product you own.

Learn directly from Illia

Illia Shapoval

Illia Shapoval

AI-assisted requirements engineering | 15 yrs PM in Banking, Aviation, MedTech

Lufthansa Systems
Backbase
Luxoft
UKRSIBBANK BNP Paribas Group
See all products from Illia

Who this workshop is for

  • You're a Business Analyst or Requirements Engineer who owns product documentation, and you want a system for AI-assisted requirements work

  • You're a Product Manager or a PO who needs AI as a specification sidekick, not a chatty assistant you re-brief from scratch on every task.

  • You've tried "shove all the context in" — and watched the output get more generic, not less. Ready for a tested framework that fixes it.

What's included

Illia Shapoval

Live sessions

Learn directly from Illia Shapoval in a real-time, interactive format.

Lifetime access

Go back to course content and recordings whenever you need to.

Community of peers

Stay accountable and share insights with like-minded professionals.

Certificate of completion

Share your new skills with your employer or on LinkedIn.

Maven Guarantee

Your purchase is backed by the Maven Guarantee.

Frequently asked questions

Maven for Teams

Reimbursement

Get your company to pay

Everything L&D needs: email template, receipts, and certificate of completion.

Get reimbursed

Team discount

Learn with your teammates

Save 20%+ when 2 or more teammates enroll in the same cohort.

Save 20%+ with a team

Private cohort

Run a cohort for your org

A dedicated cohort with a custom schedule and curriculum, tailored to your team.

Book a private cohort

$400

USD

Aug 22
·

8am–1pm EDT

Enroll