Heap Today, Gone Tomorrow

Presentation byJan Peer

Your Node.js app is bleeding memory and users are hitting OOM errors in production. In this talk, I'll walk through a real debugging story on Cloudflare, how I used Claude Code and the Chrome DevTools MCP to automate the entire investigation loop. What used to take days of manual profiling became a tight, automated feedback loop. Heap today, gone tomorrow.

Jan Peer https://www.linkedin.com/in/jpeer/

Presented with these Guilds
Cover Photo for AI for Engineers London
Primary Photo for AI for Engineers London

AI for Engineers London

Practical AI for Software Engineers - dev tools in SDLC, core patterns for LLM implementation

AI for Engineers London is a community for software engineers who want to harness AI to build better software, faster.

We focus on the engineering side of AI, not ML/data science, sharing battle-tested approaches, practical tools, and proven patterns that transform how you write, test, deploy, and maintain code today.

Join us for monthly meetups featuring live demos, case studies from London tech companies.

For collaborations, reach events@gitnation.org

Topics covered:

🛠️ AI-Enhanced Development & Delivery

Development Acceleration

  • Code generation with Claude Code, GitHub Copilot, Cursor, and emerging tools
  • Automated code reviews, refactoring, and documentation generation
  • Test generation and intelligent debugging assistance
  • Building with MCP servers, LangGraph, CrewAI, and agent orchestration frameworks
  • Smart monitoring, alerting, and root cause analysis
  • Self-healing systems and automated incident response

🔧 Practical LLM Integration Patterns

Learn proven patterns for adding AI capabilities to your applications without complexity:

Core Integration Patterns

  • RAG (Retrieval-Augmented Generation): Connect LLMs to your databases and documentation to answer questions using your own data — no model training required
  • LLM optimizations
  • Prompt Templates & Chaining: Structure prompts for consistent outputs and chain multiple AI calls for complex tasks
  • Input/Output Validation: Add guardrails to ensure AI responses meet your requirements — from JSON schemas to content filtering

And other topics within core theme of the group

Similar Presentations
Cover Photo for High-Performance Node.js: From Event Loop Mastery to Production Observability

High-Performance Node.js: From Event Loop Mastery to Production Observability

What You'll Learn:

Event Loop Optimization & Performance - Understand how the event loop really works and learn Matteo Collina's proven techniques for preventing blocking operations. We'll explore the perf_hooks module for identifying performance bottlenecks, plus practical strategies for handling CPU-intensive tasks without freezing your application.

Strategic Caching Patterns - Implement multi-layered caching strategies using Redis, in-memory stores, and HTTP caching headers. Learn when to cache, what to cache, and how to invalidate cache effectively in distributed systems.

Promise Pitfalls & Alternatives - Discover when promises become performance liabilities and explore alternatives like streams and async iterators. We'll cover memory management and the hidden costs of promise chains in high-throughput scenarios.

Worker Threads & Multithreading - Master Node.js worker threads for CPU-bound tasks, following best practices for thread pool management and data sharing. Learn when to use worker threads versus child processes, and how to architect applications that leverage multiple cores effectively.

Production Metrics & Monitoring - Implement comprehensive application metrics using Prometheus and learn to instrument your code for meaningful observability. We'll cover custom metrics, histograms, and performance-tracking patterns used in production environments.

OpenTelemetry Integration - Setup distributed tracing with OpenTelemetry to track requests across microservices. Learn to integrate with distributed systems while maintaining performance and gaining deep insights into your application's behavior through standardized telemetry collection.

By the end of this workshop, you'll have the tools and knowledge to build Node.js applications that perform well under pressure, scale horizontally, and provide the observability needed for production operations.

Prerequisites: Solid understanding of JavaScript, Node.js fundamentals, and basic async/await patterns.

Matteo Collina

Heap Today, Gone Tomorrow

Presentation byJan Peer

Your Node.js app is bleeding memory and users are hitting OOM errors in production. In this talk, I'll walk through a real debugging story on Cloudflare, how I used Claude Code and the Chrome DevTools MCP to automate the entire investigation loop. What used to take days of manual profiling became a tight, automated feedback loop. Heap today, gone tomorrow.

Jan Peer https://www.linkedin.com/in/jpeer/

Presented with these Guilds
Cover Photo for AI for Engineers London
Primary Photo for AI for Engineers London

AI for Engineers London

Practical AI for Software Engineers - dev tools in SDLC, core patterns for LLM implementation

AI for Engineers London is a community for software engineers who want to harness AI to build better software, faster.

We focus on the engineering side of AI, not ML/data science, sharing battle-tested approaches, practical tools, and proven patterns that transform how you write, test, deploy, and maintain code today.

Join us for monthly meetups featuring live demos, case studies from London tech companies.

For collaborations, reach events@gitnation.org

Topics covered:

🛠️ AI-Enhanced Development & Delivery

Development Acceleration

  • Code generation with Claude Code, GitHub Copilot, Cursor, and emerging tools
  • Automated code reviews, refactoring, and documentation generation
  • Test generation and intelligent debugging assistance
  • Building with MCP servers, LangGraph, CrewAI, and agent orchestration frameworks
  • Smart monitoring, alerting, and root cause analysis
  • Self-healing systems and automated incident response

🔧 Practical LLM Integration Patterns

Learn proven patterns for adding AI capabilities to your applications without complexity:

Core Integration Patterns

  • RAG (Retrieval-Augmented Generation): Connect LLMs to your databases and documentation to answer questions using your own data — no model training required
  • LLM optimizations
  • Prompt Templates & Chaining: Structure prompts for consistent outputs and chain multiple AI calls for complex tasks
  • Input/Output Validation: Add guardrails to ensure AI responses meet your requirements — from JSON schemas to content filtering

And other topics within core theme of the group

Similar Presentations
Cover Photo for High-Performance Node.js: From Event Loop Mastery to Production Observability

High-Performance Node.js: From Event Loop Mastery to Production Observability

What You'll Learn:

Event Loop Optimization & Performance - Understand how the event loop really works and learn Matteo Collina's proven techniques for preventing blocking operations. We'll explore the perf_hooks module for identifying performance bottlenecks, plus practical strategies for handling CPU-intensive tasks without freezing your application.

Strategic Caching Patterns - Implement multi-layered caching strategies using Redis, in-memory stores, and HTTP caching headers. Learn when to cache, what to cache, and how to invalidate cache effectively in distributed systems.

Promise Pitfalls & Alternatives - Discover when promises become performance liabilities and explore alternatives like streams and async iterators. We'll cover memory management and the hidden costs of promise chains in high-throughput scenarios.

Worker Threads & Multithreading - Master Node.js worker threads for CPU-bound tasks, following best practices for thread pool management and data sharing. Learn when to use worker threads versus child processes, and how to architect applications that leverage multiple cores effectively.

Production Metrics & Monitoring - Implement comprehensive application metrics using Prometheus and learn to instrument your code for meaningful observability. We'll cover custom metrics, histograms, and performance-tracking patterns used in production environments.

OpenTelemetry Integration - Setup distributed tracing with OpenTelemetry to track requests across microservices. Learn to integrate with distributed systems while maintaining performance and gaining deep insights into your application's behavior through standardized telemetry collection.

By the end of this workshop, you'll have the tools and knowledge to build Node.js applications that perform well under pressure, scale horizontally, and provide the observability needed for production operations.

Prerequisites: Solid understanding of JavaScript, Node.js fundamentals, and basic async/await patterns.

Matteo Collina

Get in touch!

hi@guild.host