---
title: "Mikhail Golikov (@golikovichev) | Hashnode"
description: "Software engineer building open-source Python testing tools (postman2pytest, secure-log2test, pytest-conversational). Test automation, pytest, CI. Background..."
url: "https://hashnode.com/@golikovichev"
---

@golikovichev

# Mikhail Golikov

@golikovichev · Hove · Joined May 2026

## Comments

[This matches my experience more than most automation writing. The line that lands hardest is "did the product break, or did the test break" - on a backend serving seven teams, as the only QA, that investigation was eating more of my week than writing the tests ever did. The flaky-as-trust-risk framing is right. Once people start re-running a red build by reflex, the suite has already lost. What helped me was refusing to label anything "flaky" as a category and instead forcing a class on every failure: timing, selector drift, data state, environment, or a real regression. A bucket you cannot name is usually one you have stopped reading. On AI as a junior QA that still needs review, agreed, and the review cost is real and recurring. A generated test that nobody on the team can debug six weeks later is not coverage, it is debt with a green checkmark. Question on your maintenance model: when a test survives a UI change without edits, how do you confirm it still asserts the original intent and did not quietly degrade into a weaker check that just happens to pass?](https://hashnode.com/posts/the-state-of-test-automation-maintenance-what-qa-engineers-actually-say/6a2d3b2f72a2370e3d5ab9af/comment/6a2de31173117c915f41aceb)

Comment · Article · Jun 13 · [The State of Test Automation Maintenance: What QA Engineers Actually Say](https://hashnode.com/posts/the-state-of-test-automation-maintenance-what-qa-engineers-actually-say/6a2d3b2f72a2370e3d5ab9af)

[The "testing and debugging tools" line in your AI agent platform checklist is the part that hits closest to real production pain. We built pytest-conversational for the same reason: when an AI agent handles 8 turns of multi-step support flow, manual QA can't reliably catch when turn 5 stops following the deterministic part of the workflow because the LLM reasoning step started leaking past the controlled boundary. The approach we landed on: keep the assertions deterministic (rule-based matchers on turn N response shape, role-based permissions, expected tool calls), and let only the agent reasoning be probabilistic. So tests can express things like "if user says X at turn 3, system MUST call tool Y with parameter Z extracted from turn 1, and MUST NOT skip the human handoff trigger at turn 5". Zero LLM in the test side - fully reproducible, runnable in CI without token costs. What surprised us: the more flexible the agent (Hexabot pattern, structured workflow + AI reasoning), the more important determinism on the test side becomes. If both the agent AND the test suite use AI to evaluate output, you have two non-deterministic systems judging each other and the failure modes compound silently. Question: how do you handle workflow versioning for tests? If a tool changes signature between versions of the workflow, do test fixtures auto-detect mismatch or do you rely on integration tests catching the drift after deploy?](https://hashnode.com/posts/from-chatbot-to-ai-agent-how-conversational-automation-is-evolving/6a1db351cc268013976be77b/comment/6a1dd4cb328352c4a377aff7)

Comment · Article · Jun 1 · 1 · [From Chatbot to AI Agent: How Conversational Automation Is Evolving](https://hashnode.com/posts/from-chatbot-to-ai-agent-how-conversational-automation-is-evolving/6a1db351cc268013976be77b)
