Kirill Dobrinov

Product Management

Broad coverage

Product judgment centered on proving value before scale, cutting MVPs to the testable core, preserving user control, and matching architecture to real operating constraints.

In RussianMVP scopeExperiment and pilot designDelivery architectureProduct UX
Built from
47 approved decisions
Sources
documents · AI chat history
Updated
August 27, 2026
Coverage
Many approved decisions across different kinds of work — stronger pattern coverage.
Language
Criteria, stop rules, questions and precedents are published in Russian — the expert's own words, untranslated. Everything around them is English.
Privacy
No source quotes ever publish
Connect this expertPaste into Claude, Cursor, Gemini, or ChatGPT · works now, no key
https://avva.chat/mcp/product-management-kirill-dobrinov

Step-by-step setup for your client ↓ · a free key returns the complete published model.

Calls Kirill Dobrinov actually made

2 of 47 decisions in this model, in their own words. This page prints them in published order — it has no way to know your situation. Your agent receives them ordered against it.

  1. Вместо эксперимента используют UX-тесты, комитеты или постфактум-анализ.

    Не считать их заменой A/B.

    Они не отвечают надежно о влиянии на метрики; постфактум часто ошибочен.

  2. Полная платформа включает планирование, проведение и анализ.

    Ограничить MVP техническим проведением.

    Планирование и анализ можно закрыть экспертизой и сторонними инструментами; проведение требует имплементации и ценнее.

Put Kirill Dobrinov in your agent

Two ways in, both through the connector settings of the AI you already use. One is for asking on purpose. The other lets your agent ask on its own. Avva writes no verdict. Your agent reads Kirill Dobrinov’s material and answers you.

What this expert weighs first

Сначала доказать эффект, потом масштабироватьMUST WEIGH
Сужать MVP до проверяемого ядраMUST WEIGH
Не отдавать контроль без продуктовой необходимостиMUST WEIGH
Интерфейс строить под реального пользователяALSO WEIGH
Ядро продукта — механизм поведения и ролейALSO WEIGH
Монетизация следует реальному потоку ценностиALSO WEIGH
Критические действия должны быть проверяемымиTIE-BREAKER
Архитектура следует стадии, каналу роста и контуру поставкиTIE-BREAKER

All 8 are listed here. What each one looks for, plus stop rules and context switches, arrives when your agent asks. Without a key that is a smaller slice, picked for your situation. A free key returns the complete published model.

What you can ask them

  • Check this before I commitA full pass over a plan or a draft
  • Which of these two?A call between options, their stop rules checked first
  • Anything here they would reject?A quick scan against their hard lines
  • What should I settle first?The questions they ask before choosing an approach
  • Is this even their field?Where their judgment applies, and where it stops

Each returns a protocol to follow, not a finished answer. Where the model disagrees with generic best practice, the model wins.

You remember to ask

One URL, no key

Paste it as a custom connector. It works now and returns a smaller slice, picked for your situation.

https://avva.chat/mcp/product-management-kirill-dobrinov

You have to remember to ask your agent to use it.

Your AI remembers

Key, plus a standing instruction

A free key returns the complete published model. A line in CLAUDE.md, AGENTS.md or GEMINI.md makes your agent consult Kirill Dobrinov without being asked.

Finish setup ↓

Catches the decisions you would not have thought to ask about.

Connect Kirill Dobrinov to your agent

The connector works now, with no key. A free key is optional, and it returns the complete published model. The standing note is what keeps Kirill Dobrinov getting asked.

  1. Add the connector

    Pick where your agent runs, then paste the line below. It connects without a key. A free key in the next step returns the complete published model.

    https://avva.chat/mcp/product-management-kirill-dobrinov

    Settings → Connectors → Add custom connector. Works now without a key. Get a free key and this snippet updates to include it — copy it again and reconnect for the complete published model.

  2. Optional — free key for the complete published model

    Your agent then receives every decision, criterion, and stop rule Kirill Dobrinov published, not a selection from them. The key appears once, in this tab only. Anyone who has it shares your daily limit.

    One work email so we know who is using the beta. It is stored separately from the key — never joined to it, or to anything your agent asks. No account, no card.

  3. Make it standing

    This is the point of the product. Paste it once into CLAUDE.md — or wherever this client keeps project instructions. Your agent then works under Kirill Dobrinov’s rules the whole way: it asks their questions before locking an approach, gates drafts on their stop rules, and reviews against their bar before anything ships. Not a one-off second opinion.

    # CLAUDE.md — standing advisor (Avva: Kirill Dobrinov) For product Management work: - Early in a task, call `expert_questions` before locking an approach. - Use `red_flag_check` as a cheap gate on drafts/diffs. - Before finalizing a significant decision, call `review` with context + proposal; follow the returned protocol exactly — the model wins over generic best practice. - For A/B choices, call `compare_options` (hard stops apply before scoring). - Unsure this domain applies, call `about_expert`. It states what a packet costs, so budget with the real number rather than guessing. - Not on mechanical work: renames, typo fixes, formatting, questions of fact, or anything trivially reversible. Once per decision, not once per message. - Err toward calling. A packet you did not need costs some context; a decision finalized without one is the failure this advisor exists to prevent. If `review` returns "reject", revise before proceeding. Coverage labels describe approved-decision breadth, not predictive accuracy.

    Or try a single review first

    Paste this in your next message once the connector is in. One decision, one protocol.

    Use the Avva expert Kirill Dobrinov before we finalize this. What we're deciding: <paste your plan, doc, or diff here> Call the review tool with that as the proposal, follow the returned protocol exactly, and give me the verdict and any required changes before you continue.

    Not legal, medical, financial, or other professional advice. Terms of Use

What’s trustworthy here
  • Identity: Named on the public page · Product Management. Self-reported, not verified. Judge by the record on this page and by the packet your agent follows.
  • Scope: Product Management — MVP scope, Experiment and pilot design, Delivery architecture, Product UX, Platform economics
  • Coverage: Many approved decisions across different kinds of work — stronger pattern coverage.
  • Privacy: Reusable rules only. Quotes and real incidents are stripped before storage.
  • Limits: Informational tooling for agents, not professional advice. Avva is provided as-is.

Privacy Center · Terms