Meetups

Monday, November 30, 2026 at 6:00 PM

AI coding tools shine in clean tutorials and side projects. But what happens when you bring them to a 500,000-line codebase with years of history, cross-service dependencies, and a strong team style? This is a practical talk — no demos prepared in advance. We'll open real codebases on the web together, throw the same problems at AI coding tools, and you'll decide for yourself whether the result holds up. We'll work through 10 practical cases drawn from real engineering work on large codebases: 1. Adding a feature end-to-end across a monorepo (DB → API → frontend), without manual orchestration. 2. Removing a deprecated library from hundreds of call sites in one pass. 3. Porting a service between languages (e.g., Python → Go) while preserving behavior. 4. Generating test coverage for legacy modules that have never been tested. 5. Refactoring duplicated code spread across many files and services. 6. Migrating major framework versions (React, Next.js, Strapi) with breaking changes. 7. Onboarding a new engineer — letting them query the codebase instead of reading docs for a week. 8. Running parallel YOLO-mode development across 3+ independent tasks at once. 9. Auditing a large codebase against security and compliance guardrails. 10. Implementing a feature directly from a PDF spec — an RFC, a book chapter, or an internal design doc. Evgeny Potapov, engineering manager with over 20 years of experience and co-founder of ApexData, will share what consistently works and what still breaks on large codebases, with concrete prompts you can take home and try. For developers, tech leads, and engineering managers who already use AI coding tools but want to push them further on real code.

Saturday, October 31, 2026 at 6:00 PM

AI coding tools shine in clean tutorials and side projects. But what happens when you bring them to a 500,000-line codebase with years of history, cross-service dependencies, and a strong team style? This is a practical talk — no demos prepared in advance. We'll open real codebases on the web together, throw the same problems at AI coding tools, and you'll decide for yourself whether the result holds up. We'll work through 10 practical cases drawn from real engineering work on large codebases: 1. Adding a feature end-to-end across a monorepo (DB → API → frontend), without manual orchestration. 2. Removing a deprecated library from hundreds of call sites in one pass. 3. Porting a service between languages (e.g., Python → Go) while preserving behavior. 4. Generating test coverage for legacy modules that have never been tested. 5. Refactoring duplicated code spread across many files and services. 6. Migrating major framework versions (React, Next.js, Strapi) with breaking changes. 7. Onboarding a new engineer — letting them query the codebase instead of reading docs for a week. 8. Running parallel YOLO-mode development across 3+ independent tasks at once. 9. Auditing a large codebase against security and compliance guardrails. 10. Implementing a feature directly from a PDF spec — an RFC, a book chapter, or an internal design doc. Evgeny Potapov, engineering manager with over 20 years of experience and co-founder of ApexData, will share what consistently works and what still breaks on large codebases, with concrete prompts you can take home and try. For developers, tech leads, and engineering managers who already use AI coding tools but want to push them further on real code.

Wednesday, September 30, 2026 at 6:00 PM

AI coding tools shine in clean tutorials and side projects. But what happens when you bring them to a 500,000-line codebase with years of history, cross-service dependencies, and a strong team style? This is a practical talk — no demos prepared in advance. We'll open real codebases on the web together, throw the same problems at AI coding tools, and you'll decide for yourself whether the result holds up. We'll work through 10 practical cases drawn from real engineering work on large codebases: 1. Adding a feature end-to-end across a monorepo (DB → API → frontend), without manual orchestration. 2. Removing a deprecated library from hundreds of call sites in one pass. 3. Porting a service between languages (e.g., Python → Go) while preserving behavior. 4. Generating test coverage for legacy modules that have never been tested. 5. Refactoring duplicated code spread across many files and services. 6. Migrating major framework versions (React, Next.js, Strapi) with breaking changes. 7. Onboarding a new engineer — letting them query the codebase instead of reading docs for a week. 8. Running parallel YOLO-mode development across 3+ independent tasks at once. 9. Auditing a large codebase against security and compliance guardrails. 10. Implementing a feature directly from a PDF spec — an RFC, a book chapter, or an internal design doc. Evgeny Potapov, engineering manager with over 20 years of experience and co-founder of ApexData, will share what consistently works and what still breaks on large codebases, with concrete prompts you can take home and try. For developers, tech leads, and engineering managers who already use AI coding tools but want to push them further on real code.

Thursday, July 2, 2026 at 4:30 PM

AI coding tools shine in clean tutorials and side projects. But what happens when you bring them to a 500,000-line codebase with years of history, cross-service dependencies, and a strong team style? This is a practical talk — no demos prepared in advance. We'll open real codebases on the web together, throw the same problems at AI coding tools, and you'll decide for yourself whether the result holds up. We'll work through 10 practical cases drawn from real engineering work on large codebases: 1. Adding a feature end-to-end across a monorepo (DB → API → frontend), without manual orchestration. 2. Removing a deprecated library from hundreds of call sites in one pass. 3. Porting a service between languages (e.g., Python → Go) while preserving behavior. 4. Generating test coverage for legacy modules that have never been tested. 5. Refactoring duplicated code spread across many files and services. 6. Migrating major framework versions (React, Next.js, Strapi) with breaking changes. 7. Onboarding a new engineer — letting them query the codebase instead of reading docs for a week. 8. Running parallel YOLO-mode development across 3+ independent tasks at once. 9. Auditing a large codebase against security and compliance guardrails. 10. Implementing a feature directly from a PDF spec — an RFC, a book chapter, or an internal design doc. Evgeny Potapov, engineering manager with over 20 years of experience and co-founder of ApexData, will share what consistently works and what still breaks on large codebases, with concrete prompts you can take home and try. For developers, tech leads, and engineering managers who already use AI coding tools but want to push them further on real code.

Thursday, June 25, 2026 at 4:30 PM

AI coding tools shine in clean tutorials and side projects. But what happens when you bring them to a 500,000-line codebase with years of history, cross-service dependencies, and a strong team style? This is a practical talk — no demos prepared in advance. We'll open real codebases on the web together, throw the same problems at AI coding tools, and you'll decide for yourself whether the result holds up. We'll work through 10 practical cases drawn from real engineering work on large codebases: 1. Adding a feature end-to-end across a monorepo (DB → API → frontend), without manual orchestration. 2. Removing a deprecated library from hundreds of call sites in one pass. 3. Porting a service between languages (e.g., Python → Go) while preserving behavior. 4. Generating test coverage for legacy modules that have never been tested. 5. Refactoring duplicated code spread across many files and services. 6. Migrating major framework versions (React, Next.js, Strapi) with breaking changes. 7. Onboarding a new engineer — letting them query the codebase instead of reading docs for a week. 8. Running parallel YOLO-mode development across 3+ independent tasks at once. 9. Auditing a large codebase against security and compliance guardrails. 10. Implementing a feature directly from a PDF spec — an RFC, a book chapter, or an internal design doc. Evgeny Potapov, engineering manager with over 20 years of experience and co-founder of ApexData, will share what consistently works and what still breaks on large codebases, with concrete prompts you can take home and try. For developers, tech leads, and engineering managers who already use AI coding tools but want to push them further on real code.

Thursday, January 15, 2026 at 4:30 PM

AI coding tools are everywhere now, but adoption is uneven. Some developers use them daily; others remain skeptical. Getting a whole team on board is harder than it looks. This meetup explores the practical side of that challenge — how to bridge the gap between enthusiasts and skeptics, and what actually works when rolling out AI coding across a team. Evgeny Potapov, engineering manager with over 20 years of experience and cofounder of US-based startup ApexData, will share lessons from 1.5 years of navigating this shift: — Why some developers hesitate, and the psychology behind it — What gets adopted easily, and which team practices help — When AI coding won't work and forcing adoption makes no sense — How to push back when AI is the wrong tool for the job If you're a developer, tech lead, or engineering manager facing similar questions, this is a chance to learn from real experience and connect with others on the same path.

Saturday, November 22, 2025 at 7:00 AM

Join us for a deep, hands-on session with Evgeny Potapov, Co-Founder & CEO of ApexData — a US/Armenian developer-focused observability startup. – The evolution of AI-first development: from ChatGPT hints to near-autonomous coding with Claude Code & Codex ​– Why Cursor is losing the race — and what makes Claude Code + Codex CLI fundamentally different ​– Deep dive into Claude Code: planning, debugging, TDD-first workflows, subagents, Anthropic Skills, and the SuperPowers plugin ​– The YOLO (“You Only Live Once”) method for building side-projects autonomously ​– Live workshop: developing and modifying an app using the newest AI-driven techniques